mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Replace CRLF line endings
This commit is contained in:
Kovid Goyal
parent
a1ce980d99
commit
c0f549625a
File diff suppressed because it is too large
Load Diff
@ -1,157 +1,157 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<!-- Generator: Adobe Illustrator 14.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 43363) -->
|
||||
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
|
||||
<svg version="1.1" id="svg2" xmlns:svg="http://www.w3.org/2000/svg" xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
|
||||
xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" width="128px" height="128px"
|
||||
viewBox="0 0 128 128" enable-background="new 0 0 128 128" xml:space="preserve">
|
||||
<filter id="filter5365">
|
||||
<feGaussianBlur stdDeviation="1.3829225" inkscape:collect="always" id="feGaussianBlur5367"></feGaussianBlur>
|
||||
</filter>
|
||||
<g id="layer1">
|
||||
</g>
|
||||
<g id="layer2">
|
||||
<polygon id="rect3200" opacity="0.5722" fill="#0000A4" enable-background="new " points="167.5,297.005 171.429,297.005
|
||||
171.429,297.005 "/>
|
||||
<g id="path5265" filter="url(#filter5365)">
|
||||
<polygon fill="#362D2D" points="21.951,79.904 70.397,63.09 119.953,80.636 70.397,97.084 "/>
|
||||
<polygon fill="none" stroke="#362D2D" stroke-width="1.2507" stroke-linejoin="bevel" points="21.951,79.904 70.397,63.09
|
||||
119.953,80.636 70.397,97.084 "/>
|
||||
</g>
|
||||
<g id="path5267" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M118.639,100.902v1.724l-46.437,15.432c-3.723-9.284-1.901-16.34,0.089-20.69l46.883-15.518l-6.34,2.068
|
||||
l2.322,16.553L118.639,100.902z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.9" d="M118.639,100.902v1.724l-46.437,15.432
|
||||
c-3.723-9.284-1.901-16.34,0.089-20.69l46.883-15.518l-6.34,2.068l2.322,16.553L118.639,100.902z"/>
|
||||
</g>
|
||||
<g id="path5269" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M70.711,98.81l47.581-15.743l0.29,18.582l-47.56,15.986c0,0-1.515-3.455-1.942-9.812
|
||||
C68.936,101.726,70.711,98.81,70.711,98.81z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.1" d="M70.711,98.81l47.581-15.743l0.29,18.582l-47.56,15.986
|
||||
c0,0-1.515-3.455-1.942-9.812C68.936,101.726,70.711,98.81,70.711,98.81z"/>
|
||||
</g>
|
||||
<g id="path5271" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M21.479,79.607l49.115,17.501c-3.287,7.816-2.385,15.202,0.982,23.019l-50.008-16.208
|
||||
C17.974,94.288,17.113,87.874,21.479,79.607z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.6" d="M21.479,79.607l49.115,17.501c-3.287,7.816-2.385,15.202,0.982,23.019
|
||||
l-50.008-16.208C17.974,94.288,17.113,87.874,21.479,79.607z"/>
|
||||
</g>
|
||||
<g id="path5273" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M120.871,99.092v4.827l-50.008,16.897l-49.651-15.863c-4.763-11.162-1.987-18.682,0.714-25.346
|
||||
l49.651-16.724l48.579,17.242v3.449l-2.143,1.033l0.357,14.139L120.871,99.092z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.7" stroke-linejoin="bevel" d="M120.871,99.092v4.827l-50.008,16.897
|
||||
l-49.651-15.863c-4.763-11.162-1.987-18.682,0.714-25.346l49.651-16.724l48.579,17.242v3.449l-2.143,1.033l0.357,14.139
|
||||
L120.871,99.092z"/>
|
||||
</g>
|
||||
<path id="path5385" fill="#78CE4F" d="M19.316,78.05l48.438-17.414l49.548,18.171L67.754,95.842L19.316,78.05z"/>
|
||||
<path id="path5387" fill="none" stroke="#0F973B" stroke-width="1.9" d="M115.988,99.796v1.786l-46.43,15.982
|
||||
c-3.722-9.616-1.901-16.924,0.09-21.43l46.875-16.07l-6.34,2.143l2.322,17.143L115.988,99.796z"/>
|
||||
|
||||
<radialGradient id="path5389_1_" cx="498.3457" cy="267.1621" r="27.1927" gradientTransform="matrix(-0.064 0.175 1.8694 0.6835 -425.1342 -169.6643)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#B5FFA6"/>
|
||||
<stop offset="1" style="stop-color:#76E976"/>
|
||||
</radialGradient>
|
||||
<path id="path5389" fill="url(#path5389_1_)" stroke="#003131" stroke-width="1.6" stroke-opacity="0.9608" d="M18.845,77.742
|
||||
l49.107,18.125c-3.287,8.096-2.385,15.744,0.981,23.84l-50-16.786C15.339,92.946,14.479,86.304,18.845,77.742z"/>
|
||||
<path id="path5391" fill="none" stroke="#003131" stroke-width="2.7" stroke-linejoin="bevel" stroke-opacity="0.9608" d="
|
||||
M118.22,97.921v5l-50,17.5l-49.643-16.429c-4.762-11.561-1.987-19.348,0.714-26.25l49.642-17.321l48.572,17.857v3.571l-2.143,1.071
|
||||
l0.356,14.644L118.22,97.921z"/>
|
||||
<path id="path5393" fill="#FFFFFF" d="M68.068,97.629l47.572-16.305l0.29,19.245l-47.194,16.423c0,0-1.424-2.819-2.12-10.029
|
||||
C66.471,100.649,68.068,97.629,68.068,97.629z"/>
|
||||
<g id="path5419" filter="url(#filter5365)">
|
||||
<polygon fill="#362D2D" points="8.737,52.047 57.183,35.233 106.738,52.778 57.183,69.227 "/>
|
||||
<polygon fill="none" stroke="#362D2D" stroke-width="1.2507" stroke-linejoin="bevel" points="8.737,52.047 57.183,35.233
|
||||
106.738,52.778 57.183,69.227 "/>
|
||||
</g>
|
||||
<g id="path5421" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M105.424,73.045v1.724L58.988,90.2c-3.723-9.284-1.902-16.34,0.089-20.69l46.882-15.518l-6.341,2.069
|
||||
l2.322,16.552L105.424,73.045z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.9" d="M105.424,73.045v1.724L58.988,90.2
|
||||
c-3.723-9.284-1.902-16.34,0.089-20.69l46.882-15.518l-6.341,2.069l2.322,16.552L105.424,73.045z"/>
|
||||
</g>
|
||||
<g id="path5423" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M57.497,70.953l47.581-15.744l0.289,18.582L57.809,89.777c0,0-1.515-3.455-1.942-9.812
|
||||
C55.721,73.869,57.497,70.953,57.497,70.953z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.1" d="M57.497,70.953l47.581-15.744l0.289,18.582L57.809,89.777
|
||||
c0,0-1.515-3.455-1.942-9.812C55.721,73.869,57.497,70.953,57.497,70.953z"/>
|
||||
</g>
|
||||
<g id="path5425" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M8.265,51.751l49.116,17.501c-3.288,7.816-2.385,15.201,0.982,23.018L8.354,76.062
|
||||
C4.759,66.431,3.899,60.017,8.265,51.751z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.6" d="M8.265,51.751l49.116,17.501c-3.288,7.816-2.385,15.201,0.982,23.018
|
||||
L8.354,76.062C4.759,66.431,3.899,60.017,8.265,51.751z"/>
|
||||
</g>
|
||||
<g id="path5427" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M107.656,71.234v4.828L57.648,92.959L7.998,77.097C3.234,65.934,6.011,58.415,8.712,51.751l49.651-16.725
|
||||
l48.58,17.242v3.448l-2.144,1.035l0.357,14.139L107.656,71.234z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.7" stroke-linejoin="bevel" d="M107.656,71.234v4.828L57.648,92.959
|
||||
L7.998,77.097C3.234,65.934,6.011,58.415,8.712,51.751l49.651-16.725l48.58,17.242v3.448l-2.144,1.035l0.357,14.139
|
||||
L107.656,71.234z"/>
|
||||
</g>
|
||||
<path id="path5431" fill="#60BAFF" stroke="#003244" stroke-width="1.2507" stroke-linejoin="bevel" d="M6.102,50.193L54.54,32.779
|
||||
l49.548,18.171L54.54,67.985L6.102,50.193z"/>
|
||||
<path id="path5433" fill="none" stroke="#0056D5" stroke-width="2.8104" d="M102.768,71.76v1.803L56.35,89.701
|
||||
c-3.721-9.71-1.901-17.089,0.089-21.639l46.865-16.229l-6.338,2.164l2.321,17.312L102.768,71.76z"/>
|
||||
|
||||
<radialGradient id="path5435_1_" cx="316.8916" cy="261.2949" r="27.1937" gradientTransform="matrix(-0.0902 0.2793 1.9257 0.6218 -445.576 -180.1955)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#789DED"/>
|
||||
<stop offset="1" style="stop-color:#2381E8"/>
|
||||
</radialGradient>
|
||||
<path id="path5435" fill="url(#path5435_1_)" stroke="#003244" stroke-width="1.6" d="M5.63,49.885L54.738,68.01
|
||||
c-3.287,8.096-2.385,15.744,0.982,23.84l-50-16.785C2.125,65.09,1.265,58.447,5.63,49.885z"/>
|
||||
<path id="path5437" fill="none" stroke="#003244" stroke-width="2.7" stroke-linejoin="bevel" d="M105.006,70.064v5l-50,17.5
|
||||
L5.363,76.135c-4.762-11.561-1.987-19.348,0.714-26.25L55.72,32.564l48.571,17.857v3.572l-2.143,1.071l0.357,14.643L105.006,70.064
|
||||
z"/>
|
||||
<path id="path5439" fill="#FFFFFF" d="M54.854,69.772l47.573-16.306l0.29,19.245L55.522,89.135c0,0-1.425-2.819-2.121-10.028
|
||||
C53.256,72.793,54.854,69.772,54.854,69.772z"/>
|
||||
<g id="path5447" filter="url(#filter5365)">
|
||||
<polygon fill="#362D2D" points="25.88,28.119 74.326,11.305 123.882,28.85 74.326,45.299 "/>
|
||||
<polygon fill="none" stroke="#362D2D" stroke-width="1.2507" stroke-linejoin="bevel" points="25.88,28.119 74.326,11.305
|
||||
123.882,28.85 74.326,45.299 "/>
|
||||
</g>
|
||||
<g id="path5449" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M122.567,49.116v1.724L76.131,66.271c-3.723-9.284-1.902-16.34,0.09-20.69l46.883-15.518l-6.341,2.069
|
||||
l2.321,16.552L122.567,49.116z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.9" d="M122.567,49.116v1.724L76.131,66.271
|
||||
c-3.723-9.284-1.902-16.34,0.09-20.69l46.883-15.518l-6.341,2.069l2.321,16.552L122.567,49.116z"/>
|
||||
</g>
|
||||
<g id="path5451" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M74.641,47.024l47.58-15.744l0.289,18.582L74.951,65.849c0,0-1.514-3.455-1.941-9.812
|
||||
C72.863,49.94,74.641,47.024,74.641,47.024z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.1" d="M74.641,47.024l47.58-15.744l0.289,18.582L74.951,65.849
|
||||
c0,0-1.514-3.455-1.941-9.812C72.863,49.94,74.641,47.024,74.641,47.024z"/>
|
||||
</g>
|
||||
<g id="path5453" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M25.408,27.822l49.115,17.5c-3.287,7.816-2.385,15.202,0.982,23.018L25.498,52.133
|
||||
C21.902,42.502,21.042,36.088,25.408,27.822z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.6" d="M25.408,27.822l49.115,17.5c-3.287,7.816-2.385,15.202,0.982,23.018
|
||||
L25.498,52.133C21.902,42.502,21.042,36.088,25.408,27.822z"/>
|
||||
</g>
|
||||
<g id="path5455" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M124.8,47.306v4.828L74.791,69.03L25.14,53.168c-4.763-11.163-1.987-18.682,0.714-25.346l49.651-16.725
|
||||
l48.58,17.242v3.449l-2.145,1.034l0.357,14.139L124.8,47.306z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.7" stroke-linejoin="bevel" d="M124.8,47.306v4.828L74.791,69.03L25.14,53.168
|
||||
c-4.763-11.163-1.987-18.682,0.714-25.346l49.651-16.725l48.58,17.242v3.449l-2.145,1.034l0.357,14.139L124.8,47.306z"/>
|
||||
</g>
|
||||
<path id="path5459" fill="#FF7272" d="M23.245,26.264L71.684,8.85l49.547,18.171L71.684,44.057L23.245,26.264z"/>
|
||||
<path id="path5461" fill="none" stroke="#CF0505" stroke-width="1.9" d="M119.916,48.01v1.786L73.488,65.778
|
||||
c-3.723-9.616-1.902-16.923,0.089-21.429l46.875-16.071l-6.339,2.143l2.32,17.143L119.916,48.01z"/>
|
||||
|
||||
<radialGradient id="path5463_1_" cx="14.938" cy="-466.4766" r="27.3207" gradientTransform="matrix(2.5834 0.998 0.0835 -0.2162 46.7076 -68.8071)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#FD8A8A"/>
|
||||
<stop offset="1" style="stop-color:#FF7878"/>
|
||||
</radialGradient>
|
||||
<path id="path5463" fill="url(#path5463_1_)" stroke="#600101" stroke-width="1.6" d="M22.773,25.957l49.107,18.125
|
||||
c-3.287,8.095-2.385,15.744,0.982,23.839l-50-18.806C19.268,39.14,18.408,34.518,22.773,25.957z"/>
|
||||
|
||||
<linearGradient id="path3311_1_" gradientUnits="userSpaceOnUse" x1="-1.3145" y1="103.2168" x2="67.4683" y2="103.2168" gradientTransform="matrix(1 0 0 -1 5.4287 129.1426)">
|
||||
<stop offset="0" style="stop-color:#FFFFFF"/>
|
||||
<stop offset="1" style="stop-color:#FFFFFF;stop-opacity:0.2471"/>
|
||||
</linearGradient>
|
||||
<path id="path3311" fill="url(#path3311_1_)" d="M23.904,25.736L72.342,8.322l49.548,18.171L72.342,43.529L23.904,25.736z"/>
|
||||
<path id="path5465" fill="none" stroke="#600101" stroke-width="2.7" stroke-linejoin="bevel" d="M122.148,46.135v5l-50,17.5
|
||||
l-49.39-18.701c-4.762-11.562-2.239-17.076,0.461-23.977L72.863,8.635l48.57,17.857v3.571l-2.143,1.071l0.357,14.643
|
||||
L122.148,46.135z"/>
|
||||
<path id="path5467" fill="#FFFFFF" d="M71.997,45.844l47.573-16.306l0.289,19.246L72.666,65.206c0,0-1.426-2.819-2.121-10.028
|
||||
C70.399,48.864,71.997,45.844,71.997,45.844z"/>
|
||||
</g>
|
||||
</svg>
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<!-- Generator: Adobe Illustrator 14.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 43363) -->
|
||||
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
|
||||
<svg version="1.1" id="svg2" xmlns:svg="http://www.w3.org/2000/svg" xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
|
||||
xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" width="128px" height="128px"
|
||||
viewBox="0 0 128 128" enable-background="new 0 0 128 128" xml:space="preserve">
|
||||
<filter id="filter5365">
|
||||
<feGaussianBlur stdDeviation="1.3829225" inkscape:collect="always" id="feGaussianBlur5367"></feGaussianBlur>
|
||||
</filter>
|
||||
<g id="layer1">
|
||||
</g>
|
||||
<g id="layer2">
|
||||
<polygon id="rect3200" opacity="0.5722" fill="#0000A4" enable-background="new " points="167.5,297.005 171.429,297.005
|
||||
171.429,297.005 "/>
|
||||
<g id="path5265" filter="url(#filter5365)">
|
||||
<polygon fill="#362D2D" points="21.951,79.904 70.397,63.09 119.953,80.636 70.397,97.084 "/>
|
||||
<polygon fill="none" stroke="#362D2D" stroke-width="1.2507" stroke-linejoin="bevel" points="21.951,79.904 70.397,63.09
|
||||
119.953,80.636 70.397,97.084 "/>
|
||||
</g>
|
||||
<g id="path5267" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M118.639,100.902v1.724l-46.437,15.432c-3.723-9.284-1.901-16.34,0.089-20.69l46.883-15.518l-6.34,2.068
|
||||
l2.322,16.553L118.639,100.902z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.9" d="M118.639,100.902v1.724l-46.437,15.432
|
||||
c-3.723-9.284-1.901-16.34,0.089-20.69l46.883-15.518l-6.34,2.068l2.322,16.553L118.639,100.902z"/>
|
||||
</g>
|
||||
<g id="path5269" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M70.711,98.81l47.581-15.743l0.29,18.582l-47.56,15.986c0,0-1.515-3.455-1.942-9.812
|
||||
C68.936,101.726,70.711,98.81,70.711,98.81z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.1" d="M70.711,98.81l47.581-15.743l0.29,18.582l-47.56,15.986
|
||||
c0,0-1.515-3.455-1.942-9.812C68.936,101.726,70.711,98.81,70.711,98.81z"/>
|
||||
</g>
|
||||
<g id="path5271" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M21.479,79.607l49.115,17.501c-3.287,7.816-2.385,15.202,0.982,23.019l-50.008-16.208
|
||||
C17.974,94.288,17.113,87.874,21.479,79.607z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.6" d="M21.479,79.607l49.115,17.501c-3.287,7.816-2.385,15.202,0.982,23.019
|
||||
l-50.008-16.208C17.974,94.288,17.113,87.874,21.479,79.607z"/>
|
||||
</g>
|
||||
<g id="path5273" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M120.871,99.092v4.827l-50.008,16.897l-49.651-15.863c-4.763-11.162-1.987-18.682,0.714-25.346
|
||||
l49.651-16.724l48.579,17.242v3.449l-2.143,1.033l0.357,14.139L120.871,99.092z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.7" stroke-linejoin="bevel" d="M120.871,99.092v4.827l-50.008,16.897
|
||||
l-49.651-15.863c-4.763-11.162-1.987-18.682,0.714-25.346l49.651-16.724l48.579,17.242v3.449l-2.143,1.033l0.357,14.139
|
||||
L120.871,99.092z"/>
|
||||
</g>
|
||||
<path id="path5385" fill="#78CE4F" d="M19.316,78.05l48.438-17.414l49.548,18.171L67.754,95.842L19.316,78.05z"/>
|
||||
<path id="path5387" fill="none" stroke="#0F973B" stroke-width="1.9" d="M115.988,99.796v1.786l-46.43,15.982
|
||||
c-3.722-9.616-1.901-16.924,0.09-21.43l46.875-16.07l-6.34,2.143l2.322,17.143L115.988,99.796z"/>
|
||||
|
||||
<radialGradient id="path5389_1_" cx="498.3457" cy="267.1621" r="27.1927" gradientTransform="matrix(-0.064 0.175 1.8694 0.6835 -425.1342 -169.6643)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#B5FFA6"/>
|
||||
<stop offset="1" style="stop-color:#76E976"/>
|
||||
</radialGradient>
|
||||
<path id="path5389" fill="url(#path5389_1_)" stroke="#003131" stroke-width="1.6" stroke-opacity="0.9608" d="M18.845,77.742
|
||||
l49.107,18.125c-3.287,8.096-2.385,15.744,0.981,23.84l-50-16.786C15.339,92.946,14.479,86.304,18.845,77.742z"/>
|
||||
<path id="path5391" fill="none" stroke="#003131" stroke-width="2.7" stroke-linejoin="bevel" stroke-opacity="0.9608" d="
|
||||
M118.22,97.921v5l-50,17.5l-49.643-16.429c-4.762-11.561-1.987-19.348,0.714-26.25l49.642-17.321l48.572,17.857v3.571l-2.143,1.071
|
||||
l0.356,14.644L118.22,97.921z"/>
|
||||
<path id="path5393" fill="#FFFFFF" d="M68.068,97.629l47.572-16.305l0.29,19.245l-47.194,16.423c0,0-1.424-2.819-2.12-10.029
|
||||
C66.471,100.649,68.068,97.629,68.068,97.629z"/>
|
||||
<g id="path5419" filter="url(#filter5365)">
|
||||
<polygon fill="#362D2D" points="8.737,52.047 57.183,35.233 106.738,52.778 57.183,69.227 "/>
|
||||
<polygon fill="none" stroke="#362D2D" stroke-width="1.2507" stroke-linejoin="bevel" points="8.737,52.047 57.183,35.233
|
||||
106.738,52.778 57.183,69.227 "/>
|
||||
</g>
|
||||
<g id="path5421" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M105.424,73.045v1.724L58.988,90.2c-3.723-9.284-1.902-16.34,0.089-20.69l46.882-15.518l-6.341,2.069
|
||||
l2.322,16.552L105.424,73.045z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.9" d="M105.424,73.045v1.724L58.988,90.2
|
||||
c-3.723-9.284-1.902-16.34,0.089-20.69l46.882-15.518l-6.341,2.069l2.322,16.552L105.424,73.045z"/>
|
||||
</g>
|
||||
<g id="path5423" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M57.497,70.953l47.581-15.744l0.289,18.582L57.809,89.777c0,0-1.515-3.455-1.942-9.812
|
||||
C55.721,73.869,57.497,70.953,57.497,70.953z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.1" d="M57.497,70.953l47.581-15.744l0.289,18.582L57.809,89.777
|
||||
c0,0-1.515-3.455-1.942-9.812C55.721,73.869,57.497,70.953,57.497,70.953z"/>
|
||||
</g>
|
||||
<g id="path5425" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M8.265,51.751l49.116,17.501c-3.288,7.816-2.385,15.201,0.982,23.018L8.354,76.062
|
||||
C4.759,66.431,3.899,60.017,8.265,51.751z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.6" d="M8.265,51.751l49.116,17.501c-3.288,7.816-2.385,15.201,0.982,23.018
|
||||
L8.354,76.062C4.759,66.431,3.899,60.017,8.265,51.751z"/>
|
||||
</g>
|
||||
<g id="path5427" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M107.656,71.234v4.828L57.648,92.959L7.998,77.097C3.234,65.934,6.011,58.415,8.712,51.751l49.651-16.725
|
||||
l48.58,17.242v3.448l-2.144,1.035l0.357,14.139L107.656,71.234z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.7" stroke-linejoin="bevel" d="M107.656,71.234v4.828L57.648,92.959
|
||||
L7.998,77.097C3.234,65.934,6.011,58.415,8.712,51.751l49.651-16.725l48.58,17.242v3.448l-2.144,1.035l0.357,14.139
|
||||
L107.656,71.234z"/>
|
||||
</g>
|
||||
<path id="path5431" fill="#60BAFF" stroke="#003244" stroke-width="1.2507" stroke-linejoin="bevel" d="M6.102,50.193L54.54,32.779
|
||||
l49.548,18.171L54.54,67.985L6.102,50.193z"/>
|
||||
<path id="path5433" fill="none" stroke="#0056D5" stroke-width="2.8104" d="M102.768,71.76v1.803L56.35,89.701
|
||||
c-3.721-9.71-1.901-17.089,0.089-21.639l46.865-16.229l-6.338,2.164l2.321,17.312L102.768,71.76z"/>
|
||||
|
||||
<radialGradient id="path5435_1_" cx="316.8916" cy="261.2949" r="27.1937" gradientTransform="matrix(-0.0902 0.2793 1.9257 0.6218 -445.576 -180.1955)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#789DED"/>
|
||||
<stop offset="1" style="stop-color:#2381E8"/>
|
||||
</radialGradient>
|
||||
<path id="path5435" fill="url(#path5435_1_)" stroke="#003244" stroke-width="1.6" d="M5.63,49.885L54.738,68.01
|
||||
c-3.287,8.096-2.385,15.744,0.982,23.84l-50-16.785C2.125,65.09,1.265,58.447,5.63,49.885z"/>
|
||||
<path id="path5437" fill="none" stroke="#003244" stroke-width="2.7" stroke-linejoin="bevel" d="M105.006,70.064v5l-50,17.5
|
||||
L5.363,76.135c-4.762-11.561-1.987-19.348,0.714-26.25L55.72,32.564l48.571,17.857v3.572l-2.143,1.071l0.357,14.643L105.006,70.064
|
||||
z"/>
|
||||
<path id="path5439" fill="#FFFFFF" d="M54.854,69.772l47.573-16.306l0.29,19.245L55.522,89.135c0,0-1.425-2.819-2.121-10.028
|
||||
C53.256,72.793,54.854,69.772,54.854,69.772z"/>
|
||||
<g id="path5447" filter="url(#filter5365)">
|
||||
<polygon fill="#362D2D" points="25.88,28.119 74.326,11.305 123.882,28.85 74.326,45.299 "/>
|
||||
<polygon fill="none" stroke="#362D2D" stroke-width="1.2507" stroke-linejoin="bevel" points="25.88,28.119 74.326,11.305
|
||||
123.882,28.85 74.326,45.299 "/>
|
||||
</g>
|
||||
<g id="path5449" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M122.567,49.116v1.724L76.131,66.271c-3.723-9.284-1.902-16.34,0.09-20.69l46.883-15.518l-6.341,2.069
|
||||
l2.321,16.552L122.567,49.116z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.9" d="M122.567,49.116v1.724L76.131,66.271
|
||||
c-3.723-9.284-1.902-16.34,0.09-20.69l46.883-15.518l-6.341,2.069l2.321,16.552L122.567,49.116z"/>
|
||||
</g>
|
||||
<g id="path5451" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M74.641,47.024l47.58-15.744l0.289,18.582L74.951,65.849c0,0-1.514-3.455-1.941-9.812
|
||||
C72.863,49.94,74.641,47.024,74.641,47.024z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.1" d="M74.641,47.024l47.58-15.744l0.289,18.582L74.951,65.849
|
||||
c0,0-1.514-3.455-1.941-9.812C72.863,49.94,74.641,47.024,74.641,47.024z"/>
|
||||
</g>
|
||||
<g id="path5453" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M25.408,27.822l49.115,17.5c-3.287,7.816-2.385,15.202,0.982,23.018L25.498,52.133
|
||||
C21.902,42.502,21.042,36.088,25.408,27.822z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="1.6" d="M25.408,27.822l49.115,17.5c-3.287,7.816-2.385,15.202,0.982,23.018
|
||||
L25.498,52.133C21.902,42.502,21.042,36.088,25.408,27.822z"/>
|
||||
</g>
|
||||
<g id="path5455" filter="url(#filter5365)">
|
||||
<path fill="#362D2D" d="M124.8,47.306v4.828L74.791,69.03L25.14,53.168c-4.763-11.163-1.987-18.682,0.714-25.346l49.651-16.725
|
||||
l48.58,17.242v3.449l-2.145,1.034l0.357,14.139L124.8,47.306z"/>
|
||||
<path fill="none" stroke="#362D2D" stroke-width="2.7" stroke-linejoin="bevel" d="M124.8,47.306v4.828L74.791,69.03L25.14,53.168
|
||||
c-4.763-11.163-1.987-18.682,0.714-25.346l49.651-16.725l48.58,17.242v3.449l-2.145,1.034l0.357,14.139L124.8,47.306z"/>
|
||||
</g>
|
||||
<path id="path5459" fill="#FF7272" d="M23.245,26.264L71.684,8.85l49.547,18.171L71.684,44.057L23.245,26.264z"/>
|
||||
<path id="path5461" fill="none" stroke="#CF0505" stroke-width="1.9" d="M119.916,48.01v1.786L73.488,65.778
|
||||
c-3.723-9.616-1.902-16.923,0.089-21.429l46.875-16.071l-6.339,2.143l2.32,17.143L119.916,48.01z"/>
|
||||
|
||||
<radialGradient id="path5463_1_" cx="14.938" cy="-466.4766" r="27.3207" gradientTransform="matrix(2.5834 0.998 0.0835 -0.2162 46.7076 -68.8071)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#FD8A8A"/>
|
||||
<stop offset="1" style="stop-color:#FF7878"/>
|
||||
</radialGradient>
|
||||
<path id="path5463" fill="url(#path5463_1_)" stroke="#600101" stroke-width="1.6" d="M22.773,25.957l49.107,18.125
|
||||
c-3.287,8.095-2.385,15.744,0.982,23.839l-50-18.806C19.268,39.14,18.408,34.518,22.773,25.957z"/>
|
||||
|
||||
<linearGradient id="path3311_1_" gradientUnits="userSpaceOnUse" x1="-1.3145" y1="103.2168" x2="67.4683" y2="103.2168" gradientTransform="matrix(1 0 0 -1 5.4287 129.1426)">
|
||||
<stop offset="0" style="stop-color:#FFFFFF"/>
|
||||
<stop offset="1" style="stop-color:#FFFFFF;stop-opacity:0.2471"/>
|
||||
</linearGradient>
|
||||
<path id="path3311" fill="url(#path3311_1_)" d="M23.904,25.736L72.342,8.322l49.548,18.171L72.342,43.529L23.904,25.736z"/>
|
||||
<path id="path5465" fill="none" stroke="#600101" stroke-width="2.7" stroke-linejoin="bevel" d="M122.148,46.135v5l-50,17.5
|
||||
l-49.39-18.701c-4.762-11.562-2.239-17.076,0.461-23.977L72.863,8.635l48.57,17.857v3.571l-2.143,1.071l0.357,14.643
|
||||
L122.148,46.135z"/>
|
||||
<path id="path5467" fill="#FFFFFF" d="M71.997,45.844l47.573-16.306l0.289,19.246L72.666,65.206c0,0-1.426-2.819-2.121-10.028
|
||||
C70.399,48.864,71.997,45.844,71.997,45.844z"/>
|
||||
</g>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 11 KiB After Width: | Height: | Size: 11 KiB |
902
imgsrc/sd.svg
902
imgsrc/sd.svg
File diff suppressed because it is too large
Load Diff
|
Before Width: | Height: | Size: 473 KiB After Width: | Height: | Size: 472 KiB |
@ -1,32 +1,32 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<!-- Generator: Adobe Illustrator 15.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0) -->
|
||||
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
|
||||
<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
|
||||
width="181px" height="212px" viewBox="0 0 181 212" enable-background="new 0 0 181 212" xml:space="preserve">
|
||||
<g>
|
||||
<path fill="#FFFFFF" d="M105.134,97.504l-3.598,2.688l-4.197-5.618l-5.754,4.299l-1.733-2.32
|
||||
c19.007-16.602,22.311-45.299,6.955-65.852C80.691,9.133,50.143,4.711,28.574,20.826s-25.99,46.663-9.875,68.232
|
||||
c15.355,20.553,43.812,25.521,65.122,12l1.732,2.319l-5.755,4.3l4.198,5.619l-3.598,2.688l68.083,91.125l24.734-18.48
|
||||
L105.134,97.504z M29.113,81.277C17.296,65.46,20.538,43.058,36.355,31.24c15.816-11.817,38.219-8.575,50.036,7.242
|
||||
c11.817,15.817,8.575,38.22-7.241,50.037C63.333,100.337,40.931,97.094,29.113,81.277z"/>
|
||||
<g>
|
||||
<g>
|
||||
<path fill="#010101" d="M28.574,15.642C7.006,31.756,2.584,62.305,18.699,83.874c16.114,21.568,46.663,25.989,68.231,9.875
|
||||
c21.569-16.115,25.99-46.664,9.876-68.232C80.691,3.948,50.143-0.473,28.574,15.642z M79.15,83.335
|
||||
c-15.817,11.817-38.22,8.574-50.037-7.242c-11.817-15.817-8.575-38.219,7.242-50.037c15.816-11.817,38.219-8.575,50.036,7.242
|
||||
C98.209,49.115,94.967,71.517,79.15,83.335z"/>
|
||||
</g>
|
||||
|
||||
<rect x="83.577" y="89.507" transform="matrix(0.8011 -0.5986 0.5986 0.8011 -39.0685 71.0375)" fill="#010101" width="7.528" height="9.579"/>
|
||||
|
||||
<rect x="81.819" y="94.546" transform="matrix(0.8011 -0.5985 0.5985 0.8011 -42.3354 75.7256)" fill="#991A37" width="21.894" height="14.026"/>
|
||||
|
||||
<linearGradient id="SVGID_1_" gradientUnits="userSpaceOnUse" x1="98.5879" y1="122.3535" x2="129.4668" y2="122.3535" gradientTransform="matrix(0.8011 -0.5985 0.5985 0.8011 -37.7672 117.3501)">
|
||||
<stop offset="0" style="stop-color:#000000"/>
|
||||
<stop offset="0.3983" style="stop-color:#FFFFFF"/>
|
||||
<stop offset="1" style="stop-color:#000000"/>
|
||||
</linearGradient>
|
||||
<polygon fill="url(#SVGID_1_)" points="173.217,183.444 148.482,201.925 80.399,110.8 105.134,92.319 "/>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<!-- Generator: Adobe Illustrator 15.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0) -->
|
||||
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
|
||||
<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
|
||||
width="181px" height="212px" viewBox="0 0 181 212" enable-background="new 0 0 181 212" xml:space="preserve">
|
||||
<g>
|
||||
<path fill="#FFFFFF" d="M105.134,97.504l-3.598,2.688l-4.197-5.618l-5.754,4.299l-1.733-2.32
|
||||
c19.007-16.602,22.311-45.299,6.955-65.852C80.691,9.133,50.143,4.711,28.574,20.826s-25.99,46.663-9.875,68.232
|
||||
c15.355,20.553,43.812,25.521,65.122,12l1.732,2.319l-5.755,4.3l4.198,5.619l-3.598,2.688l68.083,91.125l24.734-18.48
|
||||
L105.134,97.504z M29.113,81.277C17.296,65.46,20.538,43.058,36.355,31.24c15.816-11.817,38.219-8.575,50.036,7.242
|
||||
c11.817,15.817,8.575,38.22-7.241,50.037C63.333,100.337,40.931,97.094,29.113,81.277z"/>
|
||||
<g>
|
||||
<g>
|
||||
<path fill="#010101" d="M28.574,15.642C7.006,31.756,2.584,62.305,18.699,83.874c16.114,21.568,46.663,25.989,68.231,9.875
|
||||
c21.569-16.115,25.99-46.664,9.876-68.232C80.691,3.948,50.143-0.473,28.574,15.642z M79.15,83.335
|
||||
c-15.817,11.817-38.22,8.574-50.037-7.242c-11.817-15.817-8.575-38.219,7.242-50.037c15.816-11.817,38.219-8.575,50.036,7.242
|
||||
C98.209,49.115,94.967,71.517,79.15,83.335z"/>
|
||||
</g>
|
||||
|
||||
<rect x="83.577" y="89.507" transform="matrix(0.8011 -0.5986 0.5986 0.8011 -39.0685 71.0375)" fill="#010101" width="7.528" height="9.579"/>
|
||||
|
||||
<rect x="81.819" y="94.546" transform="matrix(0.8011 -0.5985 0.5985 0.8011 -42.3354 75.7256)" fill="#991A37" width="21.894" height="14.026"/>
|
||||
|
||||
<linearGradient id="SVGID_1_" gradientUnits="userSpaceOnUse" x1="98.5879" y1="122.3535" x2="129.4668" y2="122.3535" gradientTransform="matrix(0.8011 -0.5985 0.5985 0.8011 -37.7672 117.3501)">
|
||||
<stop offset="0" style="stop-color:#000000"/>
|
||||
<stop offset="0.3983" style="stop-color:#FFFFFF"/>
|
||||
<stop offset="1" style="stop-color:#000000"/>
|
||||
</linearGradient>
|
||||
<polygon fill="url(#SVGID_1_)" points="173.217,183.444 148.482,201.925 80.399,110.8 105.134,92.319 "/>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 2.2 KiB After Width: | Height: | Size: 2.2 KiB |
@ -1,30 +1,30 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'MrStefan <mrstefaan@gmail.com>'
|
||||
|
||||
'''
|
||||
www.autosport.com
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class autosport(BasicNewsRecipe):
|
||||
title = u'Autosport'
|
||||
__author__ = 'MrStefan <mrstefaan@gmail.com>'
|
||||
language = 'en_GB'
|
||||
description =u'Daily Formula 1 and motorsport news from the leading weekly motor racing magazine. The authority on Formula 1, F1, MotoGP, GP2, Champ Car, Le Mans...'
|
||||
masthead_url='http://cdn.images.autosport.com/asdotcom.gif'
|
||||
remove_empty_feeds= True
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript=True
|
||||
no_stylesheets=True
|
||||
|
||||
keep_only_tags =[]
|
||||
keep_only_tags.append(dict(name = 'h1', attrs = {'class' : 'news_headline'}))
|
||||
keep_only_tags.append(dict(name = 'td', attrs = {'class' : 'news_article_author'}))
|
||||
keep_only_tags.append(dict(name = 'td', attrs = {'class' : 'news_article_date'}))
|
||||
keep_only_tags.append(dict(name = 'p'))
|
||||
|
||||
feeds = [(u'ALL NEWS', u'http://www.autosport.com/rss/allnews.xml')]
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'MrStefan <mrstefaan@gmail.com>'
|
||||
|
||||
'''
|
||||
www.autosport.com
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class autosport(BasicNewsRecipe):
|
||||
title = u'Autosport'
|
||||
__author__ = 'MrStefan <mrstefaan@gmail.com>'
|
||||
language = 'en_GB'
|
||||
description =u'Daily Formula 1 and motorsport news from the leading weekly motor racing magazine. The authority on Formula 1, F1, MotoGP, GP2, Champ Car, Le Mans...'
|
||||
masthead_url='http://cdn.images.autosport.com/asdotcom.gif'
|
||||
remove_empty_feeds= True
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript=True
|
||||
no_stylesheets=True
|
||||
|
||||
keep_only_tags =[]
|
||||
keep_only_tags.append(dict(name = 'h1', attrs = {'class' : 'news_headline'}))
|
||||
keep_only_tags.append(dict(name = 'td', attrs = {'class' : 'news_article_author'}))
|
||||
keep_only_tags.append(dict(name = 'td', attrs = {'class' : 'news_article_date'}))
|
||||
keep_only_tags.append(dict(name = 'p'))
|
||||
|
||||
feeds = [(u'ALL NEWS', u'http://www.autosport.com/rss/allnews.xml')]
|
||||
|
||||
@ -1,45 +1,45 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
'''Calibre recipe to convert the RSS feeds of the Buchreport to an ebook.'''
|
||||
|
||||
class Buchreport(BasicNewsRecipe) :
|
||||
__author__ = 'a.peter'
|
||||
__copyright__ = 'a.peter'
|
||||
__license__ = 'GPL v3'
|
||||
description = 'Buchreport'
|
||||
version = 4
|
||||
title = u'Buchreport'
|
||||
timefmt = ' [%d.%m.%Y]'
|
||||
encoding = 'cp1252'
|
||||
language = 'de'
|
||||
|
||||
|
||||
extra_css = 'body { margin-left: 0.00em; margin-right: 0.00em; } \
|
||||
article, articledate, articledescription { text-align: left; } \
|
||||
h1 { text-align: left; font-size: 140%; font-weight: bold; } \
|
||||
h2 { text-align: left; font-size: 100%; font-weight: bold; font-style: italic; } \
|
||||
h3 { text-align: left; font-size: 100%; font-weight: regular; font-style: italic; } \
|
||||
h4, h5, h6 { text-align: left; font-size: 100%; font-weight: bold; }'
|
||||
|
||||
oldest_article = 7.0
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
publication_type = 'newspaper'
|
||||
|
||||
remove_tags_before = dict(name='h2')
|
||||
remove_tags_after = [
|
||||
dict(name='div', attrs={'style':["padding-top:10px;clear:both"]})
|
||||
]
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'style':["padding-top:10px;clear:both"]}),
|
||||
dict(name='iframe'),
|
||||
dict(name='img')
|
||||
]
|
||||
|
||||
feeds = [
|
||||
(u'Buchreport', u'http://www.buchreport.de/index.php?id=5&type=100')
|
||||
]
|
||||
|
||||
def get_masthead_url(self):
|
||||
return 'http://www.buchreport.de/fileadmin/template/img/buchreport_logo.jpg'
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
'''Calibre recipe to convert the RSS feeds of the Buchreport to an ebook.'''
|
||||
|
||||
class Buchreport(BasicNewsRecipe) :
|
||||
__author__ = 'a.peter'
|
||||
__copyright__ = 'a.peter'
|
||||
__license__ = 'GPL v3'
|
||||
description = 'Buchreport'
|
||||
version = 4
|
||||
title = u'Buchreport'
|
||||
timefmt = ' [%d.%m.%Y]'
|
||||
encoding = 'cp1252'
|
||||
language = 'de'
|
||||
|
||||
|
||||
extra_css = 'body { margin-left: 0.00em; margin-right: 0.00em; } \
|
||||
article, articledate, articledescription { text-align: left; } \
|
||||
h1 { text-align: left; font-size: 140%; font-weight: bold; } \
|
||||
h2 { text-align: left; font-size: 100%; font-weight: bold; font-style: italic; } \
|
||||
h3 { text-align: left; font-size: 100%; font-weight: regular; font-style: italic; } \
|
||||
h4, h5, h6 { text-align: left; font-size: 100%; font-weight: bold; }'
|
||||
|
||||
oldest_article = 7.0
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
publication_type = 'newspaper'
|
||||
|
||||
remove_tags_before = dict(name='h2')
|
||||
remove_tags_after = [
|
||||
dict(name='div', attrs={'style':["padding-top:10px;clear:both"]})
|
||||
]
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'style':["padding-top:10px;clear:both"]}),
|
||||
dict(name='iframe'),
|
||||
dict(name='img')
|
||||
]
|
||||
|
||||
feeds = [
|
||||
(u'Buchreport', u'http://www.buchreport.de/index.php?id=5&type=100')
|
||||
]
|
||||
|
||||
def get_masthead_url(self):
|
||||
return 'http://www.buchreport.de/fileadmin/template/img/buchreport_logo.jpg'
|
||||
|
||||
@ -1,11 +1,11 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1317341449(BasicNewsRecipe):
|
||||
title = u'Diario La Republica'
|
||||
__author__ = 'CAVALENCIA'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
auto_cleanup = True
|
||||
language = 'es_CO'
|
||||
|
||||
feeds = [(u'Diario La Republica', u'http://www.larepublica.com.co/rss/larepublica.xml')]
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1317341449(BasicNewsRecipe):
|
||||
title = u'Diario La Republica'
|
||||
__author__ = 'CAVALENCIA'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
auto_cleanup = True
|
||||
language = 'es_CO'
|
||||
|
||||
feeds = [(u'Diario La Republica', u'http://www.larepublica.com.co/rss/larepublica.xml')]
|
||||
|
||||
@ -1,98 +1,98 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__author__ = 'Darko Spasovski'
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Darko Spasovski <darko.spasovski at gmail.com>'
|
||||
'''
|
||||
dnevnik.com.mk
|
||||
'''
|
||||
|
||||
import re
|
||||
import datetime
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre import browser
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
|
||||
class Dnevnik(BasicNewsRecipe):
|
||||
|
||||
INDEX = 'http://www.dnevnik.com.mk'
|
||||
__author__ = 'Darko Spasovski'
|
||||
title = 'Dnevnik - mk'
|
||||
description = 'Daily Macedonian newspaper'
|
||||
masthead_url = 'http://www.dnevnik.com.mk/images/re-logo.gif'
|
||||
language = 'mk'
|
||||
publication_type = 'newspaper'
|
||||
category = 'news, Macedonia'
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
|
||||
preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
## Remove anything before the start of the article.
|
||||
(r'<body.*?<\?xml version=\"1.0\"\?><!--Article start-->', lambda match: '<body>'),
|
||||
|
||||
## Remove anything after the end of the article.
|
||||
(r'<!--Article end.*?</body>', lambda match : '</body>'),
|
||||
]
|
||||
]
|
||||
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif}
|
||||
.WB_DNEVNIK_Naslov{FONT-WEIGHT: bold; FONT-SIZE: 18px; FONT-FAMILY: Arial, Verdana, Tahoma; TEXT-DECORATION: none}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description,
|
||||
'tags' : category,
|
||||
'language' : language,
|
||||
'linearize_tables' : True
|
||||
}
|
||||
|
||||
def parse_index(self):
|
||||
datum = datetime.datetime.today().strftime('%d.%m.%Y')
|
||||
soup = self.index_to_soup(self.INDEX + '/default.asp?section=arhiva&arhDatum=' + datum)
|
||||
feeds = []
|
||||
for section in soup.findAll('td', attrs={'class':'WB_DNEVNIK_ArhivaFormTitle'}):
|
||||
sectionTitle = section.contents[0].string
|
||||
if sectionTitle.lower().startswith('online'):
|
||||
# Skip online articles
|
||||
continue
|
||||
containerTable = section.findPrevious(name='table').findNextSibling(name='table')
|
||||
if containerTable==None:
|
||||
print 'No container table found - page layout may have been changed.'
|
||||
continue
|
||||
articles = []
|
||||
for article in containerTable.findAll('a', attrs={'class': 'WB_DNEVNIK_ArhivaFormText'}):
|
||||
title = self.tag_to_string(article, use_alt=True).strip()
|
||||
articles.append({'title': title, 'url':'http://www.dnevnik.com.mk/' + article['href'], 'description':'', 'date':''})
|
||||
if articles:
|
||||
feeds.append((sectionTitle, articles))
|
||||
return sorted(feeds, key=lambda section: self.get_weight(section))
|
||||
|
||||
def get_weight(self, section):
|
||||
"""
|
||||
Returns 'weight' of a section.
|
||||
Used for sorting the sections based on their 'natural' order in the printed edition.
|
||||
"""
|
||||
natural_order = { u'во фокусот': 1, u'актуелно': 2, u'економија': 3,
|
||||
u'отворена': 4, u'свет': 5, u'интервју': 6, u'џубокс': 7,
|
||||
u'репортажа': 8, u'наш туризам': 9, u'живот': 10,
|
||||
u'автомобилизам': 11, u'спорт': 12, u'омнибус': 13 }
|
||||
if section[0].string.lower() in natural_order:
|
||||
return natural_order[section[0].string.lower()]
|
||||
else:
|
||||
return 999 # section names not on the list go to the bottom
|
||||
|
||||
def get_cover_url(self):
|
||||
datum = datetime.datetime.today().strftime('%d.%m.%Y')
|
||||
soup = self.index_to_soup(self.INDEX + '/default.asp?section=arhiva&arhDatum=' + datum)
|
||||
anchor = soup.find('a', attrs={'class': 'WB_DNEVNIK_MoreLink'})
|
||||
if anchor != None:
|
||||
raw = browser().open_novisit(self.INDEX + '/' + anchor['href']).read()
|
||||
cover_soup = BeautifulSoup(raw)
|
||||
url = cover_soup.find('div', attrs={'class':'WB_DNEVNIK_Datum2'}).findNext('img')['src']
|
||||
return self.INDEX + '/' + url
|
||||
return ''
|
||||
|
||||
#!/usr/bin/env python
|
||||
|
||||
__author__ = 'Darko Spasovski'
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Darko Spasovski <darko.spasovski at gmail.com>'
|
||||
'''
|
||||
dnevnik.com.mk
|
||||
'''
|
||||
|
||||
import re
|
||||
import datetime
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre import browser
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
|
||||
class Dnevnik(BasicNewsRecipe):
|
||||
|
||||
INDEX = 'http://www.dnevnik.com.mk'
|
||||
__author__ = 'Darko Spasovski'
|
||||
title = 'Dnevnik - mk'
|
||||
description = 'Daily Macedonian newspaper'
|
||||
masthead_url = 'http://www.dnevnik.com.mk/images/re-logo.gif'
|
||||
language = 'mk'
|
||||
publication_type = 'newspaper'
|
||||
category = 'news, Macedonia'
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
|
||||
preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
## Remove anything before the start of the article.
|
||||
(r'<body.*?<\?xml version=\"1.0\"\?><!--Article start-->', lambda match: '<body>'),
|
||||
|
||||
## Remove anything after the end of the article.
|
||||
(r'<!--Article end.*?</body>', lambda match : '</body>'),
|
||||
]
|
||||
]
|
||||
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif}
|
||||
.WB_DNEVNIK_Naslov{FONT-WEIGHT: bold; FONT-SIZE: 18px; FONT-FAMILY: Arial, Verdana, Tahoma; TEXT-DECORATION: none}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description,
|
||||
'tags' : category,
|
||||
'language' : language,
|
||||
'linearize_tables' : True
|
||||
}
|
||||
|
||||
def parse_index(self):
|
||||
datum = datetime.datetime.today().strftime('%d.%m.%Y')
|
||||
soup = self.index_to_soup(self.INDEX + '/default.asp?section=arhiva&arhDatum=' + datum)
|
||||
feeds = []
|
||||
for section in soup.findAll('td', attrs={'class':'WB_DNEVNIK_ArhivaFormTitle'}):
|
||||
sectionTitle = section.contents[0].string
|
||||
if sectionTitle.lower().startswith('online'):
|
||||
# Skip online articles
|
||||
continue
|
||||
containerTable = section.findPrevious(name='table').findNextSibling(name='table')
|
||||
if containerTable==None:
|
||||
print 'No container table found - page layout may have been changed.'
|
||||
continue
|
||||
articles = []
|
||||
for article in containerTable.findAll('a', attrs={'class': 'WB_DNEVNIK_ArhivaFormText'}):
|
||||
title = self.tag_to_string(article, use_alt=True).strip()
|
||||
articles.append({'title': title, 'url':'http://www.dnevnik.com.mk/' + article['href'], 'description':'', 'date':''})
|
||||
if articles:
|
||||
feeds.append((sectionTitle, articles))
|
||||
return sorted(feeds, key=lambda section: self.get_weight(section))
|
||||
|
||||
def get_weight(self, section):
|
||||
"""
|
||||
Returns 'weight' of a section.
|
||||
Used for sorting the sections based on their 'natural' order in the printed edition.
|
||||
"""
|
||||
natural_order = { u'во фокусот': 1, u'актуелно': 2, u'економија': 3,
|
||||
u'отворена': 4, u'свет': 5, u'интервју': 6, u'џубокс': 7,
|
||||
u'репортажа': 8, u'наш туризам': 9, u'живот': 10,
|
||||
u'автомобилизам': 11, u'спорт': 12, u'омнибус': 13 }
|
||||
if section[0].string.lower() in natural_order:
|
||||
return natural_order[section[0].string.lower()]
|
||||
else:
|
||||
return 999 # section names not on the list go to the bottom
|
||||
|
||||
def get_cover_url(self):
|
||||
datum = datetime.datetime.today().strftime('%d.%m.%Y')
|
||||
soup = self.index_to_soup(self.INDEX + '/default.asp?section=arhiva&arhDatum=' + datum)
|
||||
anchor = soup.find('a', attrs={'class': 'WB_DNEVNIK_MoreLink'})
|
||||
if anchor != None:
|
||||
raw = browser().open_novisit(self.INDEX + '/' + anchor['href']).read()
|
||||
cover_soup = BeautifulSoup(raw)
|
||||
url = cover_soup.find('div', attrs={'class':'WB_DNEVNIK_Datum2'}).findNext('img')['src']
|
||||
return self.INDEX + '/' + url
|
||||
return ''
|
||||
|
||||
|
||||
@ -1,56 +1,56 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1311790237(BasicNewsRecipe):
|
||||
title = u'Periódico El Colombiano'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
language = 'es_CO'
|
||||
cover_url = 'http://www.elcolombiano.com/images/logoElColombiano348x46.gif'
|
||||
remove_tags_before = dict(id='contenidoArt')
|
||||
remove_tags_after = dict(id='enviaTips')
|
||||
remove_tags_after = dict(id='zonaPata')
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.elcolombiano.com/images/logoElColombiano348x46.gif'
|
||||
publication_type = 'newspaper'
|
||||
|
||||
extra_css = """
|
||||
p{text-align: justify; font-size: 100%}
|
||||
body{ text-align: left; font-size:100% }
|
||||
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
|
||||
h3{font-family: sans-serif; font-size:100%; font-style: italic; text-align: justify; }
|
||||
"""
|
||||
|
||||
|
||||
feeds = [(u'Portada', u'http://www.elcolombiano.com/rss/portada.xml'),
|
||||
(u'Antioquia', u'http://www.elcolombiano.com/rss/Antioquia.xml'),
|
||||
(u'Colombia', u'http://www.elcolombiano.com/rss/Colombia.xml'),
|
||||
(u'Economia', u'http://www.elcolombiano.com/rss/Economia.xml'),
|
||||
(u'Internacional', u'http://www.elcolombiano.com/rss/Internacional.xml'),
|
||||
(u'Politica', u'http://www.elcolombiano.com/rss/Politica.xml'),
|
||||
(u'Cultura', u'http://www.elcolombiano.com/rss/Cultura.xml'),
|
||||
(u'Entretenimiento', u'http://www.elcolombiano.com/rss/Farandula.xml'),
|
||||
(u'Tecnologia', u'http://www.elcolombiano.com/rss/Tecnologia.xml'),
|
||||
(u'Television', u'http://www.elcolombiano.com/rss/Television.xml'),
|
||||
(u'Vida y Sociedad', u'http://www.elcolombiano.com/rss/Vida.xml'),
|
||||
(u'Turismo', u'http://www.elcolombiano.com/rss/Turismo.xm'),
|
||||
(u'Salud', u'http://www.elcolombiano.com/rss/Salud.xml'),
|
||||
(u'Ciencia', u'http://www.elcolombiano.com/rss/Ciencia.xml')]
|
||||
|
||||
remove_tags = [dict(name='div', attrs={'class':'objetosRelacionados'}),
|
||||
dict(name='div', attrs={'class':'notasRelacionadas contenedor'}),
|
||||
dict(name='div', attrs={'class':'comentarios'}),
|
||||
dict(name='div', attrs={'class':'mapaDelSitio'}),
|
||||
dict(name='div', attrs={'class':'creditos'}),
|
||||
dict(name='div', attrs={'class':'votos'}),
|
||||
dict(name='div', attrs={'class':'divopt2'}),
|
||||
dict(name='div', attrs={'class':'comentarios'}),
|
||||
dict(name='div', attrs={'class':'pestanasLateral'}),
|
||||
dict(name='div', attrs={'class':'resumenSeccion'}),
|
||||
dict(name='div', attrs={'class':'zonaComercial'}),
|
||||
dict(name='div', attrs={'id':'zonaPata'})]
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1311790237(BasicNewsRecipe):
|
||||
title = u'Periódico El Colombiano'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
language = 'es_CO'
|
||||
cover_url = 'http://www.elcolombiano.com/images/logoElColombiano348x46.gif'
|
||||
remove_tags_before = dict(id='contenidoArt')
|
||||
remove_tags_after = dict(id='enviaTips')
|
||||
remove_tags_after = dict(id='zonaPata')
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.elcolombiano.com/images/logoElColombiano348x46.gif'
|
||||
publication_type = 'newspaper'
|
||||
|
||||
extra_css = """
|
||||
p{text-align: justify; font-size: 100%}
|
||||
body{ text-align: left; font-size:100% }
|
||||
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
|
||||
h3{font-family: sans-serif; font-size:100%; font-style: italic; text-align: justify; }
|
||||
"""
|
||||
|
||||
|
||||
feeds = [(u'Portada', u'http://www.elcolombiano.com/rss/portada.xml'),
|
||||
(u'Antioquia', u'http://www.elcolombiano.com/rss/Antioquia.xml'),
|
||||
(u'Colombia', u'http://www.elcolombiano.com/rss/Colombia.xml'),
|
||||
(u'Economia', u'http://www.elcolombiano.com/rss/Economia.xml'),
|
||||
(u'Internacional', u'http://www.elcolombiano.com/rss/Internacional.xml'),
|
||||
(u'Politica', u'http://www.elcolombiano.com/rss/Politica.xml'),
|
||||
(u'Cultura', u'http://www.elcolombiano.com/rss/Cultura.xml'),
|
||||
(u'Entretenimiento', u'http://www.elcolombiano.com/rss/Farandula.xml'),
|
||||
(u'Tecnologia', u'http://www.elcolombiano.com/rss/Tecnologia.xml'),
|
||||
(u'Television', u'http://www.elcolombiano.com/rss/Television.xml'),
|
||||
(u'Vida y Sociedad', u'http://www.elcolombiano.com/rss/Vida.xml'),
|
||||
(u'Turismo', u'http://www.elcolombiano.com/rss/Turismo.xm'),
|
||||
(u'Salud', u'http://www.elcolombiano.com/rss/Salud.xml'),
|
||||
(u'Ciencia', u'http://www.elcolombiano.com/rss/Ciencia.xml')]
|
||||
|
||||
remove_tags = [dict(name='div', attrs={'class':'objetosRelacionados'}),
|
||||
dict(name='div', attrs={'class':'notasRelacionadas contenedor'}),
|
||||
dict(name='div', attrs={'class':'comentarios'}),
|
||||
dict(name='div', attrs={'class':'mapaDelSitio'}),
|
||||
dict(name='div', attrs={'class':'creditos'}),
|
||||
dict(name='div', attrs={'class':'votos'}),
|
||||
dict(name='div', attrs={'class':'divopt2'}),
|
||||
dict(name='div', attrs={'class':'comentarios'}),
|
||||
dict(name='div', attrs={'class':'pestanasLateral'}),
|
||||
dict(name='div', attrs={'class':'resumenSeccion'}),
|
||||
dict(name='div', attrs={'class':'zonaComercial'}),
|
||||
dict(name='div', attrs={'id':'zonaPata'})]
|
||||
|
||||
@ -1,54 +1,54 @@
|
||||
# coding=utf-8
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class ColombiaElEspectador(BasicNewsRecipe):
|
||||
title = u'Periódico el Espectador'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
cover_url = 'http://www.elespectador.com/sites/elespectador.com/themes/elespectador/images/logo.gif'
|
||||
#remove_tags_before = dict(id='fb-root')
|
||||
remove_tags_before = dict(id='content')
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'paginacion'})]
|
||||
language = 'es_CO'
|
||||
#keep_only_tags = [dict(name='div', id='content')]
|
||||
remove_tags = [dict(name='div', attrs={'class':'herramientas_nota'}),
|
||||
dict(name='div', attrs={'class':'relpauta'}),
|
||||
dict(name='div', attrs={'class':'recursosrelacionados'}),
|
||||
dict(name='div', attrs={'class':'nav_negocios'})]
|
||||
# dict(name='div', attrs={'class':'tags_playerrecurso'}),
|
||||
# dict(name='div', attrs={'class':'ico-mail2'}),
|
||||
# dict(name='div', attrs={'id':'caja-instapaper'}),
|
||||
# dict(name='div', attrs={'class':'modulo herramientas'})]
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.elespectador.com/sites/elespectador.com/themes/elespectador/images/logo.gif'
|
||||
publication_type = 'newspaper'
|
||||
|
||||
extra_css = """
|
||||
p{text-align: justify; font-size: 100%}
|
||||
body{ text-align: left; font-size:100% }
|
||||
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
|
||||
h3{font-family: sans-serif; font-size:100%; font-style: italic; text-align: justify; }
|
||||
"""
|
||||
|
||||
|
||||
feeds = [(u'Política ', u' http://www.elespectador.com/noticias/politica/feed'),
|
||||
(u'Judicial', u'http://www.elespectador.com/noticias/judicial/feed'),
|
||||
(u'Paz', u'http://www.elespectador.com/noticias/paz/feed'),
|
||||
(u'Economía', u'http://www.elespectador.com/economia/feed'),
|
||||
(u'Soy Periodista', u'http://www.elespectador.com/noticias/soyperiodista/feed'),
|
||||
(u'Investigación', u'http://www.elespectador.com/noticias/investigacion/feed'),
|
||||
(u'Educación', u'http://www.elespectador.com/noticias/educacion/feed'),
|
||||
(u'Salud', u'http://www.elespectador.com/noticias/salud/feed'),
|
||||
(u'El Mundo', u'http://www.elespectador.com/noticias/elmundo/feed'),
|
||||
(u'Nacional', u'http://www.elespectador.com/noticias/nacional/feed'),
|
||||
(u'Bogotá', u'http://www.elespectador.com/noticias/bogota/feed'),
|
||||
(u'Deportes', u'http://www.elespectador.com/deportes/feed'),
|
||||
(u'Tecnología', u'http://www.elespectador.com/tecnologia/feed'),
|
||||
(u'Actualidad', u'http://www.elespectador.com/noticias/actualidad/feed'),
|
||||
(u'Opinión', u'http://www.elespectador.com/opinion/feed'),
|
||||
(u'Editorial', u'http://www.elespectador.com/opinion/editorial/feed')]
|
||||
# coding=utf-8
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class ColombiaElEspectador(BasicNewsRecipe):
|
||||
title = u'Periódico el Espectador'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
cover_url = 'http://www.elespectador.com/sites/elespectador.com/themes/elespectador/images/logo.gif'
|
||||
#remove_tags_before = dict(id='fb-root')
|
||||
remove_tags_before = dict(id='content')
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'paginacion'})]
|
||||
language = 'es_CO'
|
||||
#keep_only_tags = [dict(name='div', id='content')]
|
||||
remove_tags = [dict(name='div', attrs={'class':'herramientas_nota'}),
|
||||
dict(name='div', attrs={'class':'relpauta'}),
|
||||
dict(name='div', attrs={'class':'recursosrelacionados'}),
|
||||
dict(name='div', attrs={'class':'nav_negocios'})]
|
||||
# dict(name='div', attrs={'class':'tags_playerrecurso'}),
|
||||
# dict(name='div', attrs={'class':'ico-mail2'}),
|
||||
# dict(name='div', attrs={'id':'caja-instapaper'}),
|
||||
# dict(name='div', attrs={'class':'modulo herramientas'})]
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.elespectador.com/sites/elespectador.com/themes/elespectador/images/logo.gif'
|
||||
publication_type = 'newspaper'
|
||||
|
||||
extra_css = """
|
||||
p{text-align: justify; font-size: 100%}
|
||||
body{ text-align: left; font-size:100% }
|
||||
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
|
||||
h3{font-family: sans-serif; font-size:100%; font-style: italic; text-align: justify; }
|
||||
"""
|
||||
|
||||
|
||||
feeds = [(u'Política ', u' http://www.elespectador.com/noticias/politica/feed'),
|
||||
(u'Judicial', u'http://www.elespectador.com/noticias/judicial/feed'),
|
||||
(u'Paz', u'http://www.elespectador.com/noticias/paz/feed'),
|
||||
(u'Economía', u'http://www.elespectador.com/economia/feed'),
|
||||
(u'Soy Periodista', u'http://www.elespectador.com/noticias/soyperiodista/feed'),
|
||||
(u'Investigación', u'http://www.elespectador.com/noticias/investigacion/feed'),
|
||||
(u'Educación', u'http://www.elespectador.com/noticias/educacion/feed'),
|
||||
(u'Salud', u'http://www.elespectador.com/noticias/salud/feed'),
|
||||
(u'El Mundo', u'http://www.elespectador.com/noticias/elmundo/feed'),
|
||||
(u'Nacional', u'http://www.elespectador.com/noticias/nacional/feed'),
|
||||
(u'Bogotá', u'http://www.elespectador.com/noticias/bogota/feed'),
|
||||
(u'Deportes', u'http://www.elespectador.com/deportes/feed'),
|
||||
(u'Tecnología', u'http://www.elespectador.com/tecnologia/feed'),
|
||||
(u'Actualidad', u'http://www.elespectador.com/noticias/actualidad/feed'),
|
||||
(u'Opinión', u'http://www.elespectador.com/opinion/feed'),
|
||||
(u'Editorial', u'http://www.elespectador.com/opinion/editorial/feed')]
|
||||
|
||||
@ -1,40 +1,40 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1313609361(BasicNewsRecipe):
|
||||
news = True
|
||||
title = u'El Mostrador'
|
||||
__author__ = 'Alex Mitrani'
|
||||
description = u'Chilean online newspaper'
|
||||
publisher = u'La Plaza S.A.'
|
||||
category = 'news, rss'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
summary_length = 1000
|
||||
language = 'es_CL'
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.elmostrador.cl/assets/img/logo-elmostrador-m.jpg'
|
||||
remove_tags_before = dict(name='div', attrs={'class':'news-heading cf'})
|
||||
remove_tags_after = dict(name='div', attrs={'class':'footer-actions cf'})
|
||||
remove_tags = [dict(name='div', attrs={'class':'footer-actions cb cf'})
|
||||
,dict(name='div', attrs={'class':'news-aside fl'})
|
||||
,dict(name='div', attrs={'class':'footer-actions cf'})
|
||||
,dict(name='div', attrs={'class':'user-bar','id':'top'})
|
||||
,dict(name='div', attrs={'class':'indicators'})
|
||||
,dict(name='div', attrs={'id':'header'})
|
||||
]
|
||||
|
||||
|
||||
feeds = [(u'Temas Destacados'
|
||||
, u'http://www.elmostrador.cl/destacado/feed/')
|
||||
, (u'El D\xeda', u'http://www.elmostrador.cl/dia/feed/')
|
||||
, (u'Pa\xeds', u'http://www.elmostrador.cl/noticias/pais/feed/')
|
||||
, (u'Mundo', u'http://www.elmostrador.cl/noticias/mundo/feed/')
|
||||
, (u'Negocios', u'http://www.elmostrador.cl/noticias/negocios/feed/')
|
||||
, (u'Cultura', u'http://www.elmostrador.cl/noticias/cultura/feed/')
|
||||
, (u'Vida en L\xednea', u'http://www.elmostrador.cl/vida-en-linea/feed/')
|
||||
, (u'Opini\xf3n & Blogs', u'http://www.elmostrador.cl/opinion/feed/')
|
||||
]
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1313609361(BasicNewsRecipe):
|
||||
news = True
|
||||
title = u'El Mostrador'
|
||||
__author__ = 'Alex Mitrani'
|
||||
description = u'Chilean online newspaper'
|
||||
publisher = u'La Plaza S.A.'
|
||||
category = 'news, rss'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
summary_length = 1000
|
||||
language = 'es_CL'
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.elmostrador.cl/assets/img/logo-elmostrador-m.jpg'
|
||||
remove_tags_before = dict(name='div', attrs={'class':'news-heading cf'})
|
||||
remove_tags_after = dict(name='div', attrs={'class':'footer-actions cf'})
|
||||
remove_tags = [dict(name='div', attrs={'class':'footer-actions cb cf'})
|
||||
,dict(name='div', attrs={'class':'news-aside fl'})
|
||||
,dict(name='div', attrs={'class':'footer-actions cf'})
|
||||
,dict(name='div', attrs={'class':'user-bar','id':'top'})
|
||||
,dict(name='div', attrs={'class':'indicators'})
|
||||
,dict(name='div', attrs={'id':'header'})
|
||||
]
|
||||
|
||||
|
||||
feeds = [(u'Temas Destacados'
|
||||
, u'http://www.elmostrador.cl/destacado/feed/')
|
||||
, (u'El D\xeda', u'http://www.elmostrador.cl/dia/feed/')
|
||||
, (u'Pa\xeds', u'http://www.elmostrador.cl/noticias/pais/feed/')
|
||||
, (u'Mundo', u'http://www.elmostrador.cl/noticias/mundo/feed/')
|
||||
, (u'Negocios', u'http://www.elmostrador.cl/noticias/negocios/feed/')
|
||||
, (u'Cultura', u'http://www.elmostrador.cl/noticias/cultura/feed/')
|
||||
, (u'Vida en L\xednea', u'http://www.elmostrador.cl/vida-en-linea/feed/')
|
||||
, (u'Opini\xf3n & Blogs', u'http://www.elmostrador.cl/opinion/feed/')
|
||||
]
|
||||
|
||||
|
||||
@ -1,52 +1,52 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class ColombiaElTiempo02(BasicNewsRecipe):
|
||||
title = u'Periódico el Tiempo'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
language = 'es_CO'
|
||||
cover_url = 'http://www.eltiempo.com/media/css/images/logo_footer.png'
|
||||
#remove_tags_before = dict(id='fb-root')
|
||||
remove_tags_before = dict(id='contenidoArt')
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'modulo reporte'})]
|
||||
keep_only_tags = [dict(name='div', id='contenidoArt')]
|
||||
remove_tags = [dict(name='div', attrs={'class':'social-media'}),
|
||||
dict(name='div', attrs={'class':'recomend-art'}),
|
||||
dict(name='div', attrs={'class':'caja-facebook'}),
|
||||
dict(name='div', attrs={'class':'caja-twitter'}),
|
||||
dict(name='div', attrs={'class':'caja-buzz'}),
|
||||
dict(name='div', attrs={'class':'ico-mail2'}),
|
||||
dict(name='div', attrs={'id':'caja-instapaper'}),
|
||||
dict(name='div', attrs={'class':'modulo herramientas'})]
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.eltiempo.com/media/css/images/logo_footer.png'
|
||||
publication_type = 'newspaper'
|
||||
|
||||
extra_css = """
|
||||
p{text-align: justify; font-size: 100%}
|
||||
body{ text-align: left; font-size:100% }
|
||||
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
|
||||
h3{font-family: sans-serif; font-size:100%; font-style: italic; text-align: justify; }
|
||||
"""
|
||||
|
||||
|
||||
feeds = [(u'Colombia', u'http://www.eltiempo.com/colombia/rss.xml'),
|
||||
(u'Medellin', u'http://www.eltiempo.com/colombia/medellin/rss.xml'),
|
||||
(u'Economia', u'http://www.eltiempo.com/economia/rss.xml'),
|
||||
(u'Deportes', u'http://www.eltiempo.com/deportes/rss.xml'),
|
||||
(u'Mundo', u'http://www.eltiempo.com/mundo/rss.xml'),
|
||||
(u'Gente', u'http://www.eltiempo.com/gente/rss.xml'),
|
||||
(u'Vida de Hoy', u'http://www.eltiempo.com/vida-de-hoy/rss.xml'),
|
||||
(u'EEUU', u'http://www.eltiempo.com/mundo/estados-unidos/rss.xml'),
|
||||
(u'LatinoAmerica', u'http://www.eltiempo.com/mundo/latinoamerica/rss.xml'),
|
||||
(u'Europa', u'http://www.eltiempo.com/mundo/europa/rss.xml'),
|
||||
(u'Medio Oriente', u'http://www.eltiempo.com/mundo/medio-oriente/rss.xml'),
|
||||
(u'Vive in Medellin', u'http://medellin.vive.in/medellin/rss.xml'),
|
||||
(u'Don Juan', u'http://www.revistadonjuan.com/feedrss/'),
|
||||
(u'Alo', u'http://www.eltiempo.com/alo/rss.xml')]
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class ColombiaElTiempo02(BasicNewsRecipe):
|
||||
title = u'Periódico el Tiempo'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
language = 'es_CO'
|
||||
cover_url = 'http://www.eltiempo.com/media/css/images/logo_footer.png'
|
||||
#remove_tags_before = dict(id='fb-root')
|
||||
remove_tags_before = dict(id='contenidoArt')
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'modulo reporte'})]
|
||||
keep_only_tags = [dict(name='div', id='contenidoArt')]
|
||||
remove_tags = [dict(name='div', attrs={'class':'social-media'}),
|
||||
dict(name='div', attrs={'class':'recomend-art'}),
|
||||
dict(name='div', attrs={'class':'caja-facebook'}),
|
||||
dict(name='div', attrs={'class':'caja-twitter'}),
|
||||
dict(name='div', attrs={'class':'caja-buzz'}),
|
||||
dict(name='div', attrs={'class':'ico-mail2'}),
|
||||
dict(name='div', attrs={'id':'caja-instapaper'}),
|
||||
dict(name='div', attrs={'class':'modulo herramientas'})]
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.eltiempo.com/media/css/images/logo_footer.png'
|
||||
publication_type = 'newspaper'
|
||||
|
||||
extra_css = """
|
||||
p{text-align: justify; font-size: 100%}
|
||||
body{ text-align: left; font-size:100% }
|
||||
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
|
||||
h3{font-family: sans-serif; font-size:100%; font-style: italic; text-align: justify; }
|
||||
"""
|
||||
|
||||
|
||||
feeds = [(u'Colombia', u'http://www.eltiempo.com/colombia/rss.xml'),
|
||||
(u'Medellin', u'http://www.eltiempo.com/colombia/medellin/rss.xml'),
|
||||
(u'Economia', u'http://www.eltiempo.com/economia/rss.xml'),
|
||||
(u'Deportes', u'http://www.eltiempo.com/deportes/rss.xml'),
|
||||
(u'Mundo', u'http://www.eltiempo.com/mundo/rss.xml'),
|
||||
(u'Gente', u'http://www.eltiempo.com/gente/rss.xml'),
|
||||
(u'Vida de Hoy', u'http://www.eltiempo.com/vida-de-hoy/rss.xml'),
|
||||
(u'EEUU', u'http://www.eltiempo.com/mundo/estados-unidos/rss.xml'),
|
||||
(u'LatinoAmerica', u'http://www.eltiempo.com/mundo/latinoamerica/rss.xml'),
|
||||
(u'Europa', u'http://www.eltiempo.com/mundo/europa/rss.xml'),
|
||||
(u'Medio Oriente', u'http://www.eltiempo.com/mundo/medio-oriente/rss.xml'),
|
||||
(u'Vive in Medellin', u'http://medellin.vive.in/medellin/rss.xml'),
|
||||
(u'Don Juan', u'http://www.revistadonjuan.com/feedrss/'),
|
||||
(u'Alo', u'http://www.eltiempo.com/alo/rss.xml')]
|
||||
|
||||
@ -1,129 +1,129 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from datetime import datetime, timedelta
|
||||
from calibre.ebooks.BeautifulSoup import Tag,BeautifulSoup
|
||||
from calibre.utils.magick import Image, PixelWand
|
||||
from urllib2 import Request, urlopen, URLError
|
||||
|
||||
class Estadao(BasicNewsRecipe):
|
||||
THUMBALIZR_API = '' # ---->Get your at http://www.thumbalizr.com/ and put here
|
||||
LANGUAGE = 'pt_br'
|
||||
language = 'pt'
|
||||
LANGHTM = 'pt-br'
|
||||
ENCODING = 'utf'
|
||||
ENCHTM = 'utf-8'
|
||||
directionhtm = 'ltr'
|
||||
requires_version = (0,7,47)
|
||||
news = True
|
||||
|
||||
title = u'Estad\xe3o'
|
||||
__author__ = 'Euler Alves'
|
||||
description = u'Brazilian news from Estad\xe3o'
|
||||
publisher = u'Estad\xe3o'
|
||||
category = 'news, rss'
|
||||
|
||||
oldest_article = 4
|
||||
max_articles_per_feed = 100
|
||||
summary_length = 1000
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
timefmt = ' [%d %b %Y (%a)]'
|
||||
|
||||
hoje = datetime.now()-timedelta(days=2)
|
||||
pubdate = hoje.strftime('%a, %d %b')
|
||||
if hoje.hour<10:
|
||||
hoje = hoje-timedelta(days=1)
|
||||
CAPA = 'http://www.estadao.com.br/estadaodehoje/'+hoje.strftime('%Y%m%d')+'/img/capadodia.jpg'
|
||||
SCREENSHOT = 'http://estadao.com.br/'
|
||||
cover_margins = (0,0,'white')
|
||||
masthead_url = 'http://www.estadao.com.br/estadao/novo/img/logo.png'
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':['bb-md-noticia','corpo']})]
|
||||
remove_tags = [
|
||||
dict(name='div',
|
||||
attrs={'id':[
|
||||
'bb-md-noticia-tabs'
|
||||
]})
|
||||
,dict(name='div',
|
||||
attrs={'class':[
|
||||
'tags'
|
||||
,'discussion'
|
||||
,'bb-gg adsense_container'
|
||||
]})
|
||||
|
||||
,dict(name='a')
|
||||
,dict(name='iframe')
|
||||
,dict(name='link')
|
||||
,dict(name='script')
|
||||
]
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'\xDAltimas Not\xEDcias', u'http://www.estadao.com.br/rss/ultimas.xml')
|
||||
,(u'Manchetes', u'http://www.estadao.com.br/rss/manchetes.xml')
|
||||
,(u'Brasil', u'http://www.estadao.com.br/rss/brasil.xml')
|
||||
,(u'Internacional', u'http://www.estadao.com.br/rss/internacional.xml')
|
||||
,(u'Cinema', u'http://blogs.estadao.com.br/cinema/feed/')
|
||||
,(u'Planeta', u'http://www.estadao.com.br/rss/planeta.xml')
|
||||
,(u'Ci\xEAncia', u'http://www.estadao.com.br/rss/ciencia.xml')
|
||||
,(u'Sa\xFAde', u'http://www.estadao.com.br/rss/saude.xml')
|
||||
,(u'Pol\xEDtica', u'http://www.estadao.com.br/rss/politica.xml')
|
||||
]
|
||||
|
||||
conversion_options = {
|
||||
'title' : title
|
||||
,'comments' : description
|
||||
,'publisher' : publisher
|
||||
,'tags' : category
|
||||
,'language' : LANGUAGE
|
||||
,'linearize_tables': True
|
||||
}
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
if not soup.find(attrs={'http-equiv':'Content-Language'}):
|
||||
meta0 = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.LANGHTM)])
|
||||
soup.head.insert(0,meta0)
|
||||
if not soup.find(attrs={'http-equiv':'Content-Type'}):
|
||||
meta1 = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset="+self.ENCHTM)])
|
||||
soup.head.insert(0,meta1)
|
||||
return soup
|
||||
|
||||
def postprocess_html(self, soup, first):
|
||||
#process all the images. assumes that the new html has the correct path
|
||||
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
|
||||
iurl = tag['src']
|
||||
img = Image()
|
||||
img.open(iurl)
|
||||
width, height = img.size
|
||||
print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
|
||||
if img < 0:
|
||||
raise RuntimeError('Out of memory')
|
||||
pw = PixelWand()
|
||||
if( width > height and width > 590) :
|
||||
print 'Rotate image'
|
||||
img.rotate(pw, -90)
|
||||
img.save(iurl)
|
||||
return soup
|
||||
|
||||
def get_cover_url(self):
|
||||
if self.THUMBALIZR_API:
|
||||
cover_url = self.CAPA
|
||||
pedido = Request(self.CAPA)
|
||||
pedido.add_header('User-agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; '+self.LANGHTM+'; userid='+self.THUMBALIZR_API+') Calibre/0.8.47 (like Gecko)')
|
||||
pedido.add_header('Accept-Charset',self.ENCHTM)
|
||||
pedido.add_header('Referer',self.SCREENSHOT)
|
||||
try:
|
||||
resposta = urlopen(pedido)
|
||||
soup = BeautifulSoup(resposta)
|
||||
cover_item = soup.find('body')
|
||||
if cover_item:
|
||||
cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
|
||||
return cover_url
|
||||
except URLError:
|
||||
cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
|
||||
return cover_url
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from datetime import datetime, timedelta
|
||||
from calibre.ebooks.BeautifulSoup import Tag,BeautifulSoup
|
||||
from calibre.utils.magick import Image, PixelWand
|
||||
from urllib2 import Request, urlopen, URLError
|
||||
|
||||
class Estadao(BasicNewsRecipe):
|
||||
THUMBALIZR_API = '' # ---->Get your at http://www.thumbalizr.com/ and put here
|
||||
LANGUAGE = 'pt_br'
|
||||
language = 'pt'
|
||||
LANGHTM = 'pt-br'
|
||||
ENCODING = 'utf'
|
||||
ENCHTM = 'utf-8'
|
||||
directionhtm = 'ltr'
|
||||
requires_version = (0,7,47)
|
||||
news = True
|
||||
|
||||
title = u'Estad\xe3o'
|
||||
__author__ = 'Euler Alves'
|
||||
description = u'Brazilian news from Estad\xe3o'
|
||||
publisher = u'Estad\xe3o'
|
||||
category = 'news, rss'
|
||||
|
||||
oldest_article = 4
|
||||
max_articles_per_feed = 100
|
||||
summary_length = 1000
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
timefmt = ' [%d %b %Y (%a)]'
|
||||
|
||||
hoje = datetime.now()-timedelta(days=2)
|
||||
pubdate = hoje.strftime('%a, %d %b')
|
||||
if hoje.hour<10:
|
||||
hoje = hoje-timedelta(days=1)
|
||||
CAPA = 'http://www.estadao.com.br/estadaodehoje/'+hoje.strftime('%Y%m%d')+'/img/capadodia.jpg'
|
||||
SCREENSHOT = 'http://estadao.com.br/'
|
||||
cover_margins = (0,0,'white')
|
||||
masthead_url = 'http://www.estadao.com.br/estadao/novo/img/logo.png'
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':['bb-md-noticia','corpo']})]
|
||||
remove_tags = [
|
||||
dict(name='div',
|
||||
attrs={'id':[
|
||||
'bb-md-noticia-tabs'
|
||||
]})
|
||||
,dict(name='div',
|
||||
attrs={'class':[
|
||||
'tags'
|
||||
,'discussion'
|
||||
,'bb-gg adsense_container'
|
||||
]})
|
||||
|
||||
,dict(name='a')
|
||||
,dict(name='iframe')
|
||||
,dict(name='link')
|
||||
,dict(name='script')
|
||||
]
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'\xDAltimas Not\xEDcias', u'http://www.estadao.com.br/rss/ultimas.xml')
|
||||
,(u'Manchetes', u'http://www.estadao.com.br/rss/manchetes.xml')
|
||||
,(u'Brasil', u'http://www.estadao.com.br/rss/brasil.xml')
|
||||
,(u'Internacional', u'http://www.estadao.com.br/rss/internacional.xml')
|
||||
,(u'Cinema', u'http://blogs.estadao.com.br/cinema/feed/')
|
||||
,(u'Planeta', u'http://www.estadao.com.br/rss/planeta.xml')
|
||||
,(u'Ci\xEAncia', u'http://www.estadao.com.br/rss/ciencia.xml')
|
||||
,(u'Sa\xFAde', u'http://www.estadao.com.br/rss/saude.xml')
|
||||
,(u'Pol\xEDtica', u'http://www.estadao.com.br/rss/politica.xml')
|
||||
]
|
||||
|
||||
conversion_options = {
|
||||
'title' : title
|
||||
,'comments' : description
|
||||
,'publisher' : publisher
|
||||
,'tags' : category
|
||||
,'language' : LANGUAGE
|
||||
,'linearize_tables': True
|
||||
}
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
if not soup.find(attrs={'http-equiv':'Content-Language'}):
|
||||
meta0 = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.LANGHTM)])
|
||||
soup.head.insert(0,meta0)
|
||||
if not soup.find(attrs={'http-equiv':'Content-Type'}):
|
||||
meta1 = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset="+self.ENCHTM)])
|
||||
soup.head.insert(0,meta1)
|
||||
return soup
|
||||
|
||||
def postprocess_html(self, soup, first):
|
||||
#process all the images. assumes that the new html has the correct path
|
||||
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
|
||||
iurl = tag['src']
|
||||
img = Image()
|
||||
img.open(iurl)
|
||||
width, height = img.size
|
||||
print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
|
||||
if img < 0:
|
||||
raise RuntimeError('Out of memory')
|
||||
pw = PixelWand()
|
||||
if( width > height and width > 590) :
|
||||
print 'Rotate image'
|
||||
img.rotate(pw, -90)
|
||||
img.save(iurl)
|
||||
return soup
|
||||
|
||||
def get_cover_url(self):
|
||||
if self.THUMBALIZR_API:
|
||||
cover_url = self.CAPA
|
||||
pedido = Request(self.CAPA)
|
||||
pedido.add_header('User-agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; '+self.LANGHTM+'; userid='+self.THUMBALIZR_API+') Calibre/0.8.47 (like Gecko)')
|
||||
pedido.add_header('Accept-Charset',self.ENCHTM)
|
||||
pedido.add_header('Referer',self.SCREENSHOT)
|
||||
try:
|
||||
resposta = urlopen(pedido)
|
||||
soup = BeautifulSoup(resposta)
|
||||
cover_item = soup.find('body')
|
||||
if cover_item:
|
||||
cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
|
||||
return cover_url
|
||||
except URLError:
|
||||
cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
|
||||
return cover_url
|
||||
|
||||
|
||||
@ -1,165 +1,165 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from datetime import datetime, timedelta
|
||||
from calibre.ebooks.BeautifulSoup import Tag,BeautifulSoup
|
||||
from calibre.utils.magick import Image, PixelWand
|
||||
from urllib2 import Request, urlopen, URLError
|
||||
|
||||
class FolhaOnline(BasicNewsRecipe):
|
||||
THUMBALIZR_API = '' # ---->Get your at http://www.thumbalizr.com/ and put here
|
||||
LANGUAGE = 'pt_br'
|
||||
language = 'pt_BR'
|
||||
LANGHTM = 'pt-br'
|
||||
ENCODING = 'cp1252'
|
||||
ENCHTM = 'iso-8859-1'
|
||||
directionhtm = 'ltr'
|
||||
requires_version = (0,7,47)
|
||||
news = True
|
||||
|
||||
title = u'Folha de S\xE3o Paulo'
|
||||
__author__ = 'Euler Alves and Alex Mitrani'
|
||||
description = u'Brazilian news from Folha de S\xE3o Paulo'
|
||||
publisher = u'Folha de S\xE3o Paulo'
|
||||
category = 'news, rss'
|
||||
|
||||
oldest_article = 4
|
||||
max_articles_per_feed = 100
|
||||
summary_length = 1000
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
timefmt = ' [%d %b %Y (%a)]'
|
||||
|
||||
html2lrf_options = [
|
||||
'--comment', description
|
||||
,'--category', category
|
||||
,'--publisher', publisher
|
||||
]
|
||||
|
||||
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
|
||||
|
||||
hoje = datetime.now()
|
||||
pubdate = hoje.strftime('%a, %d %b')
|
||||
if hoje.hour<6:
|
||||
hoje = hoje-timedelta(days=1)
|
||||
CAPA = 'http://www1.folha.uol.com.br/fsp/images/cp'+hoje.strftime('%d%m%Y')+'.jpg'
|
||||
SCREENSHOT = 'http://www1.folha.uol.com.br/'
|
||||
cover_margins = (0,0,'white')
|
||||
masthead_url = 'http://f.i.uol.com.br/fsp/furniture/images/lgo-fsp-430x50-ffffff.gif'
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'articleNew'})]
|
||||
remove_tags = [
|
||||
dict(name='div',
|
||||
attrs={'id':[
|
||||
'articleButton'
|
||||
,'bookmarklets'
|
||||
,'ad-180x150-1'
|
||||
,'contextualAdsArticle'
|
||||
,'articleEnd'
|
||||
,'articleComments'
|
||||
]})
|
||||
,dict(name='div',
|
||||
attrs={'class':[
|
||||
'openBox adslibraryArticle'
|
||||
,'toolbar'
|
||||
]})
|
||||
|
||||
,dict(name='a')
|
||||
,dict(name='iframe')
|
||||
,dict(name='link')
|
||||
,dict(name='script')
|
||||
,dict(name='li')
|
||||
]
|
||||
remove_tags_after = dict(name='div',attrs={'id':'articleEnd'})
|
||||
|
||||
feeds = [
|
||||
(u'Em cima da hora', u'http://feeds.folha.uol.com.br/emcimadahora/rss091.xml')
|
||||
,(u'Cotidiano', u'http://feeds.folha.uol.com.br/folha/cotidiano/rss091.xml')
|
||||
,(u'Brasil', u'http://feeds.folha.uol.com.br/folha/brasil/rss091.xml')
|
||||
,(u'Mundo', u'http://feeds.folha.uol.com.br/mundo/rss091.xml')
|
||||
,(u'Poder', u'http://feeds.folha.uol.com.br/poder/rss091.xml')
|
||||
,(u'Mercado', u'http://feeds.folha.uol.com.br/folha/dinheiro/rss091.xml')
|
||||
,(u'Saber', u'http://feeds.folha.uol.com.br/folha/educacao/rss091.xml')
|
||||
,(u'Tec', u'http://feeds.folha.uol.com.br/folha/informatica/rss091.xml')
|
||||
,(u'Ilustrada', u'http://feeds.folha.uol.com.br/folha/ilustrada/rss091.xml')
|
||||
,(u'Ambiente', u'http://feeds.folha.uol.com.br/ambiente/rss091.xml')
|
||||
,(u'Bichos', u'http://feeds.folha.uol.com.br/bichos/rss091.xml')
|
||||
,(u'Ci\xEAncia', u'http://feeds.folha.uol.com.br/ciencia/rss091.xml')
|
||||
,(u'Equil\xEDbrio e Sa\xFAde', u'http://feeds.folha.uol.com.br/equilibrioesaude/rss091.xml')
|
||||
,(u'Turismo', u'http://feeds.folha.uol.com.br/folha/turismo/rss091.xml')
|
||||
,(u'Esporte', u'http://feeds.folha.uol.com.br/folha/esporte/rss091.xml')
|
||||
,(u'Zapping', u'http://feeds.folha.uol.com.br/colunas/zapping/rss091.xml')
|
||||
,(u'Cida Santos', u'http://feeds.folha.uol.com.br/colunas/cidasantos/rss091.xml')
|
||||
,(u'Clóvis Rossi', u'http://feeds.folha.uol.com.br/colunas/clovisrossi/rss091.xml')
|
||||
,(u'Eliane Cantanhêde', u'http://feeds.folha.uol.com.br/colunas/elianecantanhede/rss091.xml')
|
||||
,(u'Fernando Canzian', u'http://feeds.folha.uol.com.br/colunas/fernandocanzian/rss091.xml')
|
||||
,(u'Gilberto Dimenstein', u'http://feeds.folha.uol.com.br/colunas/gilbertodimenstein/rss091.xml')
|
||||
,(u'Hélio Schwartsman', u'http://feeds.folha.uol.com.br/colunas/helioschwartsman/rss091.xml')
|
||||
,(u'Humberto Luiz Peron', u'http://feeds.folha.uol.com.br/colunas/futebolnarede/rss091.xml')
|
||||
,(u'João Pereira Coutinho', u'http://feeds.folha.uol.com.br/colunas/joaopereiracoutinho/rss091.xml')
|
||||
,(u'José Antonio Ramalho', u'http://feeds.folha.uol.com.br/colunas/canalaberto/rss091.xml')
|
||||
,(u'Kennedy Alencar', u'http://feeds.folha.uol.com.br/colunas/kennedyalencar/rss091.xml')
|
||||
,(u'Luiz Caversan', u'http://feeds.folha.uol.com.br/colunas/luizcaversan/rss091.xml')
|
||||
,(u'Luiz Rivoiro', u'http://feeds.folha.uol.com.br/colunas/paiepai/rss091.xml')
|
||||
,(u'Marcelo Leite', u'http://feeds.folha.uol.com.br/colunas/marceloleite/rss091.xml')
|
||||
,(u'Sérgio Malbergier', u'http://feeds.folha.uol.com.br/colunas/sergiomalbergier/rss091.xml')
|
||||
,(u'Sylvia Colombo', u'http://feeds.folha.uol.com.br/colunas/sylviacolombo/rss091.xml')
|
||||
,(u'Valdo Cruz', u'http://feeds.folha.uol.com.br/colunas/valdocruz/rss091.xml')
|
||||
]
|
||||
|
||||
|
||||
conversion_options = {
|
||||
'title' : title
|
||||
,'comments' : description
|
||||
,'publisher' : publisher
|
||||
,'tags' : category
|
||||
,'language' : LANGUAGE
|
||||
,'linearize_tables': True
|
||||
}
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
if not soup.find(attrs={'http-equiv':'Content-Language'}):
|
||||
meta0 = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.LANGHTM)])
|
||||
soup.head.insert(0,meta0)
|
||||
if not soup.find(attrs={'http-equiv':'Content-Type'}):
|
||||
meta1 = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset="+self.ENCHTM)])
|
||||
soup.head.insert(0,meta1)
|
||||
return soup
|
||||
|
||||
def postprocess_html(self, soup, first):
|
||||
#process all the images. assumes that the new html has the correct path
|
||||
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
|
||||
iurl = tag['src']
|
||||
img = Image()
|
||||
img.open(iurl)
|
||||
width, height = img.size
|
||||
print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
|
||||
if img < 0:
|
||||
raise RuntimeError('Out of memory')
|
||||
pw = PixelWand()
|
||||
if( width > height and width > 590) :
|
||||
print 'Rotate image'
|
||||
img.rotate(pw, -90)
|
||||
img.save(iurl)
|
||||
return soup
|
||||
|
||||
def get_cover_url(self):
|
||||
cover_url = self.CAPA
|
||||
pedido = Request(self.CAPA)
|
||||
pedido.add_header('User-agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; '+self.LANGHTM+'; userid='+self.THUMBALIZR_API+') Calibre/0.8.47 (like Gecko)')
|
||||
pedido.add_header('Accept-Charset',self.ENCHTM)
|
||||
pedido.add_header('Referer',self.SCREENSHOT)
|
||||
try:
|
||||
resposta = urlopen(pedido)
|
||||
soup = BeautifulSoup(resposta)
|
||||
cover_item = soup.find('body')
|
||||
if cover_item:
|
||||
cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
|
||||
return cover_url
|
||||
except URLError:
|
||||
cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
|
||||
return cover_url
|
||||
# -*- coding: utf-8 -*-
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from datetime import datetime, timedelta
|
||||
from calibre.ebooks.BeautifulSoup import Tag,BeautifulSoup
|
||||
from calibre.utils.magick import Image, PixelWand
|
||||
from urllib2 import Request, urlopen, URLError
|
||||
|
||||
class FolhaOnline(BasicNewsRecipe):
|
||||
THUMBALIZR_API = '' # ---->Get your at http://www.thumbalizr.com/ and put here
|
||||
LANGUAGE = 'pt_br'
|
||||
language = 'pt_BR'
|
||||
LANGHTM = 'pt-br'
|
||||
ENCODING = 'cp1252'
|
||||
ENCHTM = 'iso-8859-1'
|
||||
directionhtm = 'ltr'
|
||||
requires_version = (0,7,47)
|
||||
news = True
|
||||
|
||||
title = u'Folha de S\xE3o Paulo'
|
||||
__author__ = 'Euler Alves and Alex Mitrani'
|
||||
description = u'Brazilian news from Folha de S\xE3o Paulo'
|
||||
publisher = u'Folha de S\xE3o Paulo'
|
||||
category = 'news, rss'
|
||||
|
||||
oldest_article = 4
|
||||
max_articles_per_feed = 100
|
||||
summary_length = 1000
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
timefmt = ' [%d %b %Y (%a)]'
|
||||
|
||||
html2lrf_options = [
|
||||
'--comment', description
|
||||
,'--category', category
|
||||
,'--publisher', publisher
|
||||
]
|
||||
|
||||
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
|
||||
|
||||
hoje = datetime.now()
|
||||
pubdate = hoje.strftime('%a, %d %b')
|
||||
if hoje.hour<6:
|
||||
hoje = hoje-timedelta(days=1)
|
||||
CAPA = 'http://www1.folha.uol.com.br/fsp/images/cp'+hoje.strftime('%d%m%Y')+'.jpg'
|
||||
SCREENSHOT = 'http://www1.folha.uol.com.br/'
|
||||
cover_margins = (0,0,'white')
|
||||
masthead_url = 'http://f.i.uol.com.br/fsp/furniture/images/lgo-fsp-430x50-ffffff.gif'
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'articleNew'})]
|
||||
remove_tags = [
|
||||
dict(name='div',
|
||||
attrs={'id':[
|
||||
'articleButton'
|
||||
,'bookmarklets'
|
||||
,'ad-180x150-1'
|
||||
,'contextualAdsArticle'
|
||||
,'articleEnd'
|
||||
,'articleComments'
|
||||
]})
|
||||
,dict(name='div',
|
||||
attrs={'class':[
|
||||
'openBox adslibraryArticle'
|
||||
,'toolbar'
|
||||
]})
|
||||
|
||||
,dict(name='a')
|
||||
,dict(name='iframe')
|
||||
,dict(name='link')
|
||||
,dict(name='script')
|
||||
,dict(name='li')
|
||||
]
|
||||
remove_tags_after = dict(name='div',attrs={'id':'articleEnd'})
|
||||
|
||||
feeds = [
|
||||
(u'Em cima da hora', u'http://feeds.folha.uol.com.br/emcimadahora/rss091.xml')
|
||||
,(u'Cotidiano', u'http://feeds.folha.uol.com.br/folha/cotidiano/rss091.xml')
|
||||
,(u'Brasil', u'http://feeds.folha.uol.com.br/folha/brasil/rss091.xml')
|
||||
,(u'Mundo', u'http://feeds.folha.uol.com.br/mundo/rss091.xml')
|
||||
,(u'Poder', u'http://feeds.folha.uol.com.br/poder/rss091.xml')
|
||||
,(u'Mercado', u'http://feeds.folha.uol.com.br/folha/dinheiro/rss091.xml')
|
||||
,(u'Saber', u'http://feeds.folha.uol.com.br/folha/educacao/rss091.xml')
|
||||
,(u'Tec', u'http://feeds.folha.uol.com.br/folha/informatica/rss091.xml')
|
||||
,(u'Ilustrada', u'http://feeds.folha.uol.com.br/folha/ilustrada/rss091.xml')
|
||||
,(u'Ambiente', u'http://feeds.folha.uol.com.br/ambiente/rss091.xml')
|
||||
,(u'Bichos', u'http://feeds.folha.uol.com.br/bichos/rss091.xml')
|
||||
,(u'Ci\xEAncia', u'http://feeds.folha.uol.com.br/ciencia/rss091.xml')
|
||||
,(u'Equil\xEDbrio e Sa\xFAde', u'http://feeds.folha.uol.com.br/equilibrioesaude/rss091.xml')
|
||||
,(u'Turismo', u'http://feeds.folha.uol.com.br/folha/turismo/rss091.xml')
|
||||
,(u'Esporte', u'http://feeds.folha.uol.com.br/folha/esporte/rss091.xml')
|
||||
,(u'Zapping', u'http://feeds.folha.uol.com.br/colunas/zapping/rss091.xml')
|
||||
,(u'Cida Santos', u'http://feeds.folha.uol.com.br/colunas/cidasantos/rss091.xml')
|
||||
,(u'Clóvis Rossi', u'http://feeds.folha.uol.com.br/colunas/clovisrossi/rss091.xml')
|
||||
,(u'Eliane Cantanhêde', u'http://feeds.folha.uol.com.br/colunas/elianecantanhede/rss091.xml')
|
||||
,(u'Fernando Canzian', u'http://feeds.folha.uol.com.br/colunas/fernandocanzian/rss091.xml')
|
||||
,(u'Gilberto Dimenstein', u'http://feeds.folha.uol.com.br/colunas/gilbertodimenstein/rss091.xml')
|
||||
,(u'Hélio Schwartsman', u'http://feeds.folha.uol.com.br/colunas/helioschwartsman/rss091.xml')
|
||||
,(u'Humberto Luiz Peron', u'http://feeds.folha.uol.com.br/colunas/futebolnarede/rss091.xml')
|
||||
,(u'João Pereira Coutinho', u'http://feeds.folha.uol.com.br/colunas/joaopereiracoutinho/rss091.xml')
|
||||
,(u'José Antonio Ramalho', u'http://feeds.folha.uol.com.br/colunas/canalaberto/rss091.xml')
|
||||
,(u'Kennedy Alencar', u'http://feeds.folha.uol.com.br/colunas/kennedyalencar/rss091.xml')
|
||||
,(u'Luiz Caversan', u'http://feeds.folha.uol.com.br/colunas/luizcaversan/rss091.xml')
|
||||
,(u'Luiz Rivoiro', u'http://feeds.folha.uol.com.br/colunas/paiepai/rss091.xml')
|
||||
,(u'Marcelo Leite', u'http://feeds.folha.uol.com.br/colunas/marceloleite/rss091.xml')
|
||||
,(u'Sérgio Malbergier', u'http://feeds.folha.uol.com.br/colunas/sergiomalbergier/rss091.xml')
|
||||
,(u'Sylvia Colombo', u'http://feeds.folha.uol.com.br/colunas/sylviacolombo/rss091.xml')
|
||||
,(u'Valdo Cruz', u'http://feeds.folha.uol.com.br/colunas/valdocruz/rss091.xml')
|
||||
]
|
||||
|
||||
|
||||
conversion_options = {
|
||||
'title' : title
|
||||
,'comments' : description
|
||||
,'publisher' : publisher
|
||||
,'tags' : category
|
||||
,'language' : LANGUAGE
|
||||
,'linearize_tables': True
|
||||
}
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
if not soup.find(attrs={'http-equiv':'Content-Language'}):
|
||||
meta0 = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.LANGHTM)])
|
||||
soup.head.insert(0,meta0)
|
||||
if not soup.find(attrs={'http-equiv':'Content-Type'}):
|
||||
meta1 = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset="+self.ENCHTM)])
|
||||
soup.head.insert(0,meta1)
|
||||
return soup
|
||||
|
||||
def postprocess_html(self, soup, first):
|
||||
#process all the images. assumes that the new html has the correct path
|
||||
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
|
||||
iurl = tag['src']
|
||||
img = Image()
|
||||
img.open(iurl)
|
||||
width, height = img.size
|
||||
print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
|
||||
if img < 0:
|
||||
raise RuntimeError('Out of memory')
|
||||
pw = PixelWand()
|
||||
if( width > height and width > 590) :
|
||||
print 'Rotate image'
|
||||
img.rotate(pw, -90)
|
||||
img.save(iurl)
|
||||
return soup
|
||||
|
||||
def get_cover_url(self):
|
||||
cover_url = self.CAPA
|
||||
pedido = Request(self.CAPA)
|
||||
pedido.add_header('User-agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; '+self.LANGHTM+'; userid='+self.THUMBALIZR_API+') Calibre/0.8.47 (like Gecko)')
|
||||
pedido.add_header('Accept-Charset',self.ENCHTM)
|
||||
pedido.add_header('Referer',self.SCREENSHOT)
|
||||
try:
|
||||
resposta = urlopen(pedido)
|
||||
soup = BeautifulSoup(resposta)
|
||||
cover_item = soup.find('body')
|
||||
if cover_item:
|
||||
cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
|
||||
return cover_url
|
||||
except URLError:
|
||||
cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
|
||||
return cover_url
|
||||
|
||||
@ -1,35 +1,35 @@
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
||||
|
||||
import re
|
||||
import string
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class GazetaPlSzczecin(BasicNewsRecipe):
|
||||
title = u'Gazeta Wyborcza Szczecin'
|
||||
description = u'Wiadomości ze Szczecina na portalu Gazeta.pl.'
|
||||
__author__ = u'Michał Szkutnik'
|
||||
__license__ = u'GPL v3'
|
||||
language = 'pl'
|
||||
publisher = 'Agora S.A.'
|
||||
category = 'news, szczecin'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
auto_cleanup = True
|
||||
remove_tags = [ { "name" : "a", "attrs" : { "href" : "http://szczecin.gazeta.pl/szczecin/www.gazeta.pl" }}]
|
||||
cover_url = "http://bi.gazeta.pl/i/hp/hp2009/logo.gif"
|
||||
feeds = [(u'Wszystkie', u'http://rss.feedsportal.com/c/32739/f/530434/index.rss')]
|
||||
|
||||
def get_article_url(self, article):
|
||||
s = re.search("""/0L(szczecin.*)/story01.htm""", article.link)
|
||||
s = s.group(1)
|
||||
replacements = { "0B" : ".", "0C" : "/", "0H" : ",", "0I" : "_"}
|
||||
for (a, b) in replacements.iteritems():
|
||||
s = string.replace(s, a, b)
|
||||
s = string.replace(s, "0A", "0")
|
||||
return "http://"+s
|
||||
|
||||
def print_version(self, url):
|
||||
s = re.search("""/(\d*),(\d*),(\d*),.*\.html""", url)
|
||||
no1 = s.group(2)
|
||||
no2 = s.group(3)
|
||||
return """http://szczecin.gazeta.pl/szczecin/2029020,%s,%s.html""" % (no1, no2)
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
||||
|
||||
import re
|
||||
import string
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class GazetaPlSzczecin(BasicNewsRecipe):
|
||||
title = u'Gazeta Wyborcza Szczecin'
|
||||
description = u'Wiadomości ze Szczecina na portalu Gazeta.pl.'
|
||||
__author__ = u'Michał Szkutnik'
|
||||
__license__ = u'GPL v3'
|
||||
language = 'pl'
|
||||
publisher = 'Agora S.A.'
|
||||
category = 'news, szczecin'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
auto_cleanup = True
|
||||
remove_tags = [ { "name" : "a", "attrs" : { "href" : "http://szczecin.gazeta.pl/szczecin/www.gazeta.pl" }}]
|
||||
cover_url = "http://bi.gazeta.pl/i/hp/hp2009/logo.gif"
|
||||
feeds = [(u'Wszystkie', u'http://rss.feedsportal.com/c/32739/f/530434/index.rss')]
|
||||
|
||||
def get_article_url(self, article):
|
||||
s = re.search("""/0L(szczecin.*)/story01.htm""", article.link)
|
||||
s = s.group(1)
|
||||
replacements = { "0B" : ".", "0C" : "/", "0H" : ",", "0I" : "_"}
|
||||
for (a, b) in replacements.iteritems():
|
||||
s = string.replace(s, a, b)
|
||||
s = string.replace(s, "0A", "0")
|
||||
return "http://"+s
|
||||
|
||||
def print_version(self, url):
|
||||
s = re.search("""/(\d*),(\d*),(\d*),.*\.html""", url)
|
||||
no1 = s.group(2)
|
||||
no2 = s.group(3)
|
||||
return """http://szczecin.gazeta.pl/szczecin/2029020,%s,%s.html""" % (no1, no2)
|
||||
|
||||
@ -1,43 +1,43 @@
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
||||
|
||||
import re
|
||||
import string
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1322322819(BasicNewsRecipe):
|
||||
title = u'GS24.pl (Głos Szczeciński)'
|
||||
description = u'Internetowy serwis Głosu Szczecińskiego'
|
||||
__author__ = u'Michał Szkutnik'
|
||||
__license__ = u'GPL v3'
|
||||
language = 'pl'
|
||||
publisher = 'Media Regionalne sp. z o.o.'
|
||||
category = 'news, szczecin'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
auto_cleanup = True
|
||||
cover_url = "http://www.gs24.pl/images/top_logo.png"
|
||||
|
||||
feeds = [
|
||||
# (u'Wszystko', u'http://www.gs24.pl/rss.xml'),
|
||||
(u'Szczecin', u'http://www.gs24.pl/szczecin.xml'),
|
||||
(u'Stargard', u'http://www.gs24.pl/stargard.xml'),
|
||||
(u'Świnoujście', u'http://www.gs24.pl/swinoujscie.xml'),
|
||||
(u'Goleniów', u'http://www.gs24.pl/goleniow.xml'),
|
||||
(u'Gryfice', u'http://www.gs24.pl/gryfice.xml'),
|
||||
(u'Kamień Pomorski', u'http://www.gs24.pl/kamienpomorski.xml'),
|
||||
(u'Police', u'http://www.gs24.pl/police.xml'),
|
||||
(u'Region', u'http://www.gs24.pl/region.xml'),
|
||||
(u'Sport', u'http://www.gs24.pl/sport.xml'),
|
||||
]
|
||||
|
||||
def get_article_url(self, article):
|
||||
s = re.search("""/0L0S(gs24.*)/story01.htm""", article.link)
|
||||
s = s.group(1)
|
||||
replacements = { "0B" : ".", "0C" : "/", "0H" : ",", "0I" : "_", "0D" : "?", "0F" : "="}
|
||||
for (a, b) in replacements.iteritems():
|
||||
s = string.replace(s, a, b)
|
||||
s = string.replace(s, "0A", "0")
|
||||
return "http://"+s
|
||||
|
||||
def print_version(self, url):
|
||||
return url + "&Template=printpicart"
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
||||
|
||||
import re
|
||||
import string
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1322322819(BasicNewsRecipe):
|
||||
title = u'GS24.pl (Głos Szczeciński)'
|
||||
description = u'Internetowy serwis Głosu Szczecińskiego'
|
||||
__author__ = u'Michał Szkutnik'
|
||||
__license__ = u'GPL v3'
|
||||
language = 'pl'
|
||||
publisher = 'Media Regionalne sp. z o.o.'
|
||||
category = 'news, szczecin'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
auto_cleanup = True
|
||||
cover_url = "http://www.gs24.pl/images/top_logo.png"
|
||||
|
||||
feeds = [
|
||||
# (u'Wszystko', u'http://www.gs24.pl/rss.xml'),
|
||||
(u'Szczecin', u'http://www.gs24.pl/szczecin.xml'),
|
||||
(u'Stargard', u'http://www.gs24.pl/stargard.xml'),
|
||||
(u'Świnoujście', u'http://www.gs24.pl/swinoujscie.xml'),
|
||||
(u'Goleniów', u'http://www.gs24.pl/goleniow.xml'),
|
||||
(u'Gryfice', u'http://www.gs24.pl/gryfice.xml'),
|
||||
(u'Kamień Pomorski', u'http://www.gs24.pl/kamienpomorski.xml'),
|
||||
(u'Police', u'http://www.gs24.pl/police.xml'),
|
||||
(u'Region', u'http://www.gs24.pl/region.xml'),
|
||||
(u'Sport', u'http://www.gs24.pl/sport.xml'),
|
||||
]
|
||||
|
||||
def get_article_url(self, article):
|
||||
s = re.search("""/0L0S(gs24.*)/story01.htm""", article.link)
|
||||
s = s.group(1)
|
||||
replacements = { "0B" : ".", "0C" : "/", "0H" : ",", "0I" : "_", "0D" : "?", "0F" : "="}
|
||||
for (a, b) in replacements.iteritems():
|
||||
s = string.replace(s, a, b)
|
||||
s = string.replace(s, "0A", "0")
|
||||
return "http://"+s
|
||||
|
||||
def print_version(self, url):
|
||||
return url + "&Template=printpicart"
|
||||
|
||||
@ -1,47 +1,47 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Seongkyoun Yoo <seongkyoun.yoo at gmail.com>'
|
||||
'''
|
||||
Profile to download The Hankyoreh
|
||||
'''
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Hankyoreh(BasicNewsRecipe):
|
||||
title = u'Hankyoreh'
|
||||
language = 'ko'
|
||||
description = u'The Hankyoreh News articles'
|
||||
__author__ = 'Seongkyoun Yoo'
|
||||
oldest_article = 5
|
||||
recursions = 1
|
||||
max_articles_per_feed = 5
|
||||
no_stylesheets = True
|
||||
keep_only_tags = [
|
||||
dict(name='tr', attrs={'height':['60px']}),
|
||||
dict(id=['fontSzArea'])
|
||||
]
|
||||
remove_tags = [
|
||||
dict(target='_blank'),
|
||||
dict(name='td', attrs={'style':['padding: 10px 8px 5px 8px;']}),
|
||||
dict(name='iframe', attrs={'width':['590']}),
|
||||
]
|
||||
remove_tags_after = [
|
||||
dict(target='_top')
|
||||
]
|
||||
feeds = [
|
||||
('All News','http://www.hani.co.kr/rss/'),
|
||||
('Politics','http://www.hani.co.kr/rss/politics/'),
|
||||
('Economy','http://www.hani.co.kr/rss/economy/'),
|
||||
('Society','http://www.hani.co.kr/rss/society/'),
|
||||
('International','http://www.hani.co.kr/rss/international/'),
|
||||
('Culture','http://www.hani.co.kr/rss/culture/'),
|
||||
('Sports','http://www.hani.co.kr/rss/sports/'),
|
||||
('Science','http://www.hani.co.kr/rss/science/'),
|
||||
('Opinion','http://www.hani.co.kr/rss/opinion/'),
|
||||
('Cartoon','http://www.hani.co.kr/rss/cartoon/'),
|
||||
('English Edition','http://www.hani.co.kr/rss/english_edition/'),
|
||||
('Specialsection','http://www.hani.co.kr/rss/specialsection/'),
|
||||
('Hanionly','http://www.hani.co.kr/rss/hanionly/'),
|
||||
('Hkronly','http://www.hani.co.kr/rss/hkronly/'),
|
||||
('Multihani','http://www.hani.co.kr/rss/multihani/'),
|
||||
('Lead','http://www.hani.co.kr/rss/lead/'),
|
||||
('Newsrank','http://www.hani.co.kr/rss/newsrank/'),
|
||||
]
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Seongkyoun Yoo <seongkyoun.yoo at gmail.com>'
|
||||
'''
|
||||
Profile to download The Hankyoreh
|
||||
'''
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Hankyoreh(BasicNewsRecipe):
|
||||
title = u'Hankyoreh'
|
||||
language = 'ko'
|
||||
description = u'The Hankyoreh News articles'
|
||||
__author__ = 'Seongkyoun Yoo'
|
||||
oldest_article = 5
|
||||
recursions = 1
|
||||
max_articles_per_feed = 5
|
||||
no_stylesheets = True
|
||||
keep_only_tags = [
|
||||
dict(name='tr', attrs={'height':['60px']}),
|
||||
dict(id=['fontSzArea'])
|
||||
]
|
||||
remove_tags = [
|
||||
dict(target='_blank'),
|
||||
dict(name='td', attrs={'style':['padding: 10px 8px 5px 8px;']}),
|
||||
dict(name='iframe', attrs={'width':['590']}),
|
||||
]
|
||||
remove_tags_after = [
|
||||
dict(target='_top')
|
||||
]
|
||||
feeds = [
|
||||
('All News','http://www.hani.co.kr/rss/'),
|
||||
('Politics','http://www.hani.co.kr/rss/politics/'),
|
||||
('Economy','http://www.hani.co.kr/rss/economy/'),
|
||||
('Society','http://www.hani.co.kr/rss/society/'),
|
||||
('International','http://www.hani.co.kr/rss/international/'),
|
||||
('Culture','http://www.hani.co.kr/rss/culture/'),
|
||||
('Sports','http://www.hani.co.kr/rss/sports/'),
|
||||
('Science','http://www.hani.co.kr/rss/science/'),
|
||||
('Opinion','http://www.hani.co.kr/rss/opinion/'),
|
||||
('Cartoon','http://www.hani.co.kr/rss/cartoon/'),
|
||||
('English Edition','http://www.hani.co.kr/rss/english_edition/'),
|
||||
('Specialsection','http://www.hani.co.kr/rss/specialsection/'),
|
||||
('Hanionly','http://www.hani.co.kr/rss/hanionly/'),
|
||||
('Hkronly','http://www.hani.co.kr/rss/hkronly/'),
|
||||
('Multihani','http://www.hani.co.kr/rss/multihani/'),
|
||||
('Lead','http://www.hani.co.kr/rss/lead/'),
|
||||
('Newsrank','http://www.hani.co.kr/rss/newsrank/'),
|
||||
]
|
||||
|
||||
@ -1,25 +1,25 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Seongkyoun Yoo <seongkyoun.yoo at gmail.com>'
|
||||
'''
|
||||
Profile to download The Hankyoreh
|
||||
'''
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Hankyoreh21(BasicNewsRecipe):
|
||||
title = u'Hankyoreh21'
|
||||
language = 'ko'
|
||||
description = u'The Hankyoreh21 Magazine articles'
|
||||
__author__ = 'Seongkyoun Yoo'
|
||||
oldest_article = 20
|
||||
recursions = 1
|
||||
max_articles_per_feed = 120
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
keep_only_tags = [
|
||||
dict(name='font', attrs={'class':'t18bk'}),
|
||||
dict(id=['fontSzArea'])
|
||||
]
|
||||
|
||||
feeds = [
|
||||
('Hani21','http://h21.hani.co.kr/rss/ '),
|
||||
]
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Seongkyoun Yoo <seongkyoun.yoo at gmail.com>'
|
||||
'''
|
||||
Profile to download The Hankyoreh
|
||||
'''
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Hankyoreh21(BasicNewsRecipe):
|
||||
title = u'Hankyoreh21'
|
||||
language = 'ko'
|
||||
description = u'The Hankyoreh21 Magazine articles'
|
||||
__author__ = 'Seongkyoun Yoo'
|
||||
oldest_article = 20
|
||||
recursions = 1
|
||||
max_articles_per_feed = 120
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
keep_only_tags = [
|
||||
dict(name='font', attrs={'class':'t18bk'}),
|
||||
dict(id=['fontSzArea'])
|
||||
]
|
||||
|
||||
feeds = [
|
||||
('Hani21','http://h21.hani.co.kr/rss/ '),
|
||||
]
|
||||
|
||||
@ -1,47 +1,47 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class HindustanTimes(BasicNewsRecipe):
|
||||
title = u'Huffington Post UK'
|
||||
language = 'en_GB'
|
||||
__author__ = 'Krittika Goyal'
|
||||
oldest_article = 2 #days
|
||||
max_articles_per_feed = 25
|
||||
#encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
|
||||
no_stylesheets = True
|
||||
auto_cleanup = True
|
||||
auto_cleanup_keep = '//div[@class="articleBody"]'
|
||||
|
||||
feeds = [
|
||||
('UK Politics',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-politics/news.xml'),
|
||||
('UK Entertainment',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-entertainment/news.xml'),
|
||||
('UK Style',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-style/news.xml'),
|
||||
('UK Fashion:',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-fashion/news.xml'),
|
||||
('UK Universities:',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-universities-education/news.xml'),
|
||||
('UK World',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-world/news.xml'),
|
||||
('UK Lifestyle',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-lifestyle/news.xml'),
|
||||
('UK Comedy',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-comedy/news.xml'),
|
||||
('UK Celebrity',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-celebrity/news.xml'),
|
||||
('UK Culture',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-culture/news.xml'),
|
||||
('UK News',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk/news.xml'),
|
||||
('UK Tech',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-tech/news.xml'),
|
||||
('UK Sport',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-sport/news.xml'),
|
||||
]
|
||||
def get_article_url(self, entry):
|
||||
if entry.links:
|
||||
return entry.links[0]['href']
|
||||
return BasicNewsRecipe.get_article_url(self, entry)
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class HindustanTimes(BasicNewsRecipe):
|
||||
title = u'Huffington Post UK'
|
||||
language = 'en_GB'
|
||||
__author__ = 'Krittika Goyal'
|
||||
oldest_article = 2 #days
|
||||
max_articles_per_feed = 25
|
||||
#encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
|
||||
no_stylesheets = True
|
||||
auto_cleanup = True
|
||||
auto_cleanup_keep = '//div[@class="articleBody"]'
|
||||
|
||||
feeds = [
|
||||
('UK Politics',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-politics/news.xml'),
|
||||
('UK Entertainment',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-entertainment/news.xml'),
|
||||
('UK Style',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-style/news.xml'),
|
||||
('UK Fashion:',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-fashion/news.xml'),
|
||||
('UK Universities:',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-universities-education/news.xml'),
|
||||
('UK World',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-world/news.xml'),
|
||||
('UK Lifestyle',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-lifestyle/news.xml'),
|
||||
('UK Comedy',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-comedy/news.xml'),
|
||||
('UK Celebrity',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-celebrity/news.xml'),
|
||||
('UK Culture',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-culture/news.xml'),
|
||||
('UK News',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk/news.xml'),
|
||||
('UK Tech',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-tech/news.xml'),
|
||||
('UK Sport',
|
||||
'http://www.huffingtonpost.com/feeds/verticals/uk-sport/news.xml'),
|
||||
]
|
||||
def get_article_url(self, entry):
|
||||
if entry.links:
|
||||
return entry.links[0]['href']
|
||||
return BasicNewsRecipe.get_article_url(self, entry)
|
||||
|
||||
@ -1,110 +1,110 @@
|
||||
from calibre import strftime
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
|
||||
MANIFESTO_BASEURL = 'http://www.ilmanifesto.it/'
|
||||
|
||||
class IlManifesto(BasicNewsRecipe):
|
||||
title = 'Il Manifesto'
|
||||
__author__ = 'Giacomo Lacava'
|
||||
description = 'quotidiano comunista - ultima edizione html disponibile'
|
||||
publication_type = 'newspaper'
|
||||
publisher = 'il manifesto coop. editrice a r.l.'
|
||||
language = 'it'
|
||||
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
delay = 1
|
||||
no_stylesheets = True
|
||||
simultaneous_downloads = 5
|
||||
timeout = 30
|
||||
auto_cleanup = True
|
||||
remove_tags = [dict(name='div', attrs={'class':'column_1 float_left'})]
|
||||
remove_tags_before = dict(name='div',attrs={'class':'column_2 float_right'})
|
||||
remove_tags_after = dict(id='myPrintArea')
|
||||
|
||||
manifesto_index = None
|
||||
manifesto_datestr = None
|
||||
|
||||
def _set_manifesto_index(self):
|
||||
if self.manifesto_index == None:
|
||||
startUrl = MANIFESTO_BASEURL + 'area-abbonati/in-edicola/'
|
||||
startSoup = self.index_to_soup(startUrl)
|
||||
lastEdition = startSoup.findAll('div',id='accordion_inedicola')[1].find('a')['href']
|
||||
del(startSoup)
|
||||
self.manifesto_index = MANIFESTO_BASEURL + lastEdition
|
||||
urlsplit = lastEdition.split('/')
|
||||
self.manifesto_datestr = urlsplit[-1]
|
||||
if urlsplit[-1] == '':
|
||||
self.manifesto_datestr = urlsplit[-2]
|
||||
|
||||
|
||||
|
||||
def get_cover_url(self):
|
||||
self._set_manifesto_index()
|
||||
url = MANIFESTO_BASEURL + 'fileadmin/archivi/in_edicola/%sprimapagina.gif' % self.manifesto_datestr
|
||||
return url
|
||||
|
||||
def parse_index(self):
|
||||
self._set_manifesto_index()
|
||||
soup = self.index_to_soup(self.manifesto_index)
|
||||
feedLinks = soup.find('div',id='accordion_inedicola').findAll('a')
|
||||
result = []
|
||||
for feed in feedLinks:
|
||||
articles = []
|
||||
feedName = feed.find('h2').string
|
||||
feedUrl = MANIFESTO_BASEURL + feed['href']
|
||||
feedSoup = self.index_to_soup(feedUrl)
|
||||
indexRoot = feedSoup.find('div',attrs={'class':'column1'})
|
||||
for div in indexRoot.findAll('div',attrs={'class':'strumenti1_inedicola'}):
|
||||
artLink = div.find('a')
|
||||
if artLink is None: continue # empty div
|
||||
title = artLink.string
|
||||
url = MANIFESTO_BASEURL + artLink['href']
|
||||
|
||||
description = ''
|
||||
descNode = div.find('div',attrs={'class':'text_12'})
|
||||
if descNode is not None:
|
||||
description = descNode.string
|
||||
|
||||
author = ''
|
||||
authNode = div.find('div',attrs={'class':'firma'})
|
||||
if authNode is not None:
|
||||
author = authNode.string
|
||||
|
||||
articleText = ''
|
||||
article = {
|
||||
'title':title,
|
||||
'url':url,
|
||||
'date': strftime('%d %B %Y'),
|
||||
'description': description,
|
||||
'content': articleText,
|
||||
'author': author
|
||||
}
|
||||
articles.append(article)
|
||||
result.append((feedName,articles))
|
||||
return result
|
||||
|
||||
|
||||
def extract_readable_article(self, html, url):
|
||||
|
||||
bs = BeautifulSoup(html)
|
||||
col1 = bs.find('div',attrs={'class':'column1'})
|
||||
|
||||
content = col1.find('div',attrs={'class':'bodytext'})
|
||||
title = bs.find(id='titolo_articolo').string
|
||||
author = col1.find('span',attrs={'class':'firma'})
|
||||
subtitle = ''
|
||||
subNode = col1.findPrevious('div',attrs={'class':'occhiello_rosso'})
|
||||
if subNode is not None:
|
||||
subtitle = subNode
|
||||
summary = ''
|
||||
sommNode = bs.find('div',attrs={'class':'sommario'})
|
||||
if sommNode is not None:
|
||||
summary = sommNode
|
||||
|
||||
template = "<html><head><title>%(title)s</title></head><body><h1>%(title)s</h1><h2>%(subtitle)s</h2><h3>%(author)s</h3><div style='font-size: x-large;'>%(summary)s</div><div>%(content)s</div></body></html>"
|
||||
del(bs)
|
||||
return template % dict(title=title,subtitle=subtitle,author=author,summary=summary,content=content)
|
||||
|
||||
|
||||
from calibre import strftime
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
|
||||
MANIFESTO_BASEURL = 'http://www.ilmanifesto.it/'
|
||||
|
||||
class IlManifesto(BasicNewsRecipe):
|
||||
title = 'Il Manifesto'
|
||||
__author__ = 'Giacomo Lacava'
|
||||
description = 'quotidiano comunista - ultima edizione html disponibile'
|
||||
publication_type = 'newspaper'
|
||||
publisher = 'il manifesto coop. editrice a r.l.'
|
||||
language = 'it'
|
||||
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
delay = 1
|
||||
no_stylesheets = True
|
||||
simultaneous_downloads = 5
|
||||
timeout = 30
|
||||
auto_cleanup = True
|
||||
remove_tags = [dict(name='div', attrs={'class':'column_1 float_left'})]
|
||||
remove_tags_before = dict(name='div',attrs={'class':'column_2 float_right'})
|
||||
remove_tags_after = dict(id='myPrintArea')
|
||||
|
||||
manifesto_index = None
|
||||
manifesto_datestr = None
|
||||
|
||||
def _set_manifesto_index(self):
|
||||
if self.manifesto_index == None:
|
||||
startUrl = MANIFESTO_BASEURL + 'area-abbonati/in-edicola/'
|
||||
startSoup = self.index_to_soup(startUrl)
|
||||
lastEdition = startSoup.findAll('div',id='accordion_inedicola')[1].find('a')['href']
|
||||
del(startSoup)
|
||||
self.manifesto_index = MANIFESTO_BASEURL + lastEdition
|
||||
urlsplit = lastEdition.split('/')
|
||||
self.manifesto_datestr = urlsplit[-1]
|
||||
if urlsplit[-1] == '':
|
||||
self.manifesto_datestr = urlsplit[-2]
|
||||
|
||||
|
||||
|
||||
def get_cover_url(self):
|
||||
self._set_manifesto_index()
|
||||
url = MANIFESTO_BASEURL + 'fileadmin/archivi/in_edicola/%sprimapagina.gif' % self.manifesto_datestr
|
||||
return url
|
||||
|
||||
def parse_index(self):
|
||||
self._set_manifesto_index()
|
||||
soup = self.index_to_soup(self.manifesto_index)
|
||||
feedLinks = soup.find('div',id='accordion_inedicola').findAll('a')
|
||||
result = []
|
||||
for feed in feedLinks:
|
||||
articles = []
|
||||
feedName = feed.find('h2').string
|
||||
feedUrl = MANIFESTO_BASEURL + feed['href']
|
||||
feedSoup = self.index_to_soup(feedUrl)
|
||||
indexRoot = feedSoup.find('div',attrs={'class':'column1'})
|
||||
for div in indexRoot.findAll('div',attrs={'class':'strumenti1_inedicola'}):
|
||||
artLink = div.find('a')
|
||||
if artLink is None: continue # empty div
|
||||
title = artLink.string
|
||||
url = MANIFESTO_BASEURL + artLink['href']
|
||||
|
||||
description = ''
|
||||
descNode = div.find('div',attrs={'class':'text_12'})
|
||||
if descNode is not None:
|
||||
description = descNode.string
|
||||
|
||||
author = ''
|
||||
authNode = div.find('div',attrs={'class':'firma'})
|
||||
if authNode is not None:
|
||||
author = authNode.string
|
||||
|
||||
articleText = ''
|
||||
article = {
|
||||
'title':title,
|
||||
'url':url,
|
||||
'date': strftime('%d %B %Y'),
|
||||
'description': description,
|
||||
'content': articleText,
|
||||
'author': author
|
||||
}
|
||||
articles.append(article)
|
||||
result.append((feedName,articles))
|
||||
return result
|
||||
|
||||
|
||||
def extract_readable_article(self, html, url):
|
||||
|
||||
bs = BeautifulSoup(html)
|
||||
col1 = bs.find('div',attrs={'class':'column1'})
|
||||
|
||||
content = col1.find('div',attrs={'class':'bodytext'})
|
||||
title = bs.find(id='titolo_articolo').string
|
||||
author = col1.find('span',attrs={'class':'firma'})
|
||||
subtitle = ''
|
||||
subNode = col1.findPrevious('div',attrs={'class':'occhiello_rosso'})
|
||||
if subNode is not None:
|
||||
subtitle = subNode
|
||||
summary = ''
|
||||
sommNode = bs.find('div',attrs={'class':'sommario'})
|
||||
if sommNode is not None:
|
||||
summary = sommNode
|
||||
|
||||
template = "<html><head><title>%(title)s</title></head><body><h1>%(title)s</h1><h2>%(subtitle)s</h2><h3>%(author)s</h3><div style='font-size: x-large;'>%(summary)s</div><div>%(content)s</div></body></html>"
|
||||
del(bs)
|
||||
return template % dict(title=title,subtitle=subtitle,author=author,summary=summary,content=content)
|
||||
|
||||
|
||||
|
||||
@ -1,34 +1,34 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class JakartaGlobe(BasicNewsRecipe):
|
||||
title = u'Jakarta Globe'
|
||||
oldest_article = 3
|
||||
max_articles_per_feed = 100
|
||||
|
||||
feeds = [
|
||||
(u'News', u'http://www.thejakartaglobe.com/pages/getrss/getrss-news.php'),
|
||||
(u'Business', u'http://www.thejakartaglobe.com/pages/getrss/getrss-business.php'),
|
||||
(u'Technology', u'http://www.thejakartaglobe.com/pages/getrss/getrss-tech.php'),
|
||||
(u'My Jakarta', u'http://www.thejakartaglobe.com/pages/getrss/getrss-myjakarta.php'),
|
||||
(u'International', u'http://www.thejakartaglobe.com/pages/getrss/getrss-international.php'),
|
||||
(u'Life and Times', u'http://www.thejakartaglobe.com/pages/getrss/getrss-lifeandtimes.php'),
|
||||
]
|
||||
__author__ = 'rty'
|
||||
pubisher = 'JakartaGlobe.com'
|
||||
description = 'JakartaGlobe, Indonesia, Newspaper'
|
||||
category = 'News, Indonesia'
|
||||
|
||||
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
language = 'en_ID'
|
||||
encoding = 'utf-8'
|
||||
conversion_options = {'linearize_tables':True}
|
||||
masthead_url = 'http://www.thejakartaglobe.com/pages/2010/images/jak-globe-logo.jpg'
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':'story'}),
|
||||
dict(name='span', attrs={'class':'headline'}),
|
||||
dict(name='div', attrs={'class':'story'}),
|
||||
dict(name='p', attrs={'id':'bodytext'})
|
||||
]
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class JakartaGlobe(BasicNewsRecipe):
|
||||
title = u'Jakarta Globe'
|
||||
oldest_article = 3
|
||||
max_articles_per_feed = 100
|
||||
|
||||
feeds = [
|
||||
(u'News', u'http://www.thejakartaglobe.com/pages/getrss/getrss-news.php'),
|
||||
(u'Business', u'http://www.thejakartaglobe.com/pages/getrss/getrss-business.php'),
|
||||
(u'Technology', u'http://www.thejakartaglobe.com/pages/getrss/getrss-tech.php'),
|
||||
(u'My Jakarta', u'http://www.thejakartaglobe.com/pages/getrss/getrss-myjakarta.php'),
|
||||
(u'International', u'http://www.thejakartaglobe.com/pages/getrss/getrss-international.php'),
|
||||
(u'Life and Times', u'http://www.thejakartaglobe.com/pages/getrss/getrss-lifeandtimes.php'),
|
||||
]
|
||||
__author__ = 'rty'
|
||||
pubisher = 'JakartaGlobe.com'
|
||||
description = 'JakartaGlobe, Indonesia, Newspaper'
|
||||
category = 'News, Indonesia'
|
||||
|
||||
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
language = 'en_ID'
|
||||
encoding = 'utf-8'
|
||||
conversion_options = {'linearize_tables':True}
|
||||
masthead_url = 'http://www.thejakartaglobe.com/pages/2010/images/jak-globe-logo.jpg'
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':'story'}),
|
||||
dict(name='span', attrs={'class':'headline'}),
|
||||
dict(name='div', attrs={'class':'story'}),
|
||||
dict(name='p', attrs={'id':'bodytext'})
|
||||
]
|
||||
|
||||
@ -1,37 +1,37 @@
|
||||
#!/usr/bin/python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Vadim Dyadkin, dyadkin@gmail.com'
|
||||
__author__ = 'Vadim Dyadkin'
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Computerra(BasicNewsRecipe):
|
||||
title = u'\u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u0440\u0430'
|
||||
oldest_article = 100
|
||||
__author__ = 'Vadim Dyadkin (edited by A. Chewi)'
|
||||
max_articles_per_feed = 50
|
||||
use_embedded_content = False
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
conversion_options = {'linearize_tables' : True}
|
||||
simultaneous_downloads = 5
|
||||
language = 'ru'
|
||||
description = u'Компьютерра: все новости про компьютеры, железо, новые технологии, информационные технологии'
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id': 'content'}),]
|
||||
|
||||
feeds = [(u'Компьютерра-Онлайн', 'http://feeds.feedburner.com/ct_news/'),]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id': ['fin', 'idc-container', 'idc-noscript',]}),
|
||||
dict(name='ul', attrs={'class': "related_post"}),
|
||||
dict(name='p', attrs={'class': 'info'}),
|
||||
dict(name='a', attrs={'class': 'twitter-share-button'}),
|
||||
dict(name='a', attrs={'type': 'button_count'}),
|
||||
dict(name='h2', attrs={})
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
return url + '?print=true'
|
||||
#!/usr/bin/python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Vadim Dyadkin, dyadkin@gmail.com'
|
||||
__author__ = 'Vadim Dyadkin'
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Computerra(BasicNewsRecipe):
|
||||
title = u'\u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u0440\u0430'
|
||||
oldest_article = 100
|
||||
__author__ = 'Vadim Dyadkin (edited by A. Chewi)'
|
||||
max_articles_per_feed = 50
|
||||
use_embedded_content = False
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
conversion_options = {'linearize_tables' : True}
|
||||
simultaneous_downloads = 5
|
||||
language = 'ru'
|
||||
description = u'Компьютерра: все новости про компьютеры, железо, новые технологии, информационные технологии'
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id': 'content'}),]
|
||||
|
||||
feeds = [(u'Компьютерра-Онлайн', 'http://feeds.feedburner.com/ct_news/'),]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id': ['fin', 'idc-container', 'idc-noscript',]}),
|
||||
dict(name='ul', attrs={'class': "related_post"}),
|
||||
dict(name='p', attrs={'class': 'info'}),
|
||||
dict(name='a', attrs={'class': 'twitter-share-button'}),
|
||||
dict(name='a', attrs={'type': 'button_count'}),
|
||||
dict(name='h2', attrs={})
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
return url + '?print=true'
|
||||
|
||||
@ -1,34 +1,34 @@
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
'''Calibre recipe to convert the RSS feeds of the Leipziger Volkszeitung to an ebook.'''
|
||||
|
||||
class SportsIllustratedRecipe(BasicNewsRecipe) :
|
||||
__author__ = 'a.peter'
|
||||
__copyright__ = 'a.peter'
|
||||
__license__ = 'GPL v3'
|
||||
language = 'de'
|
||||
description = 'Leipziger Volkszeitung Online RSS'
|
||||
version = 1
|
||||
title = u'Leipziger Volkszeitung Online RSS'
|
||||
timefmt = ' [%d.%m.%Y]'
|
||||
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
publication_type = 'newspaper'
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'article'})]
|
||||
remove_tags = [dict(name='div', attrs={'class':['ARTICLE_MORE', 'clearfloat']})]
|
||||
|
||||
feeds = [(u'Leipzig', u'http://nachrichten.lvz-online.de/rss/leipzig-rss.xml'),
|
||||
(u'Mitteldeutschland', u'http://nachrichten.lvz-online.de/rss/mitteldeutschland-rss.xml'),
|
||||
(u'Brennpunkte', u'http://nachrichten.lvz-online.de/rss/brennpunkte-rss.xml'),
|
||||
(u'Polizeiticker', u'http://nachrichten.lvz-online.de/rss/polizeiticker-rss.xml'),
|
||||
(u'Boulevard', u'http://nachrichten.lvz-online.de/rss/boulevard-rss.xml'),
|
||||
(u'Kultur', u'http://nachrichten.lvz-online.de/rss/kultur-rss.xml'),
|
||||
(u'Sport', u'http://nachrichten.lvz-online.de/rss/sport-rss.xml'),
|
||||
(u'Regionalsport', u'http://nachrichten.lvz-online.de/rss/regionalsport-rss.xml'),
|
||||
(u'Knipser', u'http://nachrichten.lvz-online.de/rss/knipser-rss.xml')]
|
||||
|
||||
def get_masthead_url(self):
|
||||
return 'http://www.lvz-online.de/resources/themes/standard/images/global/logo.gif'
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
'''Calibre recipe to convert the RSS feeds of the Leipziger Volkszeitung to an ebook.'''
|
||||
|
||||
class SportsIllustratedRecipe(BasicNewsRecipe) :
|
||||
__author__ = 'a.peter'
|
||||
__copyright__ = 'a.peter'
|
||||
__license__ = 'GPL v3'
|
||||
language = 'de'
|
||||
description = 'Leipziger Volkszeitung Online RSS'
|
||||
version = 1
|
||||
title = u'Leipziger Volkszeitung Online RSS'
|
||||
timefmt = ' [%d.%m.%Y]'
|
||||
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
publication_type = 'newspaper'
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'article'})]
|
||||
remove_tags = [dict(name='div', attrs={'class':['ARTICLE_MORE', 'clearfloat']})]
|
||||
|
||||
feeds = [(u'Leipzig', u'http://nachrichten.lvz-online.de/rss/leipzig-rss.xml'),
|
||||
(u'Mitteldeutschland', u'http://nachrichten.lvz-online.de/rss/mitteldeutschland-rss.xml'),
|
||||
(u'Brennpunkte', u'http://nachrichten.lvz-online.de/rss/brennpunkte-rss.xml'),
|
||||
(u'Polizeiticker', u'http://nachrichten.lvz-online.de/rss/polizeiticker-rss.xml'),
|
||||
(u'Boulevard', u'http://nachrichten.lvz-online.de/rss/boulevard-rss.xml'),
|
||||
(u'Kultur', u'http://nachrichten.lvz-online.de/rss/kultur-rss.xml'),
|
||||
(u'Sport', u'http://nachrichten.lvz-online.de/rss/sport-rss.xml'),
|
||||
(u'Regionalsport', u'http://nachrichten.lvz-online.de/rss/regionalsport-rss.xml'),
|
||||
(u'Knipser', u'http://nachrichten.lvz-online.de/rss/knipser-rss.xml')]
|
||||
|
||||
def get_masthead_url(self):
|
||||
return 'http://www.lvz-online.de/resources/themes/standard/images/global/logo.gif'
|
||||
|
||||
@ -1,100 +1,100 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from datetime import datetime
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
from calibre.utils.magick import Image, PixelWand
|
||||
|
||||
class LifeHacker(BasicNewsRecipe):
|
||||
THUMBALIZR_API = '' # ---->Get your at http://www.thumbalizr.com/ and put here
|
||||
LANGUAGE = 'en'
|
||||
LANGHTM = 'en'
|
||||
language = 'en'
|
||||
ENCODING = 'utf'
|
||||
ENCHTM = 'utf-8'
|
||||
requires_version = (0,7,47)
|
||||
news = True
|
||||
|
||||
title = u'LifeHacker'
|
||||
__author__ = 'Euler Alves'
|
||||
description = u'Tips, tricks, and downloads for getting things done.'
|
||||
publisher = u'lifehacker.com'
|
||||
author = u'Adam Pash & Kevin Purdy & Adam Dachis & Whitson Gordon & Gina Trapani'
|
||||
category = 'news, rss'
|
||||
|
||||
oldest_article = 4
|
||||
max_articles_per_feed = 20
|
||||
summary_length = 1000
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = True
|
||||
remove_empty_feeds = True
|
||||
timefmt = ' [%d %b %Y (%a)]'
|
||||
|
||||
hoje = datetime.now()
|
||||
pubdate = hoje.strftime('%a, %d %b')
|
||||
cover_url = 'http://api.thumbalizr.com/?api_key='+THUMBALIZR_API+'&url=http://lifehacker.com&width=600&quality=90'
|
||||
cover_margins = (0,0,'white')
|
||||
masthead_url = 'http://cache.gawkerassets.com/assets/lifehacker.com/img/logo.png'
|
||||
|
||||
remove_tags = [
|
||||
{'class': 'feedflare'},
|
||||
dict(name='div',
|
||||
attrs={'class':[
|
||||
'ad_container'
|
||||
,'ad_300x250'
|
||||
,'ad_interstitial'
|
||||
,'share-wrap'
|
||||
,'ad_300x600'
|
||||
,'ad_perma-footer-adsense'
|
||||
,'ad_perma-panorama'
|
||||
,'ad panorama'
|
||||
,'ad_container'
|
||||
]})
|
||||
,dict(name='div',
|
||||
attrs={'id':[
|
||||
'agegate_container'
|
||||
,'agegate_container_rejected'
|
||||
,'sharemenu-wrap'
|
||||
]})
|
||||
]
|
||||
|
||||
feeds = [(u'Articles', u'http://feeds.gawker.com/lifehacker/vip?format=xml')]
|
||||
|
||||
conversion_options = {
|
||||
'title' : title
|
||||
,'comments' : description
|
||||
,'publisher' : publisher
|
||||
,'tags' : category
|
||||
,'language' : LANGUAGE
|
||||
,'linearize_tables': True
|
||||
}
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
if not soup.find(attrs={'http-equiv':'Content-Language'}):
|
||||
meta0 = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.LANGHTM)])
|
||||
soup.head.insert(0,meta0)
|
||||
if not soup.find(attrs={'http-equiv':'Content-Type'}):
|
||||
meta1 = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset="+self.ENCHTM)])
|
||||
soup.head.insert(0,meta1)
|
||||
return soup
|
||||
|
||||
def postprocess_html(self, soup, first):
|
||||
#process all the images. assumes that the new html has the correct path
|
||||
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
|
||||
iurl = tag['src']
|
||||
img = Image()
|
||||
img.open(iurl)
|
||||
width, height = img.size
|
||||
print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
|
||||
if img < 0:
|
||||
raise RuntimeError('Out of memory')
|
||||
pw = PixelWand()
|
||||
if( width > height and width > 590) :
|
||||
print 'Rotate image'
|
||||
img.rotate(pw, -90)
|
||||
img.save(iurl)
|
||||
return soup
|
||||
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from datetime import datetime
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
from calibre.utils.magick import Image, PixelWand
|
||||
|
||||
class LifeHacker(BasicNewsRecipe):
|
||||
THUMBALIZR_API = '' # ---->Get your at http://www.thumbalizr.com/ and put here
|
||||
LANGUAGE = 'en'
|
||||
LANGHTM = 'en'
|
||||
language = 'en'
|
||||
ENCODING = 'utf'
|
||||
ENCHTM = 'utf-8'
|
||||
requires_version = (0,7,47)
|
||||
news = True
|
||||
|
||||
title = u'LifeHacker'
|
||||
__author__ = 'Euler Alves'
|
||||
description = u'Tips, tricks, and downloads for getting things done.'
|
||||
publisher = u'lifehacker.com'
|
||||
author = u'Adam Pash & Kevin Purdy & Adam Dachis & Whitson Gordon & Gina Trapani'
|
||||
category = 'news, rss'
|
||||
|
||||
oldest_article = 4
|
||||
max_articles_per_feed = 20
|
||||
summary_length = 1000
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = True
|
||||
remove_empty_feeds = True
|
||||
timefmt = ' [%d %b %Y (%a)]'
|
||||
|
||||
hoje = datetime.now()
|
||||
pubdate = hoje.strftime('%a, %d %b')
|
||||
cover_url = 'http://api.thumbalizr.com/?api_key='+THUMBALIZR_API+'&url=http://lifehacker.com&width=600&quality=90'
|
||||
cover_margins = (0,0,'white')
|
||||
masthead_url = 'http://cache.gawkerassets.com/assets/lifehacker.com/img/logo.png'
|
||||
|
||||
remove_tags = [
|
||||
{'class': 'feedflare'},
|
||||
dict(name='div',
|
||||
attrs={'class':[
|
||||
'ad_container'
|
||||
,'ad_300x250'
|
||||
,'ad_interstitial'
|
||||
,'share-wrap'
|
||||
,'ad_300x600'
|
||||
,'ad_perma-footer-adsense'
|
||||
,'ad_perma-panorama'
|
||||
,'ad panorama'
|
||||
,'ad_container'
|
||||
]})
|
||||
,dict(name='div',
|
||||
attrs={'id':[
|
||||
'agegate_container'
|
||||
,'agegate_container_rejected'
|
||||
,'sharemenu-wrap'
|
||||
]})
|
||||
]
|
||||
|
||||
feeds = [(u'Articles', u'http://feeds.gawker.com/lifehacker/vip?format=xml')]
|
||||
|
||||
conversion_options = {
|
||||
'title' : title
|
||||
,'comments' : description
|
||||
,'publisher' : publisher
|
||||
,'tags' : category
|
||||
,'language' : LANGUAGE
|
||||
,'linearize_tables': True
|
||||
}
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
if not soup.find(attrs={'http-equiv':'Content-Language'}):
|
||||
meta0 = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.LANGHTM)])
|
||||
soup.head.insert(0,meta0)
|
||||
if not soup.find(attrs={'http-equiv':'Content-Type'}):
|
||||
meta1 = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset="+self.ENCHTM)])
|
||||
soup.head.insert(0,meta1)
|
||||
return soup
|
||||
|
||||
def postprocess_html(self, soup, first):
|
||||
#process all the images. assumes that the new html has the correct path
|
||||
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
|
||||
iurl = tag['src']
|
||||
img = Image()
|
||||
img.open(iurl)
|
||||
width, height = img.size
|
||||
print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
|
||||
if img < 0:
|
||||
raise RuntimeError('Out of memory')
|
||||
pw = PixelWand()
|
||||
if( width > height and width > 590) :
|
||||
print 'Rotate image'
|
||||
img.rotate(pw, -90)
|
||||
img.save(iurl)
|
||||
return soup
|
||||
|
||||
|
||||
|
||||
@ -1,85 +1,85 @@
|
||||
#!/usr/bin/env python
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009, Matthew Briggs'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
'''
|
||||
http://www.herald sun.com.au/
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class DailyTelegraph(BasicNewsRecipe):
|
||||
title = u'Melbourne Herald Sun'
|
||||
__author__ = u'Ray Hartley'
|
||||
description = (u'Victorian and National News'
|
||||
'. You will need to have a subscription to '
|
||||
'http://www.heraldsun.com.au to get full articles.')
|
||||
language = 'en_AU'
|
||||
|
||||
oldest_article = 2
|
||||
needs_subscription = 'optional'
|
||||
max_articles_per_feed = 30
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
encoding = 'utf8'
|
||||
use_embedded_content = False
|
||||
language = 'en_AU'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://resources2.news.com.au/cs/heraldsun/images/header-and-footer/logo.gif'
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif }
|
||||
img{margin-bottom: 0.4em; display:block}
|
||||
.caption{display: inline; font-size: x-small}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
keep_only_tags = [dict(attrs={'id':'story'})]
|
||||
remove_tags_before=dict(attrs={'class':'story-header'})
|
||||
remove_tags_after=dict(attrs={'class':'story-footer'})
|
||||
remove_tags = [
|
||||
dict(name=['meta','link','base','iframe','embed','object','media-metadata','media-reference','media-producer'])
|
||||
,dict(attrs={'class':['story-header-tools','story-sidebar','story-footer','story-summary-list']})
|
||||
]
|
||||
remove_attributes=['lang']
|
||||
|
||||
|
||||
feeds = [(u'Breaking News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_breakingnews_206.xml' )
|
||||
,(u'Business' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_business_207.xml' )
|
||||
,(u'Entertainment' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_entertainment_208.xml' )
|
||||
,(u'Health Science' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_health_212.xml' )
|
||||
,(u'Music' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_music_449.xml' )
|
||||
,(u'National News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_national_209.xml' )
|
||||
,(u'Sport News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_sport_213.xml' )
|
||||
,(u'AFL News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_afl_205.xml' )
|
||||
,(u'State News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_vic_214.xml' )
|
||||
,(u'Technology' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_tech_215.xml' )
|
||||
,(u'World News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_world_216.xml' )
|
||||
,(u'Opinion', u'http://feeds.news.com.au/public/rss/2.0/heraldsun_opinion_210.xml' )
|
||||
,(u'Andrew Bolt' , u'http://blogs.news.com.au/heraldsun/andrewbolt/index.php/xml/rss_2.0/heraldsun/hs_andrewbolt/')
|
||||
,(u'Afl - St Kilda' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_afl_stkilda_565.xml')
|
||||
,(u'Terry McCrann' ,u'http://feeds.news.com.au/public/rss/2.0/heraldsun_tmccrann_224.xml' )
|
||||
,(u'The Other side' ,u'http://feeds.news.com.au/public/rss/2.0/heraldsun_otherside_211.xml')]
|
||||
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
if self.username and self.password:
|
||||
br.open('http://www.heraldsun.com.au')
|
||||
br.select_form(nr=0)
|
||||
br['username'] = self.username
|
||||
br['password'] = self.password
|
||||
raw = br.submit().read()
|
||||
if '>log out' not in raw.lower():
|
||||
raise ValueError('Failed to log in to www.heralsun'
|
||||
' are your username and password correct?')
|
||||
return br
|
||||
|
||||
def get_article_url(self, article):
|
||||
return article.id
|
||||
|
||||
|
||||
#!/usr/bin/env python
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009, Matthew Briggs'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
'''
|
||||
http://www.herald sun.com.au/
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class DailyTelegraph(BasicNewsRecipe):
|
||||
title = u'Melbourne Herald Sun'
|
||||
__author__ = u'Ray Hartley'
|
||||
description = (u'Victorian and National News'
|
||||
'. You will need to have a subscription to '
|
||||
'http://www.heraldsun.com.au to get full articles.')
|
||||
language = 'en_AU'
|
||||
|
||||
oldest_article = 2
|
||||
needs_subscription = 'optional'
|
||||
max_articles_per_feed = 30
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
encoding = 'utf8'
|
||||
use_embedded_content = False
|
||||
language = 'en_AU'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://resources2.news.com.au/cs/heraldsun/images/header-and-footer/logo.gif'
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif }
|
||||
img{margin-bottom: 0.4em; display:block}
|
||||
.caption{display: inline; font-size: x-small}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
keep_only_tags = [dict(attrs={'id':'story'})]
|
||||
remove_tags_before=dict(attrs={'class':'story-header'})
|
||||
remove_tags_after=dict(attrs={'class':'story-footer'})
|
||||
remove_tags = [
|
||||
dict(name=['meta','link','base','iframe','embed','object','media-metadata','media-reference','media-producer'])
|
||||
,dict(attrs={'class':['story-header-tools','story-sidebar','story-footer','story-summary-list']})
|
||||
]
|
||||
remove_attributes=['lang']
|
||||
|
||||
|
||||
feeds = [(u'Breaking News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_breakingnews_206.xml' )
|
||||
,(u'Business' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_business_207.xml' )
|
||||
,(u'Entertainment' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_entertainment_208.xml' )
|
||||
,(u'Health Science' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_health_212.xml' )
|
||||
,(u'Music' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_music_449.xml' )
|
||||
,(u'National News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_national_209.xml' )
|
||||
,(u'Sport News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_sport_213.xml' )
|
||||
,(u'AFL News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_afl_205.xml' )
|
||||
,(u'State News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_vic_214.xml' )
|
||||
,(u'Technology' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_tech_215.xml' )
|
||||
,(u'World News' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_world_216.xml' )
|
||||
,(u'Opinion', u'http://feeds.news.com.au/public/rss/2.0/heraldsun_opinion_210.xml' )
|
||||
,(u'Andrew Bolt' , u'http://blogs.news.com.au/heraldsun/andrewbolt/index.php/xml/rss_2.0/heraldsun/hs_andrewbolt/')
|
||||
,(u'Afl - St Kilda' , u'http://feeds.news.com.au/public/rss/2.0/heraldsun_afl_stkilda_565.xml')
|
||||
,(u'Terry McCrann' ,u'http://feeds.news.com.au/public/rss/2.0/heraldsun_tmccrann_224.xml' )
|
||||
,(u'The Other side' ,u'http://feeds.news.com.au/public/rss/2.0/heraldsun_otherside_211.xml')]
|
||||
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
if self.username and self.password:
|
||||
br.open('http://www.heraldsun.com.au')
|
||||
br.select_form(nr=0)
|
||||
br['username'] = self.username
|
||||
br['password'] = self.password
|
||||
raw = br.submit().read()
|
||||
if '>log out' not in raw.lower():
|
||||
raise ValueError('Failed to log in to www.heralsun'
|
||||
' are your username and password correct?')
|
||||
return br
|
||||
|
||||
def get_article_url(self, article):
|
||||
return article.id
|
||||
|
||||
|
||||
|
||||
@ -1,138 +1,138 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
from calibre.web.feeds import Feed
|
||||
|
||||
class Menorca(BasicNewsRecipe):
|
||||
|
||||
title = 'Menorca'
|
||||
publisher = 'Editorial Menorca S.A. '
|
||||
__author__ = 'M. Sintes'
|
||||
description = u'Peri\xf3dico con informaci\xf3n de Menorca, Espa\xf1a'
|
||||
category = 'news, politics, economy, culture, Menorca, Spain '
|
||||
language = 'es'
|
||||
enconding = 'cp1252'
|
||||
|
||||
no_stylesheets = True
|
||||
oldest_article = 5
|
||||
max_articles_per_feed = 25
|
||||
|
||||
|
||||
feeds = [ (u'Principal',u'http://www.menorca.info/rss'),
|
||||
(u'Opini\xf3n',u'http://www.menorca.info/rss?seccion=opinion'),
|
||||
(u'Menorca',u'http://www.menorca.info/rss?seccion=menorca'),
|
||||
(u'Alaior',u'http://www.menorca.info/rss?seccion=pueblos/alaior'),
|
||||
(u'Ciutadella', u'http://www.menorca.info/rss?seccion=pueblos/ciutadella'),
|
||||
(u'Es Castell', u'http://www.menorca.info/rss?seccion=pueblos/escastell'),
|
||||
(u'Es Mercadal', u'http://www.menorca.info/rss?seccion=pueblos/esmercadal'),
|
||||
(u'Es Migjorn', u'http://www.menorca.info/rss?seccion=pueblos/esmigjorn'),
|
||||
(u'Ferreries', u'http://www.menorca.info/rss?seccion=pueblos/ferreries'),
|
||||
(u'Fornells', u'http://www.menorca.info/rss?seccion=pueblos/fornells'),
|
||||
(u'Llucma\xe7anes', u'http://www.menorca.info/rss?seccion=pueblos/llucmaanes'),
|
||||
(u'Ma\xf3', u'http://www.menorca.info/rss?seccion=pueblos/mao'),
|
||||
(u'Sant Climent', u'http://www.menorca.info/rss?seccion=pueblos/santcliment'),
|
||||
(u'Sant Llu\xeds', u'http://www.menorca.info/rss?seccion=pueblos/santlluis'),
|
||||
(u'Deportes',u'http://www.menorca.info/rss?seccion=deportes'),
|
||||
(u'Balears', u'http://www.menorca.info/rss?seccion=balears')]
|
||||
|
||||
#Seccions amb link rss erroni. Es recupera directament de la pagina web
|
||||
seccions_web = [(u'Mundo',u'http://www.menorca.info/actualidad/mundo'),
|
||||
(u'Econom\xeda',u'http://www.menorca.info/actualidad/economia'),
|
||||
(u'Espa\xf1a',u'http://www.menorca.info/actualidad/espana')]
|
||||
|
||||
remove_tags_before = dict(name='div', attrs={'class':'bloqueTitulosNoticia'})
|
||||
remove_tags_after = dict(name='div', attrs={'class':'compartir'})
|
||||
remove_tags = [dict(id = 'utilidades'),
|
||||
dict(name='div', attrs={'class': 'totalComentarios'}),
|
||||
dict(name='div', attrs={'class': 'compartir'}),
|
||||
dict(name='div', attrs={'class': re.compile("img_noticia*")})
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
url_imprimir = url + '?d=print'
|
||||
return url.replace(url, url_imprimir)
|
||||
|
||||
def feed_to_index_append(self, feedObject, masterFeed):
|
||||
|
||||
# Loop thru the feed object and build the correct type of article list
|
||||
for feed in feedObject:
|
||||
newArticles = []
|
||||
for article in feed.articles:
|
||||
newArt = {
|
||||
'title' : article.title,
|
||||
'url' : article.url,
|
||||
'date' : article.date,
|
||||
'description' : article.text_summary
|
||||
}
|
||||
|
||||
newArticles.append(newArt)
|
||||
|
||||
# append the newly-built list object to the index object # passed in as masterFeed.
|
||||
masterFeed.append((feed.title,newArticles))
|
||||
|
||||
|
||||
def parse_index(self):
|
||||
|
||||
rssFeeds = Feed()
|
||||
rssFeeds = BasicNewsRecipe.parse_feeds(self)
|
||||
|
||||
articles = []
|
||||
feeds = []
|
||||
|
||||
self.feed_to_index_append(rssFeeds,feeds)
|
||||
|
||||
|
||||
|
||||
for (nom_seccio, url_seccio) in self.seccions_web:
|
||||
|
||||
|
||||
articles = []
|
||||
|
||||
soup = self.index_to_soup(url_seccio)
|
||||
for article in soup.findAll('div', attrs={'class':re.compile("articulo noticia|cajaNoticiaPortada")}):
|
||||
h = article.find(['h2','h3'])
|
||||
titol = self.tag_to_string(h)
|
||||
a = article.find('a', href=True)
|
||||
url = 'http://www.menorca.info' + a['href']
|
||||
|
||||
desc = None
|
||||
autor = ''
|
||||
dt = ''
|
||||
|
||||
soup_art = self.index_to_soup(url)
|
||||
aut = soup_art.find('div', attrs={'class':'autor'})
|
||||
tx = self.tag_to_string(aut)
|
||||
ls = re.split('[,;]',tx)
|
||||
|
||||
t = len(ls)
|
||||
if t >= 1:
|
||||
autor = ls[0]
|
||||
|
||||
if t > 1:
|
||||
d = ls[t-1]
|
||||
|
||||
if len(d) >= 10:
|
||||
lt = len(d) - 10
|
||||
dt = d[lt:]
|
||||
|
||||
|
||||
|
||||
self.log('\tTrobat article: ', titol, 'a', url, 'Seccio: ', nom_seccio, 'Autor: ', autor, 'Data: ', dt)
|
||||
|
||||
articles.append({'title': titol, 'url': url, 'description': desc, 'date':dt, 'author': autor})
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
if articles:
|
||||
feeds.append((nom_seccio, articles))
|
||||
|
||||
|
||||
|
||||
|
||||
return feeds
|
||||
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
from calibre.web.feeds import Feed
|
||||
|
||||
class Menorca(BasicNewsRecipe):
|
||||
|
||||
title = 'Menorca'
|
||||
publisher = 'Editorial Menorca S.A. '
|
||||
__author__ = 'M. Sintes'
|
||||
description = u'Peri\xf3dico con informaci\xf3n de Menorca, Espa\xf1a'
|
||||
category = 'news, politics, economy, culture, Menorca, Spain '
|
||||
language = 'es'
|
||||
enconding = 'cp1252'
|
||||
|
||||
no_stylesheets = True
|
||||
oldest_article = 5
|
||||
max_articles_per_feed = 25
|
||||
|
||||
|
||||
feeds = [ (u'Principal',u'http://www.menorca.info/rss'),
|
||||
(u'Opini\xf3n',u'http://www.menorca.info/rss?seccion=opinion'),
|
||||
(u'Menorca',u'http://www.menorca.info/rss?seccion=menorca'),
|
||||
(u'Alaior',u'http://www.menorca.info/rss?seccion=pueblos/alaior'),
|
||||
(u'Ciutadella', u'http://www.menorca.info/rss?seccion=pueblos/ciutadella'),
|
||||
(u'Es Castell', u'http://www.menorca.info/rss?seccion=pueblos/escastell'),
|
||||
(u'Es Mercadal', u'http://www.menorca.info/rss?seccion=pueblos/esmercadal'),
|
||||
(u'Es Migjorn', u'http://www.menorca.info/rss?seccion=pueblos/esmigjorn'),
|
||||
(u'Ferreries', u'http://www.menorca.info/rss?seccion=pueblos/ferreries'),
|
||||
(u'Fornells', u'http://www.menorca.info/rss?seccion=pueblos/fornells'),
|
||||
(u'Llucma\xe7anes', u'http://www.menorca.info/rss?seccion=pueblos/llucmaanes'),
|
||||
(u'Ma\xf3', u'http://www.menorca.info/rss?seccion=pueblos/mao'),
|
||||
(u'Sant Climent', u'http://www.menorca.info/rss?seccion=pueblos/santcliment'),
|
||||
(u'Sant Llu\xeds', u'http://www.menorca.info/rss?seccion=pueblos/santlluis'),
|
||||
(u'Deportes',u'http://www.menorca.info/rss?seccion=deportes'),
|
||||
(u'Balears', u'http://www.menorca.info/rss?seccion=balears')]
|
||||
|
||||
#Seccions amb link rss erroni. Es recupera directament de la pagina web
|
||||
seccions_web = [(u'Mundo',u'http://www.menorca.info/actualidad/mundo'),
|
||||
(u'Econom\xeda',u'http://www.menorca.info/actualidad/economia'),
|
||||
(u'Espa\xf1a',u'http://www.menorca.info/actualidad/espana')]
|
||||
|
||||
remove_tags_before = dict(name='div', attrs={'class':'bloqueTitulosNoticia'})
|
||||
remove_tags_after = dict(name='div', attrs={'class':'compartir'})
|
||||
remove_tags = [dict(id = 'utilidades'),
|
||||
dict(name='div', attrs={'class': 'totalComentarios'}),
|
||||
dict(name='div', attrs={'class': 'compartir'}),
|
||||
dict(name='div', attrs={'class': re.compile("img_noticia*")})
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
url_imprimir = url + '?d=print'
|
||||
return url.replace(url, url_imprimir)
|
||||
|
||||
def feed_to_index_append(self, feedObject, masterFeed):
|
||||
|
||||
# Loop thru the feed object and build the correct type of article list
|
||||
for feed in feedObject:
|
||||
newArticles = []
|
||||
for article in feed.articles:
|
||||
newArt = {
|
||||
'title' : article.title,
|
||||
'url' : article.url,
|
||||
'date' : article.date,
|
||||
'description' : article.text_summary
|
||||
}
|
||||
|
||||
newArticles.append(newArt)
|
||||
|
||||
# append the newly-built list object to the index object # passed in as masterFeed.
|
||||
masterFeed.append((feed.title,newArticles))
|
||||
|
||||
|
||||
def parse_index(self):
|
||||
|
||||
rssFeeds = Feed()
|
||||
rssFeeds = BasicNewsRecipe.parse_feeds(self)
|
||||
|
||||
articles = []
|
||||
feeds = []
|
||||
|
||||
self.feed_to_index_append(rssFeeds,feeds)
|
||||
|
||||
|
||||
|
||||
for (nom_seccio, url_seccio) in self.seccions_web:
|
||||
|
||||
|
||||
articles = []
|
||||
|
||||
soup = self.index_to_soup(url_seccio)
|
||||
for article in soup.findAll('div', attrs={'class':re.compile("articulo noticia|cajaNoticiaPortada")}):
|
||||
h = article.find(['h2','h3'])
|
||||
titol = self.tag_to_string(h)
|
||||
a = article.find('a', href=True)
|
||||
url = 'http://www.menorca.info' + a['href']
|
||||
|
||||
desc = None
|
||||
autor = ''
|
||||
dt = ''
|
||||
|
||||
soup_art = self.index_to_soup(url)
|
||||
aut = soup_art.find('div', attrs={'class':'autor'})
|
||||
tx = self.tag_to_string(aut)
|
||||
ls = re.split('[,;]',tx)
|
||||
|
||||
t = len(ls)
|
||||
if t >= 1:
|
||||
autor = ls[0]
|
||||
|
||||
if t > 1:
|
||||
d = ls[t-1]
|
||||
|
||||
if len(d) >= 10:
|
||||
lt = len(d) - 10
|
||||
dt = d[lt:]
|
||||
|
||||
|
||||
|
||||
self.log('\tTrobat article: ', titol, 'a', url, 'Seccio: ', nom_seccio, 'Autor: ', autor, 'Data: ', dt)
|
||||
|
||||
articles.append({'title': titol, 'url': url, 'description': desc, 'date':dt, 'author': autor})
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
if articles:
|
||||
feeds.append((nom_seccio, articles))
|
||||
|
||||
|
||||
|
||||
|
||||
return feeds
|
||||
|
||||
|
||||
|
||||
|
||||
@ -1,27 +1,27 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1329123365(BasicNewsRecipe):
|
||||
title = u'Mobilebulgaria.com'
|
||||
__author__ = 'M3 Web'
|
||||
description = 'The biggest Bulgarian site covering mobile consumer electronics. Offers detailed reviews, popular discussion forum, shop and platform for selling new and second hand phones and gadgets.'
|
||||
category = 'News, Reviews, Offers, Forum'
|
||||
oldest_article = 45
|
||||
max_articles_per_feed = 10
|
||||
language = 'bg'
|
||||
encoding = 'windows-1251'
|
||||
no_stylesheets = False
|
||||
remove_javascript = True
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'bigblock'}),
|
||||
dict(name='div', attrs={'class':'verybigblock'}),
|
||||
dict(name='table', attrs={'class':'obiaviresults'}),
|
||||
dict(name='div', attrs={'class':'forumblock'}),
|
||||
dict(name='div', attrs={'class':'forumblock_b1'}),
|
||||
dict(name='div', attrs={'class':'block2_2colswrap'})]
|
||||
|
||||
feeds = [(u'News', u'http://www.mobilebulgaria.com/rss_full.php'),
|
||||
(u'Reviews', u'http://www.mobilebulgaria.com/rss_reviews.php'),
|
||||
(u'Offers', u'http://www.mobilebulgaria.com/obiavi/rss.php'),
|
||||
(u'Forum', u'http://www.mobilebulgaria.com/rss_forum_last10.php')]
|
||||
|
||||
extra_css = '''
|
||||
#gallery1 div{display: block; float: left; margin: 0 10px 10px 0;} '''
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1329123365(BasicNewsRecipe):
|
||||
title = u'Mobilebulgaria.com'
|
||||
__author__ = 'M3 Web'
|
||||
description = 'The biggest Bulgarian site covering mobile consumer electronics. Offers detailed reviews, popular discussion forum, shop and platform for selling new and second hand phones and gadgets.'
|
||||
category = 'News, Reviews, Offers, Forum'
|
||||
oldest_article = 45
|
||||
max_articles_per_feed = 10
|
||||
language = 'bg'
|
||||
encoding = 'windows-1251'
|
||||
no_stylesheets = False
|
||||
remove_javascript = True
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'bigblock'}),
|
||||
dict(name='div', attrs={'class':'verybigblock'}),
|
||||
dict(name='table', attrs={'class':'obiaviresults'}),
|
||||
dict(name='div', attrs={'class':'forumblock'}),
|
||||
dict(name='div', attrs={'class':'forumblock_b1'}),
|
||||
dict(name='div', attrs={'class':'block2_2colswrap'})]
|
||||
|
||||
feeds = [(u'News', u'http://www.mobilebulgaria.com/rss_full.php'),
|
||||
(u'Reviews', u'http://www.mobilebulgaria.com/rss_reviews.php'),
|
||||
(u'Offers', u'http://www.mobilebulgaria.com/obiavi/rss.php'),
|
||||
(u'Forum', u'http://www.mobilebulgaria.com/rss_forum_last10.php')]
|
||||
|
||||
extra_css = '''
|
||||
#gallery1 div{display: block; float: left; margin: 0 10px 10px 0;} '''
|
||||
|
||||
@ -15,7 +15,7 @@ class mojegotowanie(BasicNewsRecipe):
|
||||
language = 'pl'
|
||||
description =u'Gotowanie to Twoja pasja? Uwielbiasz sałatki? Lubisz grillować? Przepisy kulinarne doskonałe na wszystkie okazje znajdziesz na www.mojegotowanie.pl.'
|
||||
masthead_url='http://www.mojegotowanie.pl/extension/selfstart/design/self/images/top_c2.gif'
|
||||
cover_url = 'http://www.mojegotowanie.pl/extension/selfstart/design/self/images/mgpl/mojegotowanie.gif'
|
||||
cover_url = 'http://www.mojegotowanie.pl/extension/selfstart/design/self/images/mgpl/mojegotowanie.gif'
|
||||
remove_empty_feeds= True
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
|
||||
@ -1,35 +1,35 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1308572538(BasicNewsRecipe):
|
||||
title = u'Novinite.com'
|
||||
__author__ = 'Martin Tsanchev'
|
||||
description = 'Real time provider of the latest Bulgarian news in English'
|
||||
category = 'Business, Politics, Society, Sports, Crime, Lifestyle, World, People'
|
||||
language = 'en_BG'
|
||||
encoding = 'utf-8'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 10
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'content'})]
|
||||
remove_tags = [dict(name='a', attrs={'class':'twitter-share-button'})]
|
||||
remove_tags_after = dict(id='textsize')
|
||||
no_stylesheets = True
|
||||
feeds = [(u'Business', u'http://www.novinite.com/services/news_rdf.php?category_id=1'),
|
||||
(u'Finance', u'http://www.novinite.com/services/news_rdf.php?category_id=15'),
|
||||
(u'Energy', u'http://www.novinite.com/services/news_rdf.php?category_id=16'),
|
||||
(u'Industry', u'http://www.novinite.com/services/news_rdf.php?category_id=17'),
|
||||
(u'Properties', u'http://www.novinite.com/services/news_rdf.php?category_id=18'),
|
||||
(u'Politics', u'http://www.novinite.com/services/news_rdf.php?category_id=2'),
|
||||
(u'Diplomacy', u'http://www.novinite.com/services/news_rdf.php?category_id=20'),
|
||||
(u'Defense', u'http://www.novinite.com/services/news_rdf.php?category_id=21'),
|
||||
(u'Bulgaria in EU', u'http://www.novinite.com/services/news_rdf.php?category_id=22'),
|
||||
(u'Domestic', u'http://www.novinite.com/services/news_rdf.php?category_id=23'),
|
||||
(u'Society', u'http://www.novinite.com/services/news_rdf.php?category_id=3'),
|
||||
(u'Environment', u'http://www.novinite.com/services/news_rdf.php?category_id=24'),
|
||||
(u'Education', u'http://www.novinite.com/services/news_rdf.php?category_id=25'),
|
||||
(u'Culture', u'http://www.novinite.com/services/news_rdf.php?category_id=26'),
|
||||
(u'Archaeology', u'http://www.novinite.com/services/news_rdf.php?category_id=34'),
|
||||
(u'Health', u'http://www.novinite.com/services/news_rdf.php?category_id=62'),
|
||||
(u'Sports', u'http://www.novinite.com/services/news_rdf.php?category_id=4'),
|
||||
(u'Crime', u'http://www.novinite.com/services/news_rdf.php?category_id=5'),
|
||||
(u'Lifestyle', u'http://www.novinite.com/services/news_rdf.php?category_id=6'),
|
||||
(u'World', u'http://www.novinite.com/services/news_rdf.php?category_id=30')]
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1308572538(BasicNewsRecipe):
|
||||
title = u'Novinite.com'
|
||||
__author__ = 'Martin Tsanchev'
|
||||
description = 'Real time provider of the latest Bulgarian news in English'
|
||||
category = 'Business, Politics, Society, Sports, Crime, Lifestyle, World, People'
|
||||
language = 'en_BG'
|
||||
encoding = 'utf-8'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 10
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'content'})]
|
||||
remove_tags = [dict(name='a', attrs={'class':'twitter-share-button'})]
|
||||
remove_tags_after = dict(id='textsize')
|
||||
no_stylesheets = True
|
||||
feeds = [(u'Business', u'http://www.novinite.com/services/news_rdf.php?category_id=1'),
|
||||
(u'Finance', u'http://www.novinite.com/services/news_rdf.php?category_id=15'),
|
||||
(u'Energy', u'http://www.novinite.com/services/news_rdf.php?category_id=16'),
|
||||
(u'Industry', u'http://www.novinite.com/services/news_rdf.php?category_id=17'),
|
||||
(u'Properties', u'http://www.novinite.com/services/news_rdf.php?category_id=18'),
|
||||
(u'Politics', u'http://www.novinite.com/services/news_rdf.php?category_id=2'),
|
||||
(u'Diplomacy', u'http://www.novinite.com/services/news_rdf.php?category_id=20'),
|
||||
(u'Defense', u'http://www.novinite.com/services/news_rdf.php?category_id=21'),
|
||||
(u'Bulgaria in EU', u'http://www.novinite.com/services/news_rdf.php?category_id=22'),
|
||||
(u'Domestic', u'http://www.novinite.com/services/news_rdf.php?category_id=23'),
|
||||
(u'Society', u'http://www.novinite.com/services/news_rdf.php?category_id=3'),
|
||||
(u'Environment', u'http://www.novinite.com/services/news_rdf.php?category_id=24'),
|
||||
(u'Education', u'http://www.novinite.com/services/news_rdf.php?category_id=25'),
|
||||
(u'Culture', u'http://www.novinite.com/services/news_rdf.php?category_id=26'),
|
||||
(u'Archaeology', u'http://www.novinite.com/services/news_rdf.php?category_id=34'),
|
||||
(u'Health', u'http://www.novinite.com/services/news_rdf.php?category_id=62'),
|
||||
(u'Sports', u'http://www.novinite.com/services/news_rdf.php?category_id=4'),
|
||||
(u'Crime', u'http://www.novinite.com/services/news_rdf.php?category_id=5'),
|
||||
(u'Lifestyle', u'http://www.novinite.com/services/news_rdf.php?category_id=6'),
|
||||
(u'World', u'http://www.novinite.com/services/news_rdf.php?category_id=30')]
|
||||
|
||||
@ -1,36 +1,36 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1311799898(BasicNewsRecipe):
|
||||
title = u'Periódico Portafolio Colombia'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
language = 'es_CO'
|
||||
cover_url = 'http://www.portafolio.co/sites/portafolio.co/themes/portafolio_2011/logo.png'
|
||||
remove_tags_before = dict(id='contenidoArt')
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'articulo-mas'})]
|
||||
keep_only_tags = [dict(name='div', id='contenidoArt')]
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.portafolio.co/sites/portafolio.co/themes/portafolio_2011/logo.png'
|
||||
publication_type = 'newspaper'
|
||||
|
||||
extra_css = """
|
||||
p{text-align: justify; font-size: 100%}
|
||||
body{ text-align: left; font-size:100% }
|
||||
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
|
||||
h3{font-family: sans-serif; font-size:100%; font-style: italic; text-align: justify; }
|
||||
"""
|
||||
|
||||
|
||||
feeds = [(u'Negocios', u'http://www.portafolio.co/negocios/feed'),
|
||||
(u'Economia', u'http://www.portafolio.co/economia/feed'),
|
||||
(u'Internacional', u'http://www.portafolio.co/internacional/feed'),
|
||||
(u'Indicadores', u'http://www.portafolio.co/indicadores/feed'),
|
||||
(u'Opinion', u'http://www.portafolio.co/opinion/feed'),
|
||||
(u'Finanzas Personales', u'http://www.portafolio.co/finanzas-personales/feed'),
|
||||
(u'Herramientas', u'http://www.portafolio.co/herramientas/feed')]
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1311799898(BasicNewsRecipe):
|
||||
title = u'Periódico Portafolio Colombia'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
language = 'es_CO'
|
||||
cover_url = 'http://www.portafolio.co/sites/portafolio.co/themes/portafolio_2011/logo.png'
|
||||
remove_tags_before = dict(id='contenidoArt')
|
||||
remove_tags_after = [dict(name='div', attrs={'class':'articulo-mas'})]
|
||||
keep_only_tags = [dict(name='div', id='contenidoArt')]
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.portafolio.co/sites/portafolio.co/themes/portafolio_2011/logo.png'
|
||||
publication_type = 'newspaper'
|
||||
|
||||
extra_css = """
|
||||
p{text-align: justify; font-size: 100%}
|
||||
body{ text-align: left; font-size:100% }
|
||||
h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
|
||||
h3{font-family: sans-serif; font-size:100%; font-style: italic; text-align: justify; }
|
||||
"""
|
||||
|
||||
|
||||
feeds = [(u'Negocios', u'http://www.portafolio.co/negocios/feed'),
|
||||
(u'Economia', u'http://www.portafolio.co/economia/feed'),
|
||||
(u'Internacional', u'http://www.portafolio.co/internacional/feed'),
|
||||
(u'Indicadores', u'http://www.portafolio.co/indicadores/feed'),
|
||||
(u'Opinion', u'http://www.portafolio.co/opinion/feed'),
|
||||
(u'Finanzas Personales', u'http://www.portafolio.co/finanzas-personales/feed'),
|
||||
(u'Herramientas', u'http://www.portafolio.co/herramientas/feed')]
|
||||
|
||||
@ -1,11 +1,11 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class AdvancedUserRecipe1317341570(BasicNewsRecipe):
|
||||
title = u'Revista Semana'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
language = 'es_CO'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
|
||||
feeds = [(u'Revista Semana', u'http://www.semana.com/rss/Semana_OnLine.xml')]
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class AdvancedUserRecipe1317341570(BasicNewsRecipe):
|
||||
title = u'Revista Semana'
|
||||
__author__ = 'BIGO-CAVA'
|
||||
language = 'es_CO'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
|
||||
feeds = [(u'Revista Semana', u'http://www.semana.com/rss/Semana_OnLine.xml')]
|
||||
|
||||
@ -1,28 +1,28 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'MrStefan <mrstefaan@gmail.com>'
|
||||
|
||||
'''
|
||||
www.rushisaband.com
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class rushisaband(BasicNewsRecipe):
|
||||
title = u'Rushisaband'
|
||||
__author__ = 'MrStefan <mrstefaan@gmail.com>'
|
||||
language = 'en_GB'
|
||||
description =u'A blog devoted to the band RUSH and its members, Neil Peart, Geddy Lee and Alex Lifeson'
|
||||
remove_empty_feeds= True
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript=True
|
||||
no_stylesheets=True
|
||||
|
||||
keep_only_tags =[]
|
||||
keep_only_tags.append(dict(name = 'h4'))
|
||||
keep_only_tags.append(dict(name = 'h5'))
|
||||
keep_only_tags.append(dict(name = 'p'))
|
||||
|
||||
feeds = [(u'Rush is a Band', u'http://feeds2.feedburner.com/rushisaband/blog')]
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'MrStefan <mrstefaan@gmail.com>'
|
||||
|
||||
'''
|
||||
www.rushisaband.com
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class rushisaband(BasicNewsRecipe):
|
||||
title = u'Rushisaband'
|
||||
__author__ = 'MrStefan <mrstefaan@gmail.com>'
|
||||
language = 'en_GB'
|
||||
description =u'A blog devoted to the band RUSH and its members, Neil Peart, Geddy Lee and Alex Lifeson'
|
||||
remove_empty_feeds= True
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript=True
|
||||
no_stylesheets=True
|
||||
|
||||
keep_only_tags =[]
|
||||
keep_only_tags.append(dict(name = 'h4'))
|
||||
keep_only_tags.append(dict(name = 'h5'))
|
||||
keep_only_tags.append(dict(name = 'p'))
|
||||
|
||||
feeds = [(u'Rush is a Band', u'http://feeds2.feedburner.com/rushisaband/blog')]
|
||||
|
||||
@ -1,29 +1,29 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2012, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
'''
|
||||
rybinski.eu
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Rybinski(BasicNewsRecipe):
|
||||
title = u'Rybinski.eu - economy of the XXI century'
|
||||
description = u'Blog ekonomiczny dra hab. Krzysztofa Rybi\u0144skiego'
|
||||
language = 'pl'
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
|
||||
feeds = [(u'wpisy', u'http://www.rybinski.eu/?feed=rss2&lang=pl')]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'post'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name = 'div', attrs = {'class' : 'post-meta-1'}),
|
||||
dict(name = 'div', attrs = {'class' : 'post-meta-2'}),
|
||||
dict(name = 'div', attrs = {'class' : 'post-comments'})
|
||||
]
|
||||
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2012, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
'''
|
||||
rybinski.eu
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Rybinski(BasicNewsRecipe):
|
||||
title = u'Rybinski.eu - economy of the XXI century'
|
||||
description = u'Blog ekonomiczny dra hab. Krzysztofa Rybi\u0144skiego'
|
||||
language = 'pl'
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
|
||||
feeds = [(u'wpisy', u'http://www.rybinski.eu/?feed=rss2&lang=pl')]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'post'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name = 'div', attrs = {'class' : 'post-meta-1'}),
|
||||
dict(name = 'div', attrs = {'class' : 'post-meta-2'}),
|
||||
dict(name = 'div', attrs = {'class' : 'post-comments'})
|
||||
]
|
||||
|
||||
|
||||
@ -1,22 +1,22 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011 Neil Grogan'
|
||||
#
|
||||
# Silicon Republic Recipe
|
||||
#
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class SiliconRepublic(BasicNewsRecipe):
|
||||
title = u'Silicon Republic'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
__author__ = u'Neil Grogan'
|
||||
language = 'en_IE'
|
||||
|
||||
remove_tags = [dict(attrs={'class':['thumb','txt','compactbox','icons','catlist','catlistinner','taglist','taglistinner','social','also-in','also-in-inner','also-in-footer','zonek-dfp','paneladvert','rcadvert','panel','h2b']}),
|
||||
dict(id=['header','logo','header-right','sitesearch','rsslinks','topnav','topvideos','topvideos-list','topnews','topnews-list','slideshow','slides','compactheader','compactnews','compactfeatures','article-type','contactlinks-header','banner-zone-k-dfp','footer-related','directory-services','also-in-section','featuredrelated1','featuredrelated2','featuredrelated3','featuredrelated4','advert2-dfp']),
|
||||
dict(name=['script', 'style'])]
|
||||
|
||||
|
||||
feeds = [(u'News', u'http://www.siliconrepublic.com/feeds/')]
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011 Neil Grogan'
|
||||
#
|
||||
# Silicon Republic Recipe
|
||||
#
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class SiliconRepublic(BasicNewsRecipe):
|
||||
title = u'Silicon Republic'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
__author__ = u'Neil Grogan'
|
||||
language = 'en_IE'
|
||||
|
||||
remove_tags = [dict(attrs={'class':['thumb','txt','compactbox','icons','catlist','catlistinner','taglist','taglistinner','social','also-in','also-in-inner','also-in-footer','zonek-dfp','paneladvert','rcadvert','panel','h2b']}),
|
||||
dict(id=['header','logo','header-right','sitesearch','rsslinks','topnav','topvideos','topvideos-list','topnews','topnews-list','slideshow','slides','compactheader','compactnews','compactfeatures','article-type','contactlinks-header','banner-zone-k-dfp','footer-related','directory-services','also-in-section','featuredrelated1','featuredrelated2','featuredrelated3','featuredrelated4','advert2-dfp']),
|
||||
dict(name=['script', 'style'])]
|
||||
|
||||
|
||||
feeds = [(u'News', u'http://www.siliconrepublic.com/feeds/')]
|
||||
|
||||
|
||||
@ -1,15 +1,15 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1296179411(BasicNewsRecipe):
|
||||
title = u'SPIN Magzine'
|
||||
__author__ = 'Quistopher'
|
||||
language = 'en'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
|
||||
feeds = [
|
||||
(u'Daily Noise Blog | SPIN.com', u'http://www.spin.com/blog/feed'),
|
||||
(u'It Happened Last Night | SPIN.com', u'http://www.spin.com/it-happened-last-night/feed'),
|
||||
(u'Album Reviews | SPIN.com', u'http://www.spin.com/album-reviews/feed')
|
||||
|
||||
]
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1296179411(BasicNewsRecipe):
|
||||
title = u'SPIN Magzine'
|
||||
__author__ = 'Quistopher'
|
||||
language = 'en'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
|
||||
feeds = [
|
||||
(u'Daily Noise Blog | SPIN.com', u'http://www.spin.com/blog/feed'),
|
||||
(u'It Happened Last Night | SPIN.com', u'http://www.spin.com/it-happened-last-night/feed'),
|
||||
(u'Album Reviews | SPIN.com', u'http://www.spin.com/album-reviews/feed')
|
||||
|
||||
]
|
||||
|
||||
@ -1,18 +1,18 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1299054026(BasicNewsRecipe):
|
||||
title = u'Thai Post Daily'
|
||||
__author__ = 'Chotechai P.'
|
||||
language = 'th'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
cover_url = 'http://upload.wikimedia.org/wikipedia/th/1/10/ThaiPost_Logo.png'
|
||||
feeds = [(u'\u0e02\u0e48\u0e32\u0e27\u0e2b\u0e19\u0e49\u0e32\u0e2b\u0e19\u0e36\u0e48\u0e07', u'http://thaipost.net/taxonomy/term/1/all/feed'), (u'\u0e1a\u0e17\u0e1a\u0e23\u0e23\u0e13\u0e32\u0e18\u0e34\u0e01\u0e32\u0e23', u'http://thaipost.net/taxonomy/term/11/all/feed'), (u'\u0e40\u0e1b\u0e25\u0e27 \u0e2a\u0e35\u0e40\u0e07\u0e34\u0e19', u'http://thaipost.net/taxonomy/term/2/all/feed'), (u'\u0e2a\u0e20\u0e32\u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e0a\u0e19', u'http://thaipost.net/taxonomy/term/3/all/feed'), (u'\u0e16\u0e39\u0e01\u0e17\u0e38\u0e01\u0e02\u0e49\u0e2d', u'http://thaipost.net/taxonomy/term/4/all/feed'), (u'\u0e01\u0e32\u0e23\u0e40\u0e21\u0e37\u0e2d\u0e07', u'http://thaipost.net/taxonomy/term/5/all/feed'), (u'\u0e17\u0e48\u0e32\u0e19\u0e02\u0e38\u0e19\u0e19\u0e49\u0e2d\u0e22', u'http://thaipost.net/taxonomy/term/12/all/feed'), (u'\u0e1a\u0e17\u0e04\u0e27\u0e32\u0e21\u0e1e\u0e34\u0e40\u0e28\u0e29', u'http://thaipost.net/taxonomy/term/66/all/feed'), (u'\u0e23\u0e32\u0e22\u0e07\u0e32\u0e19\u0e1e\u0e34\u0e40\u0e28\u0e29', u'http://thaipost.net/taxonomy/term/67/all/feed'), (u'\u0e1a\u0e31\u0e19\u0e17\u0e36\u0e01\u0e2b\u0e19\u0e49\u0e32 4', u'http://thaipost.net/taxonomy/term/13/all/feed'), (u'\u0e40\u0e2a\u0e35\u0e22\u0e1a\u0e0b\u0e36\u0e48\u0e07\u0e2b\u0e19\u0e49\u0e32', u'http://thaipost.net/taxonomy/term/64/all/feed'), (u'\u0e04\u0e31\u0e19\u0e1b\u0e32\u0e01\u0e2d\u0e22\u0e32\u0e01\u0e40\u0e25\u0e48\u0e32', u'http://thaipost.net/taxonomy/term/65/all/feed'), (u'\u0e40\u0e28\u0e23\u0e29\u0e10\u0e01\u0e34\u0e08', u'http://thaipost.net/taxonomy/term/6/all/feed'), (u'\u0e01\u0e23\u0e30\u0e08\u0e01\u0e44\u0e23\u0e49\u0e40\u0e07\u0e32', u'http://thaipost.net/taxonomy/term/14/all/feed'), (u'\u0e01\u0e23\u0e30\u0e08\u0e01\u0e2b\u0e31\u0e01\u0e21\u0e38\u0e21', u'http://thaipost.net/taxonomy/term/71/all/feed'), (u'\u0e04\u0e34\u0e14\u0e40\u0e2b\u0e19\u0e37\u0e2d\u0e01\u0e23\u0e30\u0e41\u0e2a', u'http://thaipost.net/taxonomy/term/69/all/feed'), (u'\u0e23\u0e32\u0e22\u0e07\u0e32\u0e19', u'http://thaipost.net/taxonomy/term/68/all/feed'), (u'\u0e2d\u0e34\u0e42\u0e04\u0e42\u0e1f\u0e01\u0e31\u0e2a', u'http://thaipost.net/taxonomy/term/10/all/feed'), (u'\u0e01\u0e32\u0e23\u0e28\u0e36\u0e01\u0e29\u0e32-\u0e2a\u0e32\u0e18\u0e32\u0e23\u0e13\u0e2a\u0e38\u0e02', u'http://thaipost.net/taxonomy/term/7/all/feed'), (u'\u0e15\u0e48\u0e32\u0e07\u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28', u'http://thaipost.net/taxonomy/term/8/all/feed'), (u'\u0e01\u0e35\u0e2c\u0e32', u'http://thaipost.net/taxonomy/term/9/all/feed')]
|
||||
|
||||
def print_version(self, url):
|
||||
return url.replace(url, 'http://www.thaipost.net/print/' + url [32:])
|
||||
|
||||
remove_tags = []
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'print-logo'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'print-site_name'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'print-breadcrumb'}))
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1299054026(BasicNewsRecipe):
|
||||
title = u'Thai Post Daily'
|
||||
__author__ = 'Chotechai P.'
|
||||
language = 'th'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
cover_url = 'http://upload.wikimedia.org/wikipedia/th/1/10/ThaiPost_Logo.png'
|
||||
feeds = [(u'\u0e02\u0e48\u0e32\u0e27\u0e2b\u0e19\u0e49\u0e32\u0e2b\u0e19\u0e36\u0e48\u0e07', u'http://thaipost.net/taxonomy/term/1/all/feed'), (u'\u0e1a\u0e17\u0e1a\u0e23\u0e23\u0e13\u0e32\u0e18\u0e34\u0e01\u0e32\u0e23', u'http://thaipost.net/taxonomy/term/11/all/feed'), (u'\u0e40\u0e1b\u0e25\u0e27 \u0e2a\u0e35\u0e40\u0e07\u0e34\u0e19', u'http://thaipost.net/taxonomy/term/2/all/feed'), (u'\u0e2a\u0e20\u0e32\u0e1b\u0e23\u0e30\u0e0a\u0e32\u0e0a\u0e19', u'http://thaipost.net/taxonomy/term/3/all/feed'), (u'\u0e16\u0e39\u0e01\u0e17\u0e38\u0e01\u0e02\u0e49\u0e2d', u'http://thaipost.net/taxonomy/term/4/all/feed'), (u'\u0e01\u0e32\u0e23\u0e40\u0e21\u0e37\u0e2d\u0e07', u'http://thaipost.net/taxonomy/term/5/all/feed'), (u'\u0e17\u0e48\u0e32\u0e19\u0e02\u0e38\u0e19\u0e19\u0e49\u0e2d\u0e22', u'http://thaipost.net/taxonomy/term/12/all/feed'), (u'\u0e1a\u0e17\u0e04\u0e27\u0e32\u0e21\u0e1e\u0e34\u0e40\u0e28\u0e29', u'http://thaipost.net/taxonomy/term/66/all/feed'), (u'\u0e23\u0e32\u0e22\u0e07\u0e32\u0e19\u0e1e\u0e34\u0e40\u0e28\u0e29', u'http://thaipost.net/taxonomy/term/67/all/feed'), (u'\u0e1a\u0e31\u0e19\u0e17\u0e36\u0e01\u0e2b\u0e19\u0e49\u0e32 4', u'http://thaipost.net/taxonomy/term/13/all/feed'), (u'\u0e40\u0e2a\u0e35\u0e22\u0e1a\u0e0b\u0e36\u0e48\u0e07\u0e2b\u0e19\u0e49\u0e32', u'http://thaipost.net/taxonomy/term/64/all/feed'), (u'\u0e04\u0e31\u0e19\u0e1b\u0e32\u0e01\u0e2d\u0e22\u0e32\u0e01\u0e40\u0e25\u0e48\u0e32', u'http://thaipost.net/taxonomy/term/65/all/feed'), (u'\u0e40\u0e28\u0e23\u0e29\u0e10\u0e01\u0e34\u0e08', u'http://thaipost.net/taxonomy/term/6/all/feed'), (u'\u0e01\u0e23\u0e30\u0e08\u0e01\u0e44\u0e23\u0e49\u0e40\u0e07\u0e32', u'http://thaipost.net/taxonomy/term/14/all/feed'), (u'\u0e01\u0e23\u0e30\u0e08\u0e01\u0e2b\u0e31\u0e01\u0e21\u0e38\u0e21', u'http://thaipost.net/taxonomy/term/71/all/feed'), (u'\u0e04\u0e34\u0e14\u0e40\u0e2b\u0e19\u0e37\u0e2d\u0e01\u0e23\u0e30\u0e41\u0e2a', u'http://thaipost.net/taxonomy/term/69/all/feed'), (u'\u0e23\u0e32\u0e22\u0e07\u0e32\u0e19', u'http://thaipost.net/taxonomy/term/68/all/feed'), (u'\u0e2d\u0e34\u0e42\u0e04\u0e42\u0e1f\u0e01\u0e31\u0e2a', u'http://thaipost.net/taxonomy/term/10/all/feed'), (u'\u0e01\u0e32\u0e23\u0e28\u0e36\u0e01\u0e29\u0e32-\u0e2a\u0e32\u0e18\u0e32\u0e23\u0e13\u0e2a\u0e38\u0e02', u'http://thaipost.net/taxonomy/term/7/all/feed'), (u'\u0e15\u0e48\u0e32\u0e07\u0e1b\u0e23\u0e30\u0e40\u0e17\u0e28', u'http://thaipost.net/taxonomy/term/8/all/feed'), (u'\u0e01\u0e35\u0e2c\u0e32', u'http://thaipost.net/taxonomy/term/9/all/feed')]
|
||||
|
||||
def print_version(self, url):
|
||||
return url.replace(url, 'http://www.thaipost.net/print/' + url [32:])
|
||||
|
||||
remove_tags = []
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'print-logo'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'print-site_name'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'print-breadcrumb'}))
|
||||
|
||||
@ -1,27 +1,27 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1313555075(BasicNewsRecipe):
|
||||
news = True
|
||||
title = u'The Clinic'
|
||||
__author__ = 'Alex Mitrani'
|
||||
description = u'Online version of Chilean satirical weekly'
|
||||
publisher = u'The Clinic'
|
||||
category = 'news, politics, Chile, rss'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
summary_length = 1000
|
||||
language = 'es_CL'
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.theclinic.cl/wp-content/themes/tc12m/css/ui/mainLogoTC-top.png'
|
||||
remove_tags_before = dict(name='article', attrs={'class':'scope bordered'})
|
||||
remove_tags_after = dict(name='div', attrs={'id':'commentsSection'})
|
||||
remove_tags = [dict(name='span', attrs={'class':'relTags'})
|
||||
,dict(name='div', attrs={'class':'articleActivity hdcol'})
|
||||
,dict(name='div', attrs={'id':'commentsSection'})
|
||||
]
|
||||
|
||||
feeds = [(u'The Clinic Online', u'http://www.theclinic.cl/feed/')]
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1313555075(BasicNewsRecipe):
|
||||
news = True
|
||||
title = u'The Clinic'
|
||||
__author__ = 'Alex Mitrani'
|
||||
description = u'Online version of Chilean satirical weekly'
|
||||
publisher = u'The Clinic'
|
||||
category = 'news, politics, Chile, rss'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
summary_length = 1000
|
||||
language = 'es_CL'
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
masthead_url = 'http://www.theclinic.cl/wp-content/themes/tc12m/css/ui/mainLogoTC-top.png'
|
||||
remove_tags_before = dict(name='article', attrs={'class':'scope bordered'})
|
||||
remove_tags_after = dict(name='div', attrs={'id':'commentsSection'})
|
||||
remove_tags = [dict(name='span', attrs={'class':'relTags'})
|
||||
,dict(name='div', attrs={'class':'articleActivity hdcol'})
|
||||
,dict(name='div', attrs={'id':'commentsSection'})
|
||||
]
|
||||
|
||||
feeds = [(u'The Clinic Online', u'http://www.theclinic.cl/feed/')]
|
||||
|
||||
@ -1,63 +1,63 @@
|
||||
import re
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
|
||||
class TNR(BasicNewsRecipe):
|
||||
|
||||
title = 'The New Republic'
|
||||
__author__ = 'Krittika Goyal'
|
||||
|
||||
description = '''The New Republic is a journal of opinion with an emphasis
|
||||
on politics and domestic and international affairs. It carries feature
|
||||
articles by staff and contributing editors. The second half of each issue
|
||||
is devoted to book and the arts, theater, motion pictures, music and art.'''
|
||||
|
||||
language = 'en'
|
||||
encoding = 'UTF-8'
|
||||
needs_subscription = True
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: ''),
|
||||
(re.compile(r'<script.*?</script>', re.DOTALL), lambda m: ''),
|
||||
]
|
||||
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
br.open('http://www.newrepublic.com/user')
|
||||
br.select_form(nr=1)
|
||||
try:
|
||||
br['user'] = self.username
|
||||
except:
|
||||
br['name'] = self.username
|
||||
br['pass'] = self.password
|
||||
self.log('Logging in...')
|
||||
raw = br.submit().read()
|
||||
if 'SIGN OUT' not in raw:
|
||||
raise ValueError('Failed to log in to tnr.com, check your username and password')
|
||||
self.log('Logged in successfully')
|
||||
return br
|
||||
|
||||
def parse_index(self):
|
||||
raw = self.index_to_soup('http://www.newrepublic.com/current-issue', raw=True)
|
||||
# raw = self.index_to_soup(open('/t/raw.html').read().decode('utf-8'), raw=True)
|
||||
for pat, sub in self.preprocess_regexps:
|
||||
raw = pat.sub(sub, raw)
|
||||
soup = self.index_to_soup(raw)
|
||||
feed_title = 'The New Republic Magazine Articles'
|
||||
|
||||
articles = []
|
||||
for div in soup.findAll('div', attrs={'class':lambda x: x and 'field-item' in x.split()}):
|
||||
a = div.find('a', href=True, attrs={'class':lambda x: x != 'author'})
|
||||
if a is not None:
|
||||
art_title = self.tag_to_string(a)
|
||||
url = a.get('href')
|
||||
num = re.search(r'/(\d+)/', url)
|
||||
if num is not None:
|
||||
art = num.group(1)
|
||||
url = 'http://www.newrepublic.com/node/%s/print'%art
|
||||
self.log.info('\tFound article:', art_title, 'at', url)
|
||||
article = {'title':art_title, 'url':url, 'description':'', 'date':''}
|
||||
articles.append(article)
|
||||
|
||||
return [(feed_title, articles)]
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
|
||||
class TNR(BasicNewsRecipe):
|
||||
|
||||
title = 'The New Republic'
|
||||
__author__ = 'Krittika Goyal'
|
||||
|
||||
description = '''The New Republic is a journal of opinion with an emphasis
|
||||
on politics and domestic and international affairs. It carries feature
|
||||
articles by staff and contributing editors. The second half of each issue
|
||||
is devoted to book and the arts, theater, motion pictures, music and art.'''
|
||||
|
||||
language = 'en'
|
||||
encoding = 'UTF-8'
|
||||
needs_subscription = True
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: ''),
|
||||
(re.compile(r'<script.*?</script>', re.DOTALL), lambda m: ''),
|
||||
]
|
||||
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
br.open('http://www.newrepublic.com/user')
|
||||
br.select_form(nr=1)
|
||||
try:
|
||||
br['user'] = self.username
|
||||
except:
|
||||
br['name'] = self.username
|
||||
br['pass'] = self.password
|
||||
self.log('Logging in...')
|
||||
raw = br.submit().read()
|
||||
if 'SIGN OUT' not in raw:
|
||||
raise ValueError('Failed to log in to tnr.com, check your username and password')
|
||||
self.log('Logged in successfully')
|
||||
return br
|
||||
|
||||
def parse_index(self):
|
||||
raw = self.index_to_soup('http://www.newrepublic.com/current-issue', raw=True)
|
||||
# raw = self.index_to_soup(open('/t/raw.html').read().decode('utf-8'), raw=True)
|
||||
for pat, sub in self.preprocess_regexps:
|
||||
raw = pat.sub(sub, raw)
|
||||
soup = self.index_to_soup(raw)
|
||||
feed_title = 'The New Republic Magazine Articles'
|
||||
|
||||
articles = []
|
||||
for div in soup.findAll('div', attrs={'class':lambda x: x and 'field-item' in x.split()}):
|
||||
a = div.find('a', href=True, attrs={'class':lambda x: x != 'author'})
|
||||
if a is not None:
|
||||
art_title = self.tag_to_string(a)
|
||||
url = a.get('href')
|
||||
num = re.search(r'/(\d+)/', url)
|
||||
if num is not None:
|
||||
art = num.group(1)
|
||||
url = 'http://www.newrepublic.com/node/%s/print'%art
|
||||
self.log.info('\tFound article:', art_title, 'at', url)
|
||||
article = {'title':art_title, 'url':url, 'description':'', 'date':''}
|
||||
articles.append(article)
|
||||
|
||||
return [(feed_title, articles)]
|
||||
|
||||
|
||||
@ -1,76 +1,76 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__author__ = 'Darko Spasovski'
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Darko Spasovski <darko.spasovski at gmail.com>'
|
||||
'''
|
||||
utrinski.com.mk
|
||||
'''
|
||||
|
||||
import re
|
||||
import datetime
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
from calibre import browser
|
||||
|
||||
class UtrinskiVesnik(BasicNewsRecipe):
|
||||
|
||||
INDEX = 'http://www.utrinski.com.mk/'
|
||||
title = 'Utrinski Vesnik'
|
||||
description = 'Daily Macedonian newspaper'
|
||||
masthead_url = 'http://www.utrinski.com.mk/images/LogoTop.jpg'
|
||||
language = 'mk'
|
||||
remove_javascript = True
|
||||
publication_type = 'newspaper'
|
||||
category = 'news, Macedonia'
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
## Remove anything before the start of the article.
|
||||
(r'<body.*?Article start-->', lambda match: '<body>'),
|
||||
|
||||
## Remove anything after the end of the article.
|
||||
(r'<!--Article end.*?</body>', lambda match : '</body>'),
|
||||
]
|
||||
]
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif}
|
||||
.WB_UTRINSKIVESNIK_Naslov{FONT-WEIGHT: bold; FONT-SIZE: 18px; FONT-FAMILY: Arial, Verdana, Tahoma; TEXT-DECORATION: none}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description,
|
||||
'tags' : category,
|
||||
'language' : language,
|
||||
'linearize_tables' : True
|
||||
}
|
||||
|
||||
def parse_index(self):
|
||||
feeds = []
|
||||
# open main page
|
||||
soup = self.index_to_soup(self.INDEX)
|
||||
# find all anchors with class attribute equal to 'WB_UTRINSKIVESNIK_MainMenu'
|
||||
for section in soup.findAll('a', attrs={'class':'WB_UTRINSKIVESNIK_MainMenu'}):
|
||||
sectionTitle = section.contents[0].string
|
||||
sectionUrl = self.INDEX + section['href'].strip()
|
||||
# open the anchor link
|
||||
raw = browser().open_novisit(sectionUrl).read()
|
||||
sectionSoup = BeautifulSoup(raw)
|
||||
# find all anchors with class attribute equal to 'WB_UTRINSKIVESNIK_ONLINEArticleTitle'
|
||||
sectionArticles = sectionSoup.findAll('a', attrs={'class':'WB_UTRINSKIVESNIK_ONLINEArticleTitle'})
|
||||
articles = []
|
||||
for sectionArticle in sectionArticles:
|
||||
# article title = anchor's contents, article url = anchor's href
|
||||
articleTitle = sectionArticle.contents[0].string.strip()
|
||||
articleUrl = self.INDEX + sectionArticle['href'].strip()
|
||||
articleDate = datetime.datetime.today().strftime('%d.%m.%Y')
|
||||
articles.append({'title': articleTitle, 'url':articleUrl, 'description':'', 'date': articleDate})
|
||||
if articles:
|
||||
feeds.append((sectionTitle, articles))
|
||||
return feeds
|
||||
|
||||
def get_cover_url(self):
|
||||
datum = datetime.datetime.today().strftime('%d_%m_%Y')
|
||||
return 'http://www.utrinski.com.mk/WBStorage/Files/' + datum + '.jpg'
|
||||
#!/usr/bin/env python
|
||||
|
||||
__author__ = 'Darko Spasovski'
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Darko Spasovski <darko.spasovski at gmail.com>'
|
||||
'''
|
||||
utrinski.com.mk
|
||||
'''
|
||||
|
||||
import re
|
||||
import datetime
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
from calibre import browser
|
||||
|
||||
class UtrinskiVesnik(BasicNewsRecipe):
|
||||
|
||||
INDEX = 'http://www.utrinski.com.mk/'
|
||||
title = 'Utrinski Vesnik'
|
||||
description = 'Daily Macedonian newspaper'
|
||||
masthead_url = 'http://www.utrinski.com.mk/images/LogoTop.jpg'
|
||||
language = 'mk'
|
||||
remove_javascript = True
|
||||
publication_type = 'newspaper'
|
||||
category = 'news, Macedonia'
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
## Remove anything before the start of the article.
|
||||
(r'<body.*?Article start-->', lambda match: '<body>'),
|
||||
|
||||
## Remove anything after the end of the article.
|
||||
(r'<!--Article end.*?</body>', lambda match : '</body>'),
|
||||
]
|
||||
]
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif}
|
||||
.WB_UTRINSKIVESNIK_Naslov{FONT-WEIGHT: bold; FONT-SIZE: 18px; FONT-FAMILY: Arial, Verdana, Tahoma; TEXT-DECORATION: none}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description,
|
||||
'tags' : category,
|
||||
'language' : language,
|
||||
'linearize_tables' : True
|
||||
}
|
||||
|
||||
def parse_index(self):
|
||||
feeds = []
|
||||
# open main page
|
||||
soup = self.index_to_soup(self.INDEX)
|
||||
# find all anchors with class attribute equal to 'WB_UTRINSKIVESNIK_MainMenu'
|
||||
for section in soup.findAll('a', attrs={'class':'WB_UTRINSKIVESNIK_MainMenu'}):
|
||||
sectionTitle = section.contents[0].string
|
||||
sectionUrl = self.INDEX + section['href'].strip()
|
||||
# open the anchor link
|
||||
raw = browser().open_novisit(sectionUrl).read()
|
||||
sectionSoup = BeautifulSoup(raw)
|
||||
# find all anchors with class attribute equal to 'WB_UTRINSKIVESNIK_ONLINEArticleTitle'
|
||||
sectionArticles = sectionSoup.findAll('a', attrs={'class':'WB_UTRINSKIVESNIK_ONLINEArticleTitle'})
|
||||
articles = []
|
||||
for sectionArticle in sectionArticles:
|
||||
# article title = anchor's contents, article url = anchor's href
|
||||
articleTitle = sectionArticle.contents[0].string.strip()
|
||||
articleUrl = self.INDEX + sectionArticle['href'].strip()
|
||||
articleDate = datetime.datetime.today().strftime('%d.%m.%Y')
|
||||
articles.append({'title': articleTitle, 'url':articleUrl, 'description':'', 'date': articleDate})
|
||||
if articles:
|
||||
feeds.append((sectionTitle, articles))
|
||||
return feeds
|
||||
|
||||
def get_cover_url(self):
|
||||
datum = datetime.datetime.today().strftime('%d_%m_%Y')
|
||||
return 'http://www.utrinski.com.mk/WBStorage/Files/' + datum + '.jpg'
|
||||
|
||||
@ -1,19 +1,19 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class AdvancedUserRecipe1350731826(BasicNewsRecipe):
|
||||
title = u'Yazihane'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
__author__ = 'A Erdogan'
|
||||
description = 'Sports Blog'
|
||||
publisher = 'yazihaneden.com'
|
||||
category = 'sports, basketball, nba, cycling, euroleague'
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
masthead_url = 'http://www.yazihaneden.com/wp-content/uploads/Untitled-1.png'
|
||||
language = 'tr'
|
||||
|
||||
keep_only_tags = [ dict(name='div', attrs={'id':re.compile('(^|| )post-($|| )', re.DOTALL)})]
|
||||
remove_tags_after = dict(name='div', attrs={'class':'post-footer clear'})
|
||||
feeds = [(u'Yazihane', u'http://www.yazihaneden.com/feed/')]
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class AdvancedUserRecipe1350731826(BasicNewsRecipe):
|
||||
title = u'Yazihane'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
__author__ = 'A Erdogan'
|
||||
description = 'Sports Blog'
|
||||
publisher = 'yazihaneden.com'
|
||||
category = 'sports, basketball, nba, cycling, euroleague'
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
masthead_url = 'http://www.yazihaneden.com/wp-content/uploads/Untitled-1.png'
|
||||
language = 'tr'
|
||||
|
||||
keep_only_tags = [ dict(name='div', attrs={'id':re.compile('(^|| )post-($|| )', re.DOTALL)})]
|
||||
remove_tags_after = dict(name='div', attrs={'class':'post-footer clear'})
|
||||
feeds = [(u'Yazihane', u'http://www.yazihaneden.com/feed/')]
|
||||
|
||||
@ -1,208 +1,208 @@
|
||||
@echo OFF
|
||||
REM Calibre-Portable.bat
|
||||
REM ¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬
|
||||
REM
|
||||
REM Batch File to start a Calibre configuration on Windows
|
||||
REM giving explicit control of the location of:
|
||||
REM - Calibre Program Files
|
||||
REM - Calibre Library Files
|
||||
REM - Calibre Config Files
|
||||
REM - Calibre Metadata database
|
||||
REM - Calibre Source files
|
||||
REM - Calibre Temp Files
|
||||
REM By setting the paths correctly it can be used to run:
|
||||
REM - A "portable calibre" off a USB stick.
|
||||
REM - A network installation with local metadata database
|
||||
REM (for performance) and books stored on a network share
|
||||
REM - A local installation using customised settings
|
||||
REM
|
||||
REM If trying to run off a USB stick then the folder structure
|
||||
REM shown below is recommended (relative to the location of
|
||||
REM this batch file). This can structure can also be used
|
||||
REM when running of a local hard disk if you want to get the
|
||||
REM level of control this batch file provides.
|
||||
REM - Calibre2 Location of program files
|
||||
REM - CalibreConfig Location of Configuration files
|
||||
REM - CalibreLibrary Location of Books and metadata
|
||||
REM - CalibreSource Location of Calibre Source files (Optional)
|
||||
REM
|
||||
REM This batch file is designed so that if you create the recommended
|
||||
REM folder structure then it can be used 'as is' without modification.
|
||||
REM
|
||||
REM More information on the Environment Variables used by Calibre can
|
||||
REM be found at:
|
||||
REM http://manual.calibre-ebook.com/customize.html#environment-variables
|
||||
REM
|
||||
REM The documentation for this file in the Calibre manual can be found at:
|
||||
REM http://manual.calibre-ebook.com/portable.html
|
||||
REM
|
||||
REM CHANGE HISTORY
|
||||
REM ¬¬¬¬¬¬¬¬¬¬¬¬¬¬
|
||||
REM 22 Jan 2012 itimpi - Updated to keep it in line with the calibre-portable.sh
|
||||
REM file for Linux systems
|
||||
|
||||
|
||||
|
||||
REM -------------------------------------
|
||||
REM Set up Calibre Config folder
|
||||
REM
|
||||
REM This is where user specific settings
|
||||
REM are stored.
|
||||
REM -------------------------------------
|
||||
|
||||
IF EXIST CalibreConfig (
|
||||
SET CALIBRE_CONFIG_DIRECTORY=%cd%\CalibreConfig
|
||||
ECHO CONFIG FILES: %cd%\CalibreConfig
|
||||
)
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Specify Location of ebooks
|
||||
REM
|
||||
REM Location where Book files are located
|
||||
REM Either set explicit path, or if running from a USB stick
|
||||
REM a relative path can be used to avoid need to know the
|
||||
REM drive letter of the USB stick.
|
||||
REM
|
||||
REM Comment out any of the following that are not to be used
|
||||
REM (although leaving them in does not really matter)
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
IF EXIST U:\eBooks\CalibreLibrary (
|
||||
SET CALIBRE_LIBRARY_DIRECTORY=U:\eBOOKS\CalibreLibrary
|
||||
ECHO LIBRARY FILES: U:\eBOOKS\CalibreLibrary
|
||||
)
|
||||
IF EXIST CalibreLibrary (
|
||||
SET CALIBRE_LIBRARY_DIRECTORY=%cd%\CalibreLibrary
|
||||
ECHO LIBRARY FILES: %cd%\CalibreLibrary
|
||||
)
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Specify Location of metadata database (optional)
|
||||
REM
|
||||
REM Location where the metadata.db file is located. If not set
|
||||
REM the same location as Books files will be assumed. This.
|
||||
REM option is typically set to get better performance when the
|
||||
REM Library is on a (slow) network drive. Putting the metadata.db
|
||||
REM file locally then makes gives a big performance improvement.
|
||||
REM
|
||||
REM NOTE. If you use this option, then the ability to switch
|
||||
REM libraries within Calibre will be disabled. Therefore
|
||||
REM you do not want to set it if the metadata.db file
|
||||
REM is at the same location as the book files.
|
||||
REM
|
||||
REM Another point to watch is that plugins can cause problems
|
||||
REM as they often store absolute path information
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
IF EXIST %cd%\CalibreMetadata\metadata.db (
|
||||
IF NOT "%CALIBRE_LIBRARY_DIRECTORY%" == "%cd%\CalibreMetadata" (
|
||||
SET CALIBRE_OVERRIDE_DATABASE_PATH=%cd%\CalibreMetadata\metadata.db
|
||||
ECHO DATABASE: %cd%\CalibreMetadata\metadata.db
|
||||
ECHO '
|
||||
ECHO ***CAUTION*** Library Switching will be disabled
|
||||
ECHO '
|
||||
)
|
||||
)
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Specify Location of source (optional)
|
||||
REM
|
||||
REM It is easy to run Calibre from source
|
||||
REM Just set the environment variable to where the source is located
|
||||
REM When running from source the GUI will have a '*' after the version.
|
||||
REM number that is displayed at the bottom of the Calibre main screen.
|
||||
REM
|
||||
REM More information on setting up a development environment can
|
||||
REM be found at:
|
||||
REM http://manual.calibre-ebook.com/develop.html#develop
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
IF EXIST CalibreSource\src (
|
||||
SET CALIBRE_DEVELOP_FROM=%cd%\CalibreSource\src
|
||||
ECHO SOURCE FILES: %cd%\CalibreSource\src
|
||||
) ELSE (
|
||||
ECHO SOURCE FILES: *** Not being Used ***
|
||||
)
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Specify Location of calibre Windows binaries (optional)
|
||||
REM
|
||||
REM To avoid needing Calibre to be set in the search path, ensure
|
||||
REM that Calibre Program Files is current directory when starting.
|
||||
REM The following test falls back to using search path .
|
||||
REM This folder can be populated by copying the Calibre2 folder from
|
||||
REM an existing installation or by installing direct to here.
|
||||
REM
|
||||
REM NOTE. Do not try and put both Windows and Linux binaries into
|
||||
REM same folder as this can cause problems.
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
IF EXIST %cd%\Calibre2 (
|
||||
CD %cd%\Calibre2
|
||||
ECHO PROGRAM FILES: %cd%
|
||||
) ELSE (
|
||||
ECHO PROGRAM FILES: *** Use System search PATH ***
|
||||
)
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Location of Calibre Temporary files (optional)
|
||||
REM
|
||||
REM Calibre creates a lot of temporary files while running
|
||||
REM In theory these are removed when Calibre finishes, but
|
||||
REM in practise files can be left behind (particularily if
|
||||
REM any errors occur). Using this option allows some
|
||||
REM explicit clean-up of these files.
|
||||
REM If not set Calibre uses the normal system TEMP location
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
SET CALIBRE_TEMP_DIR=%TEMP%\CALIBRE_TEMP
|
||||
ECHO TEMPORARY FILES: %CALIBRE_TEMP_DIR%
|
||||
|
||||
IF EXIST "%CALIBRE_TEMP_DIR%" RMDIR /s /q "%CALIBRE_TEMP_DIR%"
|
||||
MKDIR "%CALIBRE_TEMP_DIR%"
|
||||
REM set the following for any components that do
|
||||
REM not obey the CALIBRE_TEMP_DIR setting
|
||||
SET TMP=%CALIBRE_TEMP_DIR%
|
||||
SET TEMP=%CALIBRE_TEMP_DIR%
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Set the Interface language (optional)
|
||||
REM
|
||||
REM If not set Calibre uses the language set in Preferences
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
SET CALIBRE_OVERRIDE_LANG=EN
|
||||
ECHO INTERFACE LANGUAGE: %CALIBRE_OVERRIDE_LANG%
|
||||
|
||||
REM ----------------------------------------------------------
|
||||
REM The following gives a chance to check the settings before
|
||||
REM starting Calibre. It can be commented out if not wanted.
|
||||
REM ----------------------------------------------------------
|
||||
|
||||
ECHO '
|
||||
ECHO Press CTRL-C if you do not want to continue
|
||||
PAUSE
|
||||
|
||||
|
||||
REM --------------------------------------------------------
|
||||
REM Start up the calibre program.
|
||||
REM
|
||||
REM The use of 'belownormal' priority helps keep the system
|
||||
REM responsive while Calibre is running. Within Calibre itself
|
||||
REM the backgound processes should be set to run with 'low' priority.
|
||||
|
||||
REM Using the START command starts up Calibre in a separate process.
|
||||
REM If used without /WAIT option it launches Calibre and contines batch file.
|
||||
REM normally this would simply run off the end and close the Command window.
|
||||
REM Use with /WAIT to wait until Calibre completes to run a task on exit
|
||||
REM --------------------------------------------------------
|
||||
|
||||
ECHO "Starting up Calibre"
|
||||
ECHO OFF
|
||||
ECHO %cd%
|
||||
START /belownormal Calibre --with-library "%CALIBRE_LIBRARY_DIRECTORY%"
|
||||
@echo OFF
|
||||
REM Calibre-Portable.bat
|
||||
REM ¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬
|
||||
REM
|
||||
REM Batch File to start a Calibre configuration on Windows
|
||||
REM giving explicit control of the location of:
|
||||
REM - Calibre Program Files
|
||||
REM - Calibre Library Files
|
||||
REM - Calibre Config Files
|
||||
REM - Calibre Metadata database
|
||||
REM - Calibre Source files
|
||||
REM - Calibre Temp Files
|
||||
REM By setting the paths correctly it can be used to run:
|
||||
REM - A "portable calibre" off a USB stick.
|
||||
REM - A network installation with local metadata database
|
||||
REM (for performance) and books stored on a network share
|
||||
REM - A local installation using customised settings
|
||||
REM
|
||||
REM If trying to run off a USB stick then the folder structure
|
||||
REM shown below is recommended (relative to the location of
|
||||
REM this batch file). This can structure can also be used
|
||||
REM when running of a local hard disk if you want to get the
|
||||
REM level of control this batch file provides.
|
||||
REM - Calibre2 Location of program files
|
||||
REM - CalibreConfig Location of Configuration files
|
||||
REM - CalibreLibrary Location of Books and metadata
|
||||
REM - CalibreSource Location of Calibre Source files (Optional)
|
||||
REM
|
||||
REM This batch file is designed so that if you create the recommended
|
||||
REM folder structure then it can be used 'as is' without modification.
|
||||
REM
|
||||
REM More information on the Environment Variables used by Calibre can
|
||||
REM be found at:
|
||||
REM http://manual.calibre-ebook.com/customize.html#environment-variables
|
||||
REM
|
||||
REM The documentation for this file in the Calibre manual can be found at:
|
||||
REM http://manual.calibre-ebook.com/portable.html
|
||||
REM
|
||||
REM CHANGE HISTORY
|
||||
REM ¬¬¬¬¬¬¬¬¬¬¬¬¬¬
|
||||
REM 22 Jan 2012 itimpi - Updated to keep it in line with the calibre-portable.sh
|
||||
REM file for Linux systems
|
||||
|
||||
|
||||
|
||||
REM -------------------------------------
|
||||
REM Set up Calibre Config folder
|
||||
REM
|
||||
REM This is where user specific settings
|
||||
REM are stored.
|
||||
REM -------------------------------------
|
||||
|
||||
IF EXIST CalibreConfig (
|
||||
SET CALIBRE_CONFIG_DIRECTORY=%cd%\CalibreConfig
|
||||
ECHO CONFIG FILES: %cd%\CalibreConfig
|
||||
)
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Specify Location of ebooks
|
||||
REM
|
||||
REM Location where Book files are located
|
||||
REM Either set explicit path, or if running from a USB stick
|
||||
REM a relative path can be used to avoid need to know the
|
||||
REM drive letter of the USB stick.
|
||||
REM
|
||||
REM Comment out any of the following that are not to be used
|
||||
REM (although leaving them in does not really matter)
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
IF EXIST U:\eBooks\CalibreLibrary (
|
||||
SET CALIBRE_LIBRARY_DIRECTORY=U:\eBOOKS\CalibreLibrary
|
||||
ECHO LIBRARY FILES: U:\eBOOKS\CalibreLibrary
|
||||
)
|
||||
IF EXIST CalibreLibrary (
|
||||
SET CALIBRE_LIBRARY_DIRECTORY=%cd%\CalibreLibrary
|
||||
ECHO LIBRARY FILES: %cd%\CalibreLibrary
|
||||
)
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Specify Location of metadata database (optional)
|
||||
REM
|
||||
REM Location where the metadata.db file is located. If not set
|
||||
REM the same location as Books files will be assumed. This.
|
||||
REM option is typically set to get better performance when the
|
||||
REM Library is on a (slow) network drive. Putting the metadata.db
|
||||
REM file locally then makes gives a big performance improvement.
|
||||
REM
|
||||
REM NOTE. If you use this option, then the ability to switch
|
||||
REM libraries within Calibre will be disabled. Therefore
|
||||
REM you do not want to set it if the metadata.db file
|
||||
REM is at the same location as the book files.
|
||||
REM
|
||||
REM Another point to watch is that plugins can cause problems
|
||||
REM as they often store absolute path information
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
IF EXIST %cd%\CalibreMetadata\metadata.db (
|
||||
IF NOT "%CALIBRE_LIBRARY_DIRECTORY%" == "%cd%\CalibreMetadata" (
|
||||
SET CALIBRE_OVERRIDE_DATABASE_PATH=%cd%\CalibreMetadata\metadata.db
|
||||
ECHO DATABASE: %cd%\CalibreMetadata\metadata.db
|
||||
ECHO '
|
||||
ECHO ***CAUTION*** Library Switching will be disabled
|
||||
ECHO '
|
||||
)
|
||||
)
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Specify Location of source (optional)
|
||||
REM
|
||||
REM It is easy to run Calibre from source
|
||||
REM Just set the environment variable to where the source is located
|
||||
REM When running from source the GUI will have a '*' after the version.
|
||||
REM number that is displayed at the bottom of the Calibre main screen.
|
||||
REM
|
||||
REM More information on setting up a development environment can
|
||||
REM be found at:
|
||||
REM http://manual.calibre-ebook.com/develop.html#develop
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
IF EXIST CalibreSource\src (
|
||||
SET CALIBRE_DEVELOP_FROM=%cd%\CalibreSource\src
|
||||
ECHO SOURCE FILES: %cd%\CalibreSource\src
|
||||
) ELSE (
|
||||
ECHO SOURCE FILES: *** Not being Used ***
|
||||
)
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Specify Location of calibre Windows binaries (optional)
|
||||
REM
|
||||
REM To avoid needing Calibre to be set in the search path, ensure
|
||||
REM that Calibre Program Files is current directory when starting.
|
||||
REM The following test falls back to using search path .
|
||||
REM This folder can be populated by copying the Calibre2 folder from
|
||||
REM an existing installation or by installing direct to here.
|
||||
REM
|
||||
REM NOTE. Do not try and put both Windows and Linux binaries into
|
||||
REM same folder as this can cause problems.
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
IF EXIST %cd%\Calibre2 (
|
||||
CD %cd%\Calibre2
|
||||
ECHO PROGRAM FILES: %cd%
|
||||
) ELSE (
|
||||
ECHO PROGRAM FILES: *** Use System search PATH ***
|
||||
)
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Location of Calibre Temporary files (optional)
|
||||
REM
|
||||
REM Calibre creates a lot of temporary files while running
|
||||
REM In theory these are removed when Calibre finishes, but
|
||||
REM in practise files can be left behind (particularily if
|
||||
REM any errors occur). Using this option allows some
|
||||
REM explicit clean-up of these files.
|
||||
REM If not set Calibre uses the normal system TEMP location
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
SET CALIBRE_TEMP_DIR=%TEMP%\CALIBRE_TEMP
|
||||
ECHO TEMPORARY FILES: %CALIBRE_TEMP_DIR%
|
||||
|
||||
IF EXIST "%CALIBRE_TEMP_DIR%" RMDIR /s /q "%CALIBRE_TEMP_DIR%"
|
||||
MKDIR "%CALIBRE_TEMP_DIR%"
|
||||
REM set the following for any components that do
|
||||
REM not obey the CALIBRE_TEMP_DIR setting
|
||||
SET TMP=%CALIBRE_TEMP_DIR%
|
||||
SET TEMP=%CALIBRE_TEMP_DIR%
|
||||
|
||||
|
||||
REM --------------------------------------------------------------
|
||||
REM Set the Interface language (optional)
|
||||
REM
|
||||
REM If not set Calibre uses the language set in Preferences
|
||||
REM --------------------------------------------------------------
|
||||
|
||||
SET CALIBRE_OVERRIDE_LANG=EN
|
||||
ECHO INTERFACE LANGUAGE: %CALIBRE_OVERRIDE_LANG%
|
||||
|
||||
REM ----------------------------------------------------------
|
||||
REM The following gives a chance to check the settings before
|
||||
REM starting Calibre. It can be commented out if not wanted.
|
||||
REM ----------------------------------------------------------
|
||||
|
||||
ECHO '
|
||||
ECHO Press CTRL-C if you do not want to continue
|
||||
PAUSE
|
||||
|
||||
|
||||
REM --------------------------------------------------------
|
||||
REM Start up the calibre program.
|
||||
REM
|
||||
REM The use of 'belownormal' priority helps keep the system
|
||||
REM responsive while Calibre is running. Within Calibre itself
|
||||
REM the backgound processes should be set to run with 'low' priority.
|
||||
|
||||
REM Using the START command starts up Calibre in a separate process.
|
||||
REM If used without /WAIT option it launches Calibre and contines batch file.
|
||||
REM normally this would simply run off the end and close the Command window.
|
||||
REM Use with /WAIT to wait until Calibre completes to run a task on exit
|
||||
REM --------------------------------------------------------
|
||||
|
||||
ECHO "Starting up Calibre"
|
||||
ECHO OFF
|
||||
ECHO %cd%
|
||||
START /belownormal Calibre --with-library "%CALIBRE_LIBRARY_DIRECTORY%"
|
||||
|
||||
@ -1,10 +1,10 @@
|
||||
/**
|
||||
* Version: 1.0 Alpha-1
|
||||
* Build Date: 13-Nov-2007
|
||||
* Copyright (c) 2006-2007, Coolite Inc. (http://www.coolite.com/). All rights reserved.
|
||||
* License: Licensed under The MIT License. See license.txt and http://www.datejs.com/license/.
|
||||
* Website: http://www.datejs.com/ or http://www.coolite.com/datejs/
|
||||
*/
|
||||
/**
|
||||
* Version: 1.0 Alpha-1
|
||||
* Build Date: 13-Nov-2007
|
||||
* Copyright (c) 2006-2007, Coolite Inc. (http://www.coolite.com/). All rights reserved.
|
||||
* License: Licensed under The MIT License. See license.txt and http://www.datejs.com/license/.
|
||||
* Website: http://www.datejs.com/ or http://www.coolite.com/datejs/
|
||||
*/
|
||||
Date.CultureInfo={name:"en-US",englishName:"English (United States)",nativeName:"English (United States)",dayNames:["Sunday","Monday","Tuesday","Wednesday","Thursday","Friday","Saturday"],abbreviatedDayNames:["Sun","Mon","Tue","Wed","Thu","Fri","Sat"],shortestDayNames:["Su","Mo","Tu","We","Th","Fr","Sa"],firstLetterDayNames:["S","M","T","W","T","F","S"],monthNames:["January","February","March","April","May","June","July","August","September","October","November","December"],abbreviatedMonthNames:["Jan","Feb","Mar","Apr","May","Jun","Jul","Aug","Sep","Oct","Nov","Dec"],amDesignator:"AM",pmDesignator:"PM",firstDayOfWeek:0,twoDigitYearMax:2029,dateElementOrder:"mdy",formatPatterns:{shortDate:"M/d/yyyy",longDate:"dddd, MMMM dd, yyyy",shortTime:"h:mm tt",longTime:"h:mm:ss tt",fullDateTime:"dddd, MMMM dd, yyyy h:mm:ss tt",sortableDateTime:"yyyy-MM-ddTHH:mm:ss",universalSortableDateTime:"yyyy-MM-dd HH:mm:ssZ",rfc1123:"ddd, dd MMM yyyy HH:mm:ss GMT",monthDay:"MMMM dd",yearMonth:"MMMM, yyyy"},regexPatterns:{jan:/^jan(uary)?/i,feb:/^feb(ruary)?/i,mar:/^mar(ch)?/i,apr:/^apr(il)?/i,may:/^may/i,jun:/^jun(e)?/i,jul:/^jul(y)?/i,aug:/^aug(ust)?/i,sep:/^sep(t(ember)?)?/i,oct:/^oct(ober)?/i,nov:/^nov(ember)?/i,dec:/^dec(ember)?/i,sun:/^su(n(day)?)?/i,mon:/^mo(n(day)?)?/i,tue:/^tu(e(s(day)?)?)?/i,wed:/^we(d(nesday)?)?/i,thu:/^th(u(r(s(day)?)?)?)?/i,fri:/^fr(i(day)?)?/i,sat:/^sa(t(urday)?)?/i,future:/^next/i,past:/^last|past|prev(ious)?/i,add:/^(\+|after|from)/i,subtract:/^(\-|before|ago)/i,yesterday:/^yesterday/i,today:/^t(oday)?/i,tomorrow:/^tomorrow/i,now:/^n(ow)?/i,millisecond:/^ms|milli(second)?s?/i,second:/^sec(ond)?s?/i,minute:/^min(ute)?s?/i,hour:/^h(ou)?rs?/i,week:/^w(ee)?k/i,month:/^m(o(nth)?s?)?/i,day:/^d(ays?)?/i,year:/^y((ea)?rs?)?/i,shortMeridian:/^(a|p)/i,longMeridian:/^(a\.?m?\.?|p\.?m?\.?)/i,timezone:/^((e(s|d)t|c(s|d)t|m(s|d)t|p(s|d)t)|((gmt)?\s*(\+|\-)\s*\d\d\d\d?)|gmt)/i,ordinalSuffix:/^\s*(st|nd|rd|th)/i,timeContext:/^\s*(\:|a|p)/i},abbreviatedTimeZoneStandard:{GMT:"-000",EST:"-0400",CST:"-0500",MST:"-0600",PST:"-0700"},abbreviatedTimeZoneDST:{GMT:"-000",EDT:"-0500",CDT:"-0600",MDT:"-0700",PDT:"-0800"}};
|
||||
Date.getMonthNumberFromName=function(name){var n=Date.CultureInfo.monthNames,m=Date.CultureInfo.abbreviatedMonthNames,s=name.toLowerCase();for(var i=0;i<n.length;i++){if(n[i].toLowerCase()==s||m[i].toLowerCase()==s){return i;}}
|
||||
return-1;};Date.getDayNumberFromName=function(name){var n=Date.CultureInfo.dayNames,m=Date.CultureInfo.abbreviatedDayNames,o=Date.CultureInfo.shortestDayNames,s=name.toLowerCase();for(var i=0;i<n.length;i++){if(n[i].toLowerCase()==s||m[i].toLowerCase()==s){return i;}}
|
||||
@ -101,4 +101,4 @@ return _.any.apply(null,rx);}else{return _get(fx);}};g._formats=g.formats(["yyyy
|
||||
return g._start.call({},s);};}());Date._parse=Date.parse;Date.parse=function(s){var r=null;if(!s){return null;}
|
||||
try{r=Date.Grammar.start.call({},s);}catch(e){return null;}
|
||||
return((r[1].length===0)?r[0]:null);};Date.getParseFunction=function(fx){var fn=Date.Grammar.formats(fx);return function(s){var r=null;try{r=fn.call({},s);}catch(e){return null;}
|
||||
return((r[1].length===0)?r[0]:null);};};Date.parseExact=function(s,fx){return Date.getParseFunction(fx)(s);};
|
||||
return((r[1].length===0)?r[0]:null);};};Date.parseExact=function(s,fx){return Date.getParseFunction(fx)(s);};
|
||||
|
||||
428
resources/viewer/jquery_scrollTo.js
vendored
428
resources/viewer/jquery_scrollTo.js
vendored
@ -1,215 +1,215 @@
|
||||
/**
|
||||
* jQuery.ScrollTo
|
||||
* Copyright (c) 2007-2009 Ariel Flesler - aflesler(at)gmail(dot)com | http://flesler.blogspot.com
|
||||
* Dual licensed under MIT and GPL.
|
||||
* Date: 5/25/2009
|
||||
*
|
||||
* @projectDescription Easy element scrolling using jQuery.
|
||||
* http://flesler.blogspot.com/2007/10/jqueryscrollto.html
|
||||
* Works with jQuery +1.2.6. Tested on FF 2/3, IE 6/7/8, Opera 9.5/6, Safari 3, Chrome 1 on WinXP.
|
||||
*
|
||||
* @author Ariel Flesler
|
||||
* @version 1.4.2
|
||||
*
|
||||
* @id jQuery.scrollTo
|
||||
* @id jQuery.fn.scrollTo
|
||||
* @param {String, Number, DOMElement, jQuery, Object} target Where to scroll the matched elements.
|
||||
* The different options for target are:
|
||||
* - A number position (will be applied to all axes).
|
||||
* - A string position ('44', '100px', '+=90', etc ) will be applied to all axes
|
||||
* - A jQuery/DOM element ( logically, child of the element to scroll )
|
||||
* - A string selector, that will be relative to the element to scroll ( 'li:eq(2)', etc )
|
||||
* - A hash { top:x, left:y }, x and y can be any kind of number/string like above.
|
||||
* - A percentage of the container's dimension/s, for example: 50% to go to the middle.
|
||||
* - The string 'max' for go-to-end.
|
||||
* @param {Number} duration The OVERALL length of the animation, this argument can be the settings object instead.
|
||||
* @param {Object,Function} settings Optional set of settings or the onAfter callback.
|
||||
* @option {String} axis Which axis must be scrolled, use 'x', 'y', 'xy' or 'yx'.
|
||||
* @option {Number} duration The OVERALL length of the animation.
|
||||
* @option {String} easing The easing method for the animation.
|
||||
* @option {Boolean} margin If true, the margin of the target element will be deducted from the final position.
|
||||
* @option {Object, Number} offset Add/deduct from the end position. One number for both axes or { top:x, left:y }.
|
||||
* @option {Object, Number} over Add/deduct the height/width multiplied by 'over', can be { top:x, left:y } when using both axes.
|
||||
* @option {Boolean} queue If true, and both axis are given, the 2nd axis will only be animated after the first one ends.
|
||||
* @option {Function} onAfter Function to be called after the scrolling ends.
|
||||
* @option {Function} onAfterFirst If queuing is activated, this function will be called after the first scrolling ends.
|
||||
* @return {jQuery} Returns the same jQuery object, for chaining.
|
||||
*
|
||||
* @desc Scroll to a fixed position
|
||||
* @example $('div').scrollTo( 340 );
|
||||
*
|
||||
* @desc Scroll relatively to the actual position
|
||||
* @example $('div').scrollTo( '+=340px', { axis:'y' } );
|
||||
*
|
||||
* @dec Scroll using a selector (relative to the scrolled element)
|
||||
* @example $('div').scrollTo( 'p.paragraph:eq(2)', 500, { easing:'swing', queue:true, axis:'xy' } );
|
||||
*
|
||||
* @ Scroll to a DOM element (same for jQuery object)
|
||||
* @example var second_child = document.getElementById('container').firstChild.nextSibling;
|
||||
* $('#container').scrollTo( second_child, { duration:500, axis:'x', onAfter:function(){
|
||||
* alert('scrolled!!');
|
||||
* }});
|
||||
*
|
||||
* @desc Scroll on both axes, to different values
|
||||
* @example $('div').scrollTo( { top: 300, left:'+=200' }, { axis:'xy', offset:-20 } );
|
||||
*/
|
||||
;(function( $ ){
|
||||
|
||||
var $scrollTo = $.scrollTo = function( target, duration, settings ){
|
||||
$(window).scrollTo( target, duration, settings );
|
||||
};
|
||||
|
||||
$scrollTo.defaults = {
|
||||
axis:'xy',
|
||||
duration: parseFloat($.fn.jquery) >= 1.3 ? 0 : 1
|
||||
};
|
||||
|
||||
// Returns the element that needs to be animated to scroll the window.
|
||||
// Kept for backwards compatibility (specially for localScroll & serialScroll)
|
||||
$scrollTo.window = function( scope ){
|
||||
return $(window)._scrollable();
|
||||
};
|
||||
|
||||
// Hack, hack, hack :)
|
||||
// Returns the real elements to scroll (supports window/iframes, documents and regular nodes)
|
||||
$.fn._scrollable = function(){
|
||||
return this.map(function(){
|
||||
var elem = this,
|
||||
isWin = !elem.nodeName || $.inArray( elem.nodeName.toLowerCase(), ['iframe','#document','html','body'] ) != -1;
|
||||
|
||||
if( !isWin )
|
||||
return elem;
|
||||
|
||||
var doc = (elem.contentWindow || elem).document || elem.ownerDocument || elem;
|
||||
|
||||
return $.browser.safari || doc.compatMode == 'BackCompat' ?
|
||||
doc.body :
|
||||
doc.documentElement;
|
||||
});
|
||||
};
|
||||
|
||||
$.fn.scrollTo = function( target, duration, settings ){
|
||||
if( typeof duration == 'object' ){
|
||||
settings = duration;
|
||||
duration = 0;
|
||||
}
|
||||
if( typeof settings == 'function' )
|
||||
settings = { onAfter:settings };
|
||||
|
||||
if( target == 'max' )
|
||||
target = 9e9;
|
||||
|
||||
settings = $.extend( {}, $scrollTo.defaults, settings );
|
||||
// Speed is still recognized for backwards compatibility
|
||||
duration = duration || settings.speed || settings.duration;
|
||||
// Make sure the settings are given right
|
||||
settings.queue = settings.queue && settings.axis.length > 1;
|
||||
|
||||
if( settings.queue )
|
||||
// Let's keep the overall duration
|
||||
duration /= 2;
|
||||
settings.offset = both( settings.offset );
|
||||
settings.over = both( settings.over );
|
||||
|
||||
return this._scrollable().each(function(){
|
||||
var elem = this,
|
||||
$elem = $(elem),
|
||||
targ = target, toff, attr = {},
|
||||
win = $elem.is('html,body');
|
||||
|
||||
switch( typeof targ ){
|
||||
// A number will pass the regex
|
||||
case 'number':
|
||||
case 'string':
|
||||
if( /^([+-]=)?\d+(\.\d+)?(px|%)?$/.test(targ) ){
|
||||
targ = both( targ );
|
||||
// We are done
|
||||
break;
|
||||
}
|
||||
// Relative selector, no break!
|
||||
targ = $(targ,this);
|
||||
case 'object':
|
||||
// DOMElement / jQuery
|
||||
if( targ.is || targ.style )
|
||||
// Get the real position of the target
|
||||
toff = (targ = $(targ)).offset();
|
||||
}
|
||||
$.each( settings.axis.split(''), function( i, axis ){
|
||||
var Pos = axis == 'x' ? 'Left' : 'Top',
|
||||
pos = Pos.toLowerCase(),
|
||||
key = 'scroll' + Pos,
|
||||
old = elem[key],
|
||||
max = $scrollTo.max(elem, axis);
|
||||
|
||||
if( toff ){// jQuery / DOMElement
|
||||
attr[key] = toff[pos] + ( win ? 0 : old - $elem.offset()[pos] );
|
||||
|
||||
// If it's a dom element, reduce the margin
|
||||
if( settings.margin ){
|
||||
attr[key] -= parseInt(targ.css('margin'+Pos)) || 0;
|
||||
attr[key] -= parseInt(targ.css('border'+Pos+'Width')) || 0;
|
||||
}
|
||||
|
||||
attr[key] += settings.offset[pos] || 0;
|
||||
|
||||
if( settings.over[pos] )
|
||||
// Scroll to a fraction of its width/height
|
||||
attr[key] += targ[axis=='x'?'width':'height']() * settings.over[pos];
|
||||
}else{
|
||||
var val = targ[pos];
|
||||
// Handle percentage values
|
||||
attr[key] = val.slice && val.slice(-1) == '%' ?
|
||||
parseFloat(val) / 100 * max
|
||||
: val;
|
||||
}
|
||||
|
||||
// Number or 'number'
|
||||
if( /^\d+$/.test(attr[key]) )
|
||||
// Check the limits
|
||||
attr[key] = attr[key] <= 0 ? 0 : Math.min( attr[key], max );
|
||||
|
||||
// Queueing axes
|
||||
if( !i && settings.queue ){
|
||||
// Don't waste time animating, if there's no need.
|
||||
if( old != attr[key] )
|
||||
// Intermediate animation
|
||||
animate( settings.onAfterFirst );
|
||||
// Don't animate this axis again in the next iteration.
|
||||
delete attr[key];
|
||||
}
|
||||
});
|
||||
|
||||
animate( settings.onAfter );
|
||||
|
||||
function animate( callback ){
|
||||
$elem.animate( attr, duration, settings.easing, callback && function(){
|
||||
callback.call(this, target, settings);
|
||||
});
|
||||
};
|
||||
|
||||
}).end();
|
||||
};
|
||||
|
||||
// Max scrolling position, works on quirks mode
|
||||
// It only fails (not too badly) on IE, quirks mode.
|
||||
$scrollTo.max = function( elem, axis ){
|
||||
var Dim = axis == 'x' ? 'Width' : 'Height',
|
||||
scroll = 'scroll'+Dim;
|
||||
|
||||
if( !$(elem).is('html,body') )
|
||||
return elem[scroll] - $(elem)[Dim.toLowerCase()]();
|
||||
|
||||
var size = 'client' + Dim,
|
||||
html = elem.ownerDocument.documentElement,
|
||||
body = elem.ownerDocument.body;
|
||||
|
||||
return Math.max( html[scroll], body[scroll] )
|
||||
- Math.min( html[size] , body[size] );
|
||||
|
||||
};
|
||||
|
||||
function both( val ){
|
||||
return typeof val == 'object' ? val : { top:val, left:val };
|
||||
};
|
||||
|
||||
/**
|
||||
* jQuery.ScrollTo
|
||||
* Copyright (c) 2007-2009 Ariel Flesler - aflesler(at)gmail(dot)com | http://flesler.blogspot.com
|
||||
* Dual licensed under MIT and GPL.
|
||||
* Date: 5/25/2009
|
||||
*
|
||||
* @projectDescription Easy element scrolling using jQuery.
|
||||
* http://flesler.blogspot.com/2007/10/jqueryscrollto.html
|
||||
* Works with jQuery +1.2.6. Tested on FF 2/3, IE 6/7/8, Opera 9.5/6, Safari 3, Chrome 1 on WinXP.
|
||||
*
|
||||
* @author Ariel Flesler
|
||||
* @version 1.4.2
|
||||
*
|
||||
* @id jQuery.scrollTo
|
||||
* @id jQuery.fn.scrollTo
|
||||
* @param {String, Number, DOMElement, jQuery, Object} target Where to scroll the matched elements.
|
||||
* The different options for target are:
|
||||
* - A number position (will be applied to all axes).
|
||||
* - A string position ('44', '100px', '+=90', etc ) will be applied to all axes
|
||||
* - A jQuery/DOM element ( logically, child of the element to scroll )
|
||||
* - A string selector, that will be relative to the element to scroll ( 'li:eq(2)', etc )
|
||||
* - A hash { top:x, left:y }, x and y can be any kind of number/string like above.
|
||||
* - A percentage of the container's dimension/s, for example: 50% to go to the middle.
|
||||
* - The string 'max' for go-to-end.
|
||||
* @param {Number} duration The OVERALL length of the animation, this argument can be the settings object instead.
|
||||
* @param {Object,Function} settings Optional set of settings or the onAfter callback.
|
||||
* @option {String} axis Which axis must be scrolled, use 'x', 'y', 'xy' or 'yx'.
|
||||
* @option {Number} duration The OVERALL length of the animation.
|
||||
* @option {String} easing The easing method for the animation.
|
||||
* @option {Boolean} margin If true, the margin of the target element will be deducted from the final position.
|
||||
* @option {Object, Number} offset Add/deduct from the end position. One number for both axes or { top:x, left:y }.
|
||||
* @option {Object, Number} over Add/deduct the height/width multiplied by 'over', can be { top:x, left:y } when using both axes.
|
||||
* @option {Boolean} queue If true, and both axis are given, the 2nd axis will only be animated after the first one ends.
|
||||
* @option {Function} onAfter Function to be called after the scrolling ends.
|
||||
* @option {Function} onAfterFirst If queuing is activated, this function will be called after the first scrolling ends.
|
||||
* @return {jQuery} Returns the same jQuery object, for chaining.
|
||||
*
|
||||
* @desc Scroll to a fixed position
|
||||
* @example $('div').scrollTo( 340 );
|
||||
*
|
||||
* @desc Scroll relatively to the actual position
|
||||
* @example $('div').scrollTo( '+=340px', { axis:'y' } );
|
||||
*
|
||||
* @dec Scroll using a selector (relative to the scrolled element)
|
||||
* @example $('div').scrollTo( 'p.paragraph:eq(2)', 500, { easing:'swing', queue:true, axis:'xy' } );
|
||||
*
|
||||
* @ Scroll to a DOM element (same for jQuery object)
|
||||
* @example var second_child = document.getElementById('container').firstChild.nextSibling;
|
||||
* $('#container').scrollTo( second_child, { duration:500, axis:'x', onAfter:function(){
|
||||
* alert('scrolled!!');
|
||||
* }});
|
||||
*
|
||||
* @desc Scroll on both axes, to different values
|
||||
* @example $('div').scrollTo( { top: 300, left:'+=200' }, { axis:'xy', offset:-20 } );
|
||||
*/
|
||||
;(function( $ ){
|
||||
|
||||
var $scrollTo = $.scrollTo = function( target, duration, settings ){
|
||||
$(window).scrollTo( target, duration, settings );
|
||||
};
|
||||
|
||||
$scrollTo.defaults = {
|
||||
axis:'xy',
|
||||
duration: parseFloat($.fn.jquery) >= 1.3 ? 0 : 1
|
||||
};
|
||||
|
||||
// Returns the element that needs to be animated to scroll the window.
|
||||
// Kept for backwards compatibility (specially for localScroll & serialScroll)
|
||||
$scrollTo.window = function( scope ){
|
||||
return $(window)._scrollable();
|
||||
};
|
||||
|
||||
// Hack, hack, hack :)
|
||||
// Returns the real elements to scroll (supports window/iframes, documents and regular nodes)
|
||||
$.fn._scrollable = function(){
|
||||
return this.map(function(){
|
||||
var elem = this,
|
||||
isWin = !elem.nodeName || $.inArray( elem.nodeName.toLowerCase(), ['iframe','#document','html','body'] ) != -1;
|
||||
|
||||
if( !isWin )
|
||||
return elem;
|
||||
|
||||
var doc = (elem.contentWindow || elem).document || elem.ownerDocument || elem;
|
||||
|
||||
return $.browser.safari || doc.compatMode == 'BackCompat' ?
|
||||
doc.body :
|
||||
doc.documentElement;
|
||||
});
|
||||
};
|
||||
|
||||
$.fn.scrollTo = function( target, duration, settings ){
|
||||
if( typeof duration == 'object' ){
|
||||
settings = duration;
|
||||
duration = 0;
|
||||
}
|
||||
if( typeof settings == 'function' )
|
||||
settings = { onAfter:settings };
|
||||
|
||||
if( target == 'max' )
|
||||
target = 9e9;
|
||||
|
||||
settings = $.extend( {}, $scrollTo.defaults, settings );
|
||||
// Speed is still recognized for backwards compatibility
|
||||
duration = duration || settings.speed || settings.duration;
|
||||
// Make sure the settings are given right
|
||||
settings.queue = settings.queue && settings.axis.length > 1;
|
||||
|
||||
if( settings.queue )
|
||||
// Let's keep the overall duration
|
||||
duration /= 2;
|
||||
settings.offset = both( settings.offset );
|
||||
settings.over = both( settings.over );
|
||||
|
||||
return this._scrollable().each(function(){
|
||||
var elem = this,
|
||||
$elem = $(elem),
|
||||
targ = target, toff, attr = {},
|
||||
win = $elem.is('html,body');
|
||||
|
||||
switch( typeof targ ){
|
||||
// A number will pass the regex
|
||||
case 'number':
|
||||
case 'string':
|
||||
if( /^([+-]=)?\d+(\.\d+)?(px|%)?$/.test(targ) ){
|
||||
targ = both( targ );
|
||||
// We are done
|
||||
break;
|
||||
}
|
||||
// Relative selector, no break!
|
||||
targ = $(targ,this);
|
||||
case 'object':
|
||||
// DOMElement / jQuery
|
||||
if( targ.is || targ.style )
|
||||
// Get the real position of the target
|
||||
toff = (targ = $(targ)).offset();
|
||||
}
|
||||
$.each( settings.axis.split(''), function( i, axis ){
|
||||
var Pos = axis == 'x' ? 'Left' : 'Top',
|
||||
pos = Pos.toLowerCase(),
|
||||
key = 'scroll' + Pos,
|
||||
old = elem[key],
|
||||
max = $scrollTo.max(elem, axis);
|
||||
|
||||
if( toff ){// jQuery / DOMElement
|
||||
attr[key] = toff[pos] + ( win ? 0 : old - $elem.offset()[pos] );
|
||||
|
||||
// If it's a dom element, reduce the margin
|
||||
if( settings.margin ){
|
||||
attr[key] -= parseInt(targ.css('margin'+Pos)) || 0;
|
||||
attr[key] -= parseInt(targ.css('border'+Pos+'Width')) || 0;
|
||||
}
|
||||
|
||||
attr[key] += settings.offset[pos] || 0;
|
||||
|
||||
if( settings.over[pos] )
|
||||
// Scroll to a fraction of its width/height
|
||||
attr[key] += targ[axis=='x'?'width':'height']() * settings.over[pos];
|
||||
}else{
|
||||
var val = targ[pos];
|
||||
// Handle percentage values
|
||||
attr[key] = val.slice && val.slice(-1) == '%' ?
|
||||
parseFloat(val) / 100 * max
|
||||
: val;
|
||||
}
|
||||
|
||||
// Number or 'number'
|
||||
if( /^\d+$/.test(attr[key]) )
|
||||
// Check the limits
|
||||
attr[key] = attr[key] <= 0 ? 0 : Math.min( attr[key], max );
|
||||
|
||||
// Queueing axes
|
||||
if( !i && settings.queue ){
|
||||
// Don't waste time animating, if there's no need.
|
||||
if( old != attr[key] )
|
||||
// Intermediate animation
|
||||
animate( settings.onAfterFirst );
|
||||
// Don't animate this axis again in the next iteration.
|
||||
delete attr[key];
|
||||
}
|
||||
});
|
||||
|
||||
animate( settings.onAfter );
|
||||
|
||||
function animate( callback ){
|
||||
$elem.animate( attr, duration, settings.easing, callback && function(){
|
||||
callback.call(this, target, settings);
|
||||
});
|
||||
};
|
||||
|
||||
}).end();
|
||||
};
|
||||
|
||||
// Max scrolling position, works on quirks mode
|
||||
// It only fails (not too badly) on IE, quirks mode.
|
||||
$scrollTo.max = function( elem, axis ){
|
||||
var Dim = axis == 'x' ? 'Width' : 'Height',
|
||||
scroll = 'scroll'+Dim;
|
||||
|
||||
if( !$(elem).is('html,body') )
|
||||
return elem[scroll] - $(elem)[Dim.toLowerCase()]();
|
||||
|
||||
var size = 'client' + Dim,
|
||||
html = elem.ownerDocument.documentElement,
|
||||
body = elem.ownerDocument.body;
|
||||
|
||||
return Math.max( html[scroll], body[scroll] )
|
||||
- Math.min( html[size] , body[size] );
|
||||
|
||||
};
|
||||
|
||||
function both( val ){
|
||||
return typeof val == 'object' ? val : { top:val, left:val };
|
||||
};
|
||||
|
||||
})( jQuery );
|
||||
@ -1,67 +1,67 @@
|
||||
__license__ = 'GPL 3'
|
||||
__copyright__ = '2010, sengian <sengian1@gmail.com>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import re, htmlentitydefs
|
||||
from future_builtins import map
|
||||
|
||||
_ascii_pat = None
|
||||
|
||||
def clean_ascii_chars(txt, charlist=None):
|
||||
r'''
|
||||
Remove ASCII control chars.
|
||||
This is all control chars except \t, \n and \r
|
||||
'''
|
||||
if not txt:
|
||||
return ''
|
||||
global _ascii_pat
|
||||
if _ascii_pat is None:
|
||||
chars = set(xrange(32))
|
||||
chars.add(127)
|
||||
for x in (9, 10, 13):
|
||||
chars.remove(x)
|
||||
_ascii_pat = re.compile(u'|'.join(map(unichr, chars)))
|
||||
|
||||
if charlist is None:
|
||||
pat = _ascii_pat
|
||||
else:
|
||||
pat = re.compile(u'|'.join(map(unichr, charlist)))
|
||||
return pat.sub('', txt)
|
||||
|
||||
def allowed(x):
|
||||
x = ord(x)
|
||||
return (x != 127 and (31 < x < 0xd7ff or x in (9, 10, 13))) or (0xe000 < x < 0xfffd) or (0x10000 < x < 0x10ffff)
|
||||
|
||||
def clean_xml_chars(unicode_string):
|
||||
return u''.join(filter(allowed, unicode_string))
|
||||
|
||||
|
||||
# Fredrik Lundh: http://effbot.org/zone/re-sub.htm#unescape-html
|
||||
# Removes HTML or XML character references and entities from a text string.
|
||||
#
|
||||
# @param text The HTML (or XML) source text.
|
||||
# @return The plain text, as a Unicode string, if necessary.
|
||||
|
||||
def unescape(text, rm=False, rchar=u''):
|
||||
def fixup(m, rm=rm, rchar=rchar):
|
||||
text = m.group(0)
|
||||
if text[:2] == "&#":
|
||||
# character reference
|
||||
try:
|
||||
if text[:3] == "&#x":
|
||||
return unichr(int(text[3:-1], 16))
|
||||
else:
|
||||
return unichr(int(text[2:-1]))
|
||||
except ValueError:
|
||||
pass
|
||||
else:
|
||||
# named entity
|
||||
try:
|
||||
text = unichr(htmlentitydefs.name2codepoint[text[1:-1]])
|
||||
except KeyError:
|
||||
pass
|
||||
if rm:
|
||||
return rchar # replace by char
|
||||
return text # leave as is
|
||||
return re.sub("&#?\w+;", fixup, text)
|
||||
|
||||
__license__ = 'GPL 3'
|
||||
__copyright__ = '2010, sengian <sengian1@gmail.com>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import re, htmlentitydefs
|
||||
from future_builtins import map
|
||||
|
||||
_ascii_pat = None
|
||||
|
||||
def clean_ascii_chars(txt, charlist=None):
|
||||
r'''
|
||||
Remove ASCII control chars.
|
||||
This is all control chars except \t, \n and \r
|
||||
'''
|
||||
if not txt:
|
||||
return ''
|
||||
global _ascii_pat
|
||||
if _ascii_pat is None:
|
||||
chars = set(xrange(32))
|
||||
chars.add(127)
|
||||
for x in (9, 10, 13):
|
||||
chars.remove(x)
|
||||
_ascii_pat = re.compile(u'|'.join(map(unichr, chars)))
|
||||
|
||||
if charlist is None:
|
||||
pat = _ascii_pat
|
||||
else:
|
||||
pat = re.compile(u'|'.join(map(unichr, charlist)))
|
||||
return pat.sub('', txt)
|
||||
|
||||
def allowed(x):
|
||||
x = ord(x)
|
||||
return (x != 127 and (31 < x < 0xd7ff or x in (9, 10, 13))) or (0xe000 < x < 0xfffd) or (0x10000 < x < 0x10ffff)
|
||||
|
||||
def clean_xml_chars(unicode_string):
|
||||
return u''.join(filter(allowed, unicode_string))
|
||||
|
||||
|
||||
# Fredrik Lundh: http://effbot.org/zone/re-sub.htm#unescape-html
|
||||
# Removes HTML or XML character references and entities from a text string.
|
||||
#
|
||||
# @param text The HTML (or XML) source text.
|
||||
# @return The plain text, as a Unicode string, if necessary.
|
||||
|
||||
def unescape(text, rm=False, rchar=u''):
|
||||
def fixup(m, rm=rm, rchar=rchar):
|
||||
text = m.group(0)
|
||||
if text[:2] == "&#":
|
||||
# character reference
|
||||
try:
|
||||
if text[:3] == "&#x":
|
||||
return unichr(int(text[3:-1], 16))
|
||||
else:
|
||||
return unichr(int(text[2:-1]))
|
||||
except ValueError:
|
||||
pass
|
||||
else:
|
||||
# named entity
|
||||
try:
|
||||
text = unichr(htmlentitydefs.name2codepoint[text[1:-1]])
|
||||
except KeyError:
|
||||
pass
|
||||
if rm:
|
||||
return rchar # replace by char
|
||||
return text # leave as is
|
||||
return re.sub("&#?\w+;", fixup, text)
|
||||
|
||||
|
||||
@ -1,25 +1,25 @@
|
||||
Copyright (c) 2004-2011, CherryPy Team (team@cherrypy.org)
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without modification,
|
||||
are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above copyright notice,
|
||||
this list of conditions and the following disclaimer in the documentation
|
||||
and/or other materials provided with the distribution.
|
||||
* Neither the name of the CherryPy Team nor the names of its contributors
|
||||
may be used to endorse or promote products derived from this software
|
||||
without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
||||
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
|
||||
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
||||
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
||||
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
||||
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
Copyright (c) 2004-2011, CherryPy Team (team@cherrypy.org)
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without modification,
|
||||
are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above copyright notice,
|
||||
this list of conditions and the following disclaimer in the documentation
|
||||
and/or other materials provided with the distribution.
|
||||
* Neither the name of the CherryPy Team nor the names of its contributors
|
||||
may be used to endorse or promote products derived from this software
|
||||
without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
||||
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
|
||||
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
||||
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
||||
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
||||
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
@ -1,175 +1,175 @@
|
||||
from lxml import etree
|
||||
from html5lib.treebuilders.etree import tag_regexp
|
||||
|
||||
from gettext import gettext
|
||||
_ = gettext
|
||||
|
||||
import _base
|
||||
|
||||
from html5lib.constants import voidElements
|
||||
from html5lib import ihatexml
|
||||
|
||||
class Root(object):
|
||||
def __init__(self, et):
|
||||
self.elementtree = et
|
||||
self.children = []
|
||||
if et.docinfo.internalDTD:
|
||||
self.children.append(Doctype(self, et.docinfo.root_name,
|
||||
et.docinfo.public_id,
|
||||
et.docinfo.system_url))
|
||||
root = et.getroot()
|
||||
node = root
|
||||
|
||||
while node.getprevious() is not None:
|
||||
node = node.getprevious()
|
||||
while node is not None:
|
||||
self.children.append(node)
|
||||
node = node.getnext()
|
||||
|
||||
self.text = None
|
||||
self.tail = None
|
||||
|
||||
def __getitem__(self, key):
|
||||
return self.children[key]
|
||||
|
||||
def getnext(self):
|
||||
return None
|
||||
|
||||
def __len__(self):
|
||||
return 1
|
||||
|
||||
class Doctype(object):
|
||||
def __init__(self, root_node, name, public_id, system_id):
|
||||
self.root_node = root_node
|
||||
self.name = name
|
||||
self.public_id = public_id
|
||||
self.system_id = system_id
|
||||
|
||||
self.text = None
|
||||
self.tail = None
|
||||
|
||||
def getnext(self):
|
||||
return self.root_node.children[1]
|
||||
|
||||
class FragmentRoot(Root):
|
||||
def __init__(self, children):
|
||||
self.children = [FragmentWrapper(self, child) for child in children]
|
||||
self.text = self.tail = None
|
||||
|
||||
def getnext(self):
|
||||
return None
|
||||
|
||||
class FragmentWrapper(object):
|
||||
def __init__(self, fragment_root, obj):
|
||||
self.root_node = fragment_root
|
||||
self.obj = obj
|
||||
if hasattr(self.obj, 'text'):
|
||||
self.text = self.obj.text
|
||||
else:
|
||||
self.text = None
|
||||
if hasattr(self.obj, 'tail'):
|
||||
self.tail = self.obj.tail
|
||||
else:
|
||||
self.tail = None
|
||||
self.isstring = isinstance(obj, basestring)
|
||||
|
||||
def __getattr__(self, name):
|
||||
return getattr(self.obj, name)
|
||||
|
||||
def getnext(self):
|
||||
siblings = self.root_node.children
|
||||
idx = siblings.index(self)
|
||||
if idx < len(siblings) - 1:
|
||||
return siblings[idx + 1]
|
||||
else:
|
||||
return None
|
||||
|
||||
def __getitem__(self, key):
|
||||
return self.obj[key]
|
||||
|
||||
def __nonzero__(self):
|
||||
return bool(self.obj)
|
||||
|
||||
def getparent(self):
|
||||
return None
|
||||
|
||||
def __str__(self):
|
||||
return str(self.obj)
|
||||
|
||||
def __len__(self):
|
||||
return len(self.obj)
|
||||
|
||||
|
||||
class TreeWalker(_base.NonRecursiveTreeWalker):
|
||||
def __init__(self, tree):
|
||||
if hasattr(tree, "getroot"):
|
||||
tree = Root(tree)
|
||||
elif isinstance(tree, list):
|
||||
tree = FragmentRoot(tree)
|
||||
_base.NonRecursiveTreeWalker.__init__(self, tree)
|
||||
self.filter = ihatexml.InfosetFilter()
|
||||
def getNodeDetails(self, node):
|
||||
if isinstance(node, tuple): # Text node
|
||||
node, key = node
|
||||
assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
|
||||
return _base.TEXT, getattr(node, key)
|
||||
|
||||
elif isinstance(node, Root):
|
||||
return (_base.DOCUMENT,)
|
||||
|
||||
elif isinstance(node, Doctype):
|
||||
return _base.DOCTYPE, node.name, node.public_id, node.system_id
|
||||
|
||||
elif isinstance(node, FragmentWrapper) and node.isstring:
|
||||
return _base.TEXT, node
|
||||
|
||||
elif node.tag == etree.Comment:
|
||||
return _base.COMMENT, node.text
|
||||
|
||||
else:
|
||||
#This is assumed to be an ordinary element
|
||||
match = tag_regexp.match(node.tag)
|
||||
if match:
|
||||
namespace, tag = match.groups()
|
||||
else:
|
||||
namespace = None
|
||||
tag = node.tag
|
||||
return (_base.ELEMENT, namespace, self.filter.fromXmlName(tag),
|
||||
[(self.filter.fromXmlName(name), value) for
|
||||
name,value in node.attrib.iteritems()],
|
||||
len(node) > 0 or node.text)
|
||||
|
||||
def getFirstChild(self, node):
|
||||
assert not isinstance(node, tuple), _("Text nodes have no children")
|
||||
|
||||
assert len(node) or node.text, "Node has no children"
|
||||
if node.text:
|
||||
return (node, "text")
|
||||
else:
|
||||
return node[0]
|
||||
|
||||
def getNextSibling(self, node):
|
||||
if isinstance(node, tuple): # Text node
|
||||
node, key = node
|
||||
assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
|
||||
if key == "text":
|
||||
# XXX: we cannot use a "bool(node) and node[0] or None" construct here
|
||||
# because node[0] might evaluate to False if it has no child element
|
||||
if len(node):
|
||||
return node[0]
|
||||
else:
|
||||
return None
|
||||
else: # tail
|
||||
return node.getnext()
|
||||
|
||||
return node.tail and (node, "tail") or node.getnext()
|
||||
|
||||
def getParentNode(self, node):
|
||||
if isinstance(node, tuple): # Text node
|
||||
node, key = node
|
||||
assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
|
||||
if key == "text":
|
||||
return node
|
||||
# else: fallback to "normal" processing
|
||||
|
||||
return node.getparent()
|
||||
from lxml import etree
|
||||
from html5lib.treebuilders.etree import tag_regexp
|
||||
|
||||
from gettext import gettext
|
||||
_ = gettext
|
||||
|
||||
import _base
|
||||
|
||||
from html5lib.constants import voidElements
|
||||
from html5lib import ihatexml
|
||||
|
||||
class Root(object):
|
||||
def __init__(self, et):
|
||||
self.elementtree = et
|
||||
self.children = []
|
||||
if et.docinfo.internalDTD:
|
||||
self.children.append(Doctype(self, et.docinfo.root_name,
|
||||
et.docinfo.public_id,
|
||||
et.docinfo.system_url))
|
||||
root = et.getroot()
|
||||
node = root
|
||||
|
||||
while node.getprevious() is not None:
|
||||
node = node.getprevious()
|
||||
while node is not None:
|
||||
self.children.append(node)
|
||||
node = node.getnext()
|
||||
|
||||
self.text = None
|
||||
self.tail = None
|
||||
|
||||
def __getitem__(self, key):
|
||||
return self.children[key]
|
||||
|
||||
def getnext(self):
|
||||
return None
|
||||
|
||||
def __len__(self):
|
||||
return 1
|
||||
|
||||
class Doctype(object):
|
||||
def __init__(self, root_node, name, public_id, system_id):
|
||||
self.root_node = root_node
|
||||
self.name = name
|
||||
self.public_id = public_id
|
||||
self.system_id = system_id
|
||||
|
||||
self.text = None
|
||||
self.tail = None
|
||||
|
||||
def getnext(self):
|
||||
return self.root_node.children[1]
|
||||
|
||||
class FragmentRoot(Root):
|
||||
def __init__(self, children):
|
||||
self.children = [FragmentWrapper(self, child) for child in children]
|
||||
self.text = self.tail = None
|
||||
|
||||
def getnext(self):
|
||||
return None
|
||||
|
||||
class FragmentWrapper(object):
|
||||
def __init__(self, fragment_root, obj):
|
||||
self.root_node = fragment_root
|
||||
self.obj = obj
|
||||
if hasattr(self.obj, 'text'):
|
||||
self.text = self.obj.text
|
||||
else:
|
||||
self.text = None
|
||||
if hasattr(self.obj, 'tail'):
|
||||
self.tail = self.obj.tail
|
||||
else:
|
||||
self.tail = None
|
||||
self.isstring = isinstance(obj, basestring)
|
||||
|
||||
def __getattr__(self, name):
|
||||
return getattr(self.obj, name)
|
||||
|
||||
def getnext(self):
|
||||
siblings = self.root_node.children
|
||||
idx = siblings.index(self)
|
||||
if idx < len(siblings) - 1:
|
||||
return siblings[idx + 1]
|
||||
else:
|
||||
return None
|
||||
|
||||
def __getitem__(self, key):
|
||||
return self.obj[key]
|
||||
|
||||
def __nonzero__(self):
|
||||
return bool(self.obj)
|
||||
|
||||
def getparent(self):
|
||||
return None
|
||||
|
||||
def __str__(self):
|
||||
return str(self.obj)
|
||||
|
||||
def __len__(self):
|
||||
return len(self.obj)
|
||||
|
||||
|
||||
class TreeWalker(_base.NonRecursiveTreeWalker):
|
||||
def __init__(self, tree):
|
||||
if hasattr(tree, "getroot"):
|
||||
tree = Root(tree)
|
||||
elif isinstance(tree, list):
|
||||
tree = FragmentRoot(tree)
|
||||
_base.NonRecursiveTreeWalker.__init__(self, tree)
|
||||
self.filter = ihatexml.InfosetFilter()
|
||||
def getNodeDetails(self, node):
|
||||
if isinstance(node, tuple): # Text node
|
||||
node, key = node
|
||||
assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
|
||||
return _base.TEXT, getattr(node, key)
|
||||
|
||||
elif isinstance(node, Root):
|
||||
return (_base.DOCUMENT,)
|
||||
|
||||
elif isinstance(node, Doctype):
|
||||
return _base.DOCTYPE, node.name, node.public_id, node.system_id
|
||||
|
||||
elif isinstance(node, FragmentWrapper) and node.isstring:
|
||||
return _base.TEXT, node
|
||||
|
||||
elif node.tag == etree.Comment:
|
||||
return _base.COMMENT, node.text
|
||||
|
||||
else:
|
||||
#This is assumed to be an ordinary element
|
||||
match = tag_regexp.match(node.tag)
|
||||
if match:
|
||||
namespace, tag = match.groups()
|
||||
else:
|
||||
namespace = None
|
||||
tag = node.tag
|
||||
return (_base.ELEMENT, namespace, self.filter.fromXmlName(tag),
|
||||
[(self.filter.fromXmlName(name), value) for
|
||||
name,value in node.attrib.iteritems()],
|
||||
len(node) > 0 or node.text)
|
||||
|
||||
def getFirstChild(self, node):
|
||||
assert not isinstance(node, tuple), _("Text nodes have no children")
|
||||
|
||||
assert len(node) or node.text, "Node has no children"
|
||||
if node.text:
|
||||
return (node, "text")
|
||||
else:
|
||||
return node[0]
|
||||
|
||||
def getNextSibling(self, node):
|
||||
if isinstance(node, tuple): # Text node
|
||||
node, key = node
|
||||
assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
|
||||
if key == "text":
|
||||
# XXX: we cannot use a "bool(node) and node[0] or None" construct here
|
||||
# because node[0] might evaluate to False if it has no child element
|
||||
if len(node):
|
||||
return node[0]
|
||||
else:
|
||||
return None
|
||||
else: # tail
|
||||
return node.getnext()
|
||||
|
||||
return node.tail and (node, "tail") or node.getnext()
|
||||
|
||||
def getParentNode(self, node):
|
||||
if isinstance(node, tuple): # Text node
|
||||
node, key = node
|
||||
assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
|
||||
if key == "text":
|
||||
return node
|
||||
# else: fallback to "normal" processing
|
||||
|
||||
return node.getparent()
|
||||
|
||||
@ -1,81 +1,81 @@
|
||||
ACKNOWLEDGMENTS
|
||||
|
||||
* RAR text compression algorithm is based on Dmitry Shkarin PPMII
|
||||
and Dmitry Subbotin carryless rangecoder public domain source code.
|
||||
You may find it in ftp.elf.stuba.sk/pub/pc/pack.
|
||||
|
||||
* RAR encryption includes parts of code from Szymon Stefanek
|
||||
and Brian Gladman AES implementations also as Steve Reid SHA-1 source.
|
||||
|
||||
---------------------------------------------------------------------------
|
||||
Copyright (c) 2002, Dr Brian Gladman < >, Worcester, UK.
|
||||
All rights reserved.
|
||||
|
||||
LICENSE TERMS
|
||||
|
||||
The free distribution and use of this software in both source and binary
|
||||
form is allowed (with or without changes) provided that:
|
||||
|
||||
1. distributions of this source code include the above copyright
|
||||
notice, this list of conditions and the following disclaimer;
|
||||
|
||||
2. distributions in binary form include the above copyright
|
||||
notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other associated materials;
|
||||
|
||||
3. the copyright holder's name is not used to endorse products
|
||||
built using this software without specific written permission.
|
||||
|
||||
ALTERNATIVELY, provided that this notice is retained in full, this product
|
||||
may be distributed under the terms of the GNU General Public License (GPL),
|
||||
in which case the provisions of the GPL apply INSTEAD OF those given above.
|
||||
|
||||
DISCLAIMER
|
||||
|
||||
This software is provided 'as is' with no explicit or implied warranties
|
||||
in respect of its properties, including, but not limited to, correctness
|
||||
and/or fitness for purpose.
|
||||
---------------------------------------------------------------------------
|
||||
|
||||
Source code of this package also as other cryptographic technology
|
||||
and computing project related links are available on Brian Gladman's
|
||||
web site: http://www.gladman.me.uk
|
||||
|
||||
* RAR uses CRC32 function based on Intel Slicing-by-8 algorithm.
|
||||
Original Intel Slicing-by-8 code is available here:
|
||||
|
||||
http://sourceforge.net/projects/slicing-by-8/
|
||||
|
||||
Original Intel Slicing-by-8 code is licensed under BSD License
|
||||
available at http://www.opensource.org/licenses/bsd-license.html
|
||||
|
||||
Copyright (c) 2004-2006 Intel Corporation.
|
||||
All Rights Reserved
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions
|
||||
are met:
|
||||
|
||||
Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with
|
||||
the distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
|
||||
FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
|
||||
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
||||
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
|
||||
OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
||||
SUCH DAMAGE.
|
||||
|
||||
* Useful hints provided by Alexander Khoroshev and Bulat Ziganshin allowed
|
||||
to significantly improve RAR compression and speed.
|
||||
ACKNOWLEDGMENTS
|
||||
|
||||
* RAR text compression algorithm is based on Dmitry Shkarin PPMII
|
||||
and Dmitry Subbotin carryless rangecoder public domain source code.
|
||||
You may find it in ftp.elf.stuba.sk/pub/pc/pack.
|
||||
|
||||
* RAR encryption includes parts of code from Szymon Stefanek
|
||||
and Brian Gladman AES implementations also as Steve Reid SHA-1 source.
|
||||
|
||||
---------------------------------------------------------------------------
|
||||
Copyright (c) 2002, Dr Brian Gladman < >, Worcester, UK.
|
||||
All rights reserved.
|
||||
|
||||
LICENSE TERMS
|
||||
|
||||
The free distribution and use of this software in both source and binary
|
||||
form is allowed (with or without changes) provided that:
|
||||
|
||||
1. distributions of this source code include the above copyright
|
||||
notice, this list of conditions and the following disclaimer;
|
||||
|
||||
2. distributions in binary form include the above copyright
|
||||
notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other associated materials;
|
||||
|
||||
3. the copyright holder's name is not used to endorse products
|
||||
built using this software without specific written permission.
|
||||
|
||||
ALTERNATIVELY, provided that this notice is retained in full, this product
|
||||
may be distributed under the terms of the GNU General Public License (GPL),
|
||||
in which case the provisions of the GPL apply INSTEAD OF those given above.
|
||||
|
||||
DISCLAIMER
|
||||
|
||||
This software is provided 'as is' with no explicit or implied warranties
|
||||
in respect of its properties, including, but not limited to, correctness
|
||||
and/or fitness for purpose.
|
||||
---------------------------------------------------------------------------
|
||||
|
||||
Source code of this package also as other cryptographic technology
|
||||
and computing project related links are available on Brian Gladman's
|
||||
web site: http://www.gladman.me.uk
|
||||
|
||||
* RAR uses CRC32 function based on Intel Slicing-by-8 algorithm.
|
||||
Original Intel Slicing-by-8 code is available here:
|
||||
|
||||
http://sourceforge.net/projects/slicing-by-8/
|
||||
|
||||
Original Intel Slicing-by-8 code is licensed under BSD License
|
||||
available at http://www.opensource.org/licenses/bsd-license.html
|
||||
|
||||
Copyright (c) 2004-2006 Intel Corporation.
|
||||
All Rights Reserved
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions
|
||||
are met:
|
||||
|
||||
Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with
|
||||
the distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
|
||||
FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
|
||||
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
||||
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
|
||||
OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
||||
SUCH DAMAGE.
|
||||
|
||||
* Useful hints provided by Alexander Khoroshev and Bulat Ziganshin allowed
|
||||
to significantly improve RAR compression and speed.
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user