Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Sync to trunk.

Browse Source
This commit is contained in:
John Schember 2009-10-08 07:41:42 -04:00
commit bb6ef9ab4d
33 changed files with 409 additions and 236 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
resources/content_server/gui.js
View File

@ -247,7 +247,7 @@ function setup_sorting() {
});
$('table#book_list thead tr td').mouseout(function() {
this.style.backgroundColor = "inherit";
this.style.backgroundColor = "transparent";
});
for (i = 0; i < cmap.length; i++) {

BIN
resources/images/news/toronto_sun.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 630 B

1
setup/extensions.py
View File

@ -102,6 +102,7 @@ extensions = [
libraries=['podofo'],
lib_dirs=[podofo_lib],
inc_dirs=[podofo_inc],
optional=True,
error=podofo_error),
Extension('pictureflow',

15
setup/installer/windows/freeze.py
View File

@ -6,13 +6,15 @@ __docformat__ = 'restructuredtext en'
'''
Freeze app into executable using py2exe.
'''
import sys, os
QT_DIR = 'C:\\Qt\\4.5.2'
LIBUSB_DIR = 'C:\\libusb'
LIBUNRAR = 'C:\\Program Files\\UnrarDLL\\unrar.dll'
IMAGEMAGICK_DIR = 'C:\\ImageMagick'
SW = r'C:\cygwin\home\kovid\sw'
IMAGEMAGICK = os.path.join(SW, 'build', 'ImageMagick-6.5.6',
'VisualMagick', 'bin')
import sys
def fix_module_finder():
# ModuleFinder can't handle runtime changes to __path__, but win32com uses them
@ -186,6 +188,15 @@ class BuildEXE(bc):
for pat in ('*.dll', '*.sys', '*.cat', '*.inf'):
for f in glob.glob(os.path.join(LIBUSB_DIR, pat)):
shutil.copyfile(f, os.path.join(tdir, os.path.basename(f)))
# Copy ImageMagick
for pat in ('*.dll', '*.xml'):
for f in glob.glob(self.j(IMAGEMAGICK, pat)):
ok = True
for ex in ('magick++', 'x11.dll', 'xext.dll'):
if ex in f.lower(): ok = False
if not ok: continue
shutil.copy2(f, self.dll_dir)
print '\tAdding unrar'
shutil.copyfile(LIBUNRAR, os.path.join(PY2EXE_DIR, os.path.basename(LIBUNRAR)))

3
src/calibre/debug.py
View File

@ -190,6 +190,9 @@ def main(args=sys.argv):
elif opts.develop_from is not None:
develop_from(opts.develop_from)
else:
from calibre.utils.config import config_dir
ipydir = os.path.join(config_dir, ('_' if iswindows else '.')+'ipython')
os.environ['IPYTHONDIR'] = ipydir
from IPython.Shell import IPShellEmbed
ipshell = IPShellEmbed()
ipshell()

5
src/calibre/devices/usbms/driver.py
View File

@ -162,6 +162,7 @@ class USBMS(CLI, Device):
@classmethod
def book_from_path(cls, path):
from calibre.ebooks.metadata.meta import path_to_ext
from calibre.ebooks.metadata import MetaInformation
mime = mime_type_ext(path_to_ext(path))
if cls.settings().read_metadata or cls.MUST_READ_METADATA:
@ -171,6 +172,10 @@ class USBMS(CLI, Device):
mi = metadata_from_filename(os.path.basename(path),
re.compile(r'^(?P<title>[ \S]+?)[ _]-[ _](?P<author>[ \S]+?)_+\d+'))
if mi is None:
mi = MetaInformation(os.path.splitext(os.path.basename(path))[0],
[_('Unknown')])
authors = authors_to_string(mi.authors)
book = Book(path, mi.title, authors, mime)

5
src/calibre/ebooks/pdf/fonts.h
View File

@ -4,9 +4,7 @@
*/
#ifndef CALIBRE_REFLOW_FONTS
#define CALIBRE_REFLOW_FONTS
#pragma once
#include <vector>
#include <sstream>
@ -102,4 +100,3 @@ class Fonts : public vector<XMLFont*> {
}
#endif

4
src/calibre/ebooks/pdf/images.h
View File

@ -1,5 +1,4 @@
#ifndef _CALIBRE_REFLOW_IMAGES
#define _CALIBRE_REFLOW_IMAGES
#pragma once
#include <vector>
#include <GfxState.h>
@ -127,4 +126,3 @@ namespace calibre_reflow {
};
*/
}
#endif

5
src/calibre/ebooks/pdf/links.h
View File

@ -5,9 +5,7 @@
#ifndef _CALIBRE_XML_LINKS
#define _CALIBRE_XML_LINKS
#pragma once
#include <vector>
#include <sstream>
@ -65,5 +63,4 @@ class XMLLinks : public vector<XMLLink*> {
}
#endif

4
src/calibre/ebooks/pdf/reflow.h
View File

@ -4,8 +4,7 @@
* Based on pdftohtml from the poppler project.
*/
#ifndef CALIBRE_REFLOW
#define CALIBRE_REFLOW
#pragma once
#define UNICODE
#ifdef _WIN32
@ -248,4 +247,3 @@ class XMLOutputDev : public OutputDev {
void process_link(Link* link);
};
}
#endif

5
src/calibre/ebooks/pdf/utils.h
View File

@ -4,9 +4,7 @@
*/
#ifndef _CALIBRE_REFLOW_UTILS
#define _CALIBRE_REFLOW_UTILS
#pragma once
#include <string>
#include <sstream>
@ -45,4 +43,3 @@ inline string encode_for_xml(const string &sSrc )
}
#endif

4
src/calibre/gui2/pictureflow/pictureflow.h
View File

@ -55,8 +55,7 @@
THE SOFTWARE.
*/
#ifndef PICTUREFLOW_H
#define PICTUREFLOW_H
#pragma once
#include <QWidget>
@ -202,4 +201,3 @@ private:
PictureFlowPrivate* d;
};
#endif // PICTUREFLOW_H

11
src/calibre/trac/plugins/templates/linux.html
View File

@ -112,10 +112,13 @@ sudo python setup.py install
</pre>
Note that if your distribution does not have a
correctly compiled libunrar.so, ${app} will not
support rar files. The calibre_postinstall step
is required for device detection and integration
with your desktop environment.
</p>
support rar files. In order to compile ${app} successfully
poppler headers must include XPdf headers. That is, poppler
must have been configured with --enable-xpdf-headers. Also,
some distributions have buggy libpng headers. See
<a href="https://bugs.launchpad.net/ubuntu/+source/libpng/+bug/218409">here</a>
for example.
</p>
</div>
</td>
</tr>

6
src/calibre/utils/config.py
View File

@ -411,7 +411,11 @@ class Config(ConfigInterface):
if os.path.exists(self.config_file_path):
try:
with ExclusiveFile(self.config_file_path) as f:
src = f.read().decode('utf-8')
try:
src = f.read().decode('utf-8')
except ValueError:
print "Failed to parse", self.config_file_path
traceback.print_exc()
except LockError:
raise IOError('Could not lock config file: %s'%self.config_file_path)
return self.option_set.parse_string(src)

2
src/calibre/utils/ipc/job.py
View File

@ -131,7 +131,7 @@ class BaseJob(object):
@property
def details(self):
return self.log_file.read().decode('utf-8')
return self.log_file.read().decode('utf-8', 'replace')
class ParallelJob(BaseJob):

3
src/calibre/utils/lzx/lzc.h
View File

@ -15,6 +15,9 @@
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#pragma once
typedef struct lz_info lz_info;
typedef int (*get_chars_t)(lz_info *lzi, int n, unsigned char *buf);
typedef int (*output_match_t)(lz_info *lzi, int match_pos, int match_len);

2
src/calibre/utils/lzx/lzxc.h
View File

@ -16,6 +16,8 @@
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#pragma once
#ifdef _MSC_VER
#include "msstdint.h"
#endif

5
src/calibre/utils/lzx/lzxd.h
View File

@ -10,10 +10,10 @@
* For further details, see the file COPYING.LIB distributed with libmspack
*/
#pragma once
#include <sys/types.h>
#ifndef MSPACK_LZX_H
#define MSPACK_LZX_H 1
/* LZX compression / decompression definitions */
@ -166,4 +166,3 @@ extern int lzxd_decompress(struct lzxd_stream *lzx, off_t out_bytes);
*/
void lzxd_free(struct lzxd_stream *lzx);
#endif

5
src/calibre/utils/lzx/lzxmodule.h
View File

@ -3,13 +3,10 @@
*
* Common declarations for Python module C glue code.
*/
#pragma once
#include <Python.h>
#ifndef LZXMODULE_H
#define LZXMODULE_H
extern PyObject *LZXError;
extern PyTypeObject CompressorType;
#endif /* LZXMODULE_H */

4
src/calibre/utils/lzx/mspack.h
View File

@ -115,8 +115,7 @@
* - #MSPACK_ERR_DECRUNCH indicates an error occured during decompression.
*/
#ifndef LIB_MSPACK_H
#define LIB_MSPACK_H 1
#pragma once
#ifdef __cplusplus
extern "C" {
@ -1479,4 +1478,3 @@ struct mskwaj_decompressor {
};
#endif
#endif

11
src/calibre/utils/lzx/msstdint.h
View File

@ -29,17 +29,12 @@
//
///////////////////////////////////////////////////////////////////////////////
#pragma once
#ifndef _MSC_VER // [
#error "Use this header only with Microsoft Visual C++ compilers!"
#endif // _MSC_VER ]
#ifndef _MSC_STDINT_H_ // [
#define _MSC_STDINT_H_
#if _MSC_VER > 1000
#pragma once
#endif
#include <limits.h>
// For Visual Studio 6 in C++ mode wrap <wchar.h> include with 'extern "C++" {}'
@ -228,5 +223,3 @@ typedef uint64_t uintmax_t;
#endif // __STDC_CONSTANT_MACROS ]
#endif // _MSC_STDINT_H_ ]

5
src/calibre/utils/lzx/system.h
View File

@ -7,8 +7,7 @@
* For further details, see the file COPYING.LIB distributed with libmspack
*/
#ifndef MSPACK_SYSTEM_H
#define MSPACK_SYSTEM_H 1
#pragma once
#ifdef _MSC_VER
#define inline
@ -62,5 +61,3 @@ static inline size_t strlen(const char *s) {
return e - s;
}
#endif
#endif

2
src/calibre/utils/msdes/d3des.h
View File

@ -10,6 +10,8 @@
* (GEnie : OUTER; CIS : [71755,204])
*/
#pragma once
#undef D2_DES
#undef D3_DES

2
src/calibre/utils/msdes/spr.h
View File

@ -21,6 +21,8 @@
| URL: http://www.gnu.org/licenses/gpl.html
*/
#pragma once
static unsigned long SP1[64] = {
0x02080800L, 0x00080000L, 0x02000002L, 0x02080802L,
0x02000000L, 0x00080802L, 0x00080002L, 0x02000002L,

2
src/calibre/web/feeds/recipes/__init__.py
View File

@ -6,7 +6,7 @@ Builtin recipes.
'''
recipe_modules = ['recipe_' + r for r in (
'newsweek', 'atlantic', 'economist', 'portfolio', 'the_register',
'usatoday', 'outlook_india', 'bbc', 'greader', 'wsj',
'usatoday', 'bbc', 'greader', 'wsj', #'outlook_india',
'wired', 'globe_and_mail', 'smh', 'espn', 'business_week', 'miami_herald',
'ars_technica', 'upi', 'new_yorker', 'irish_times', 'lanacion',
'discover_magazine', 'scientific_american', 'new_york_review_of_books',

77
src/calibre/web/feeds/recipes/recipe_honoluluadvertiser.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python
# -*- coding: cp1252 -*-
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
@ -10,28 +11,62 @@ from calibre.web.feeds.news import BasicNewsRecipe
class Honoluluadvertiser(BasicNewsRecipe):
title = 'Honolulu Advertiser'
__author__ = 'Darko Miletic'
__author__ = 'Darko Miletic and Sujata Raman'
description = "Latest national and local Hawaii sports news from The Honolulu Advertiser."
publisher = 'Honolulu Advertiser'
category = 'news, Honolulu, Hawaii'
oldest_article = 2
language = 'en'
language = 'en'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
remove_javascript = True
cover_url = 'http://www.honoluluadvertiser.com/graphics/frontpage/frontpage.jpg'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher' , publisher
]
keep_only_tags = [dict(name='td')]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
remove_tags = [dict(name=['object','link'])]
remove_attributes = ['style']
keep_only_tags = [dict(name='div', attrs={'class':["hon_article_top","article-bodytext","hon_article_photo","storyphoto","article"]}),
dict(name='div', attrs={'id':["storycontentleft","article"]})
]
remove_tags = [dict(name=['object','link','embed']),
dict(name='div', attrs={'class':["article-tools","titleBar","invisiblespacer","articleflex-container","hon_newslist","categoryheader","columnframe","subHeadline","poster-container"]}),
dict(name='div', attrs={'align':["right"]}),
dict(name='div', attrs={'id':["pluckcomments"]}),
dict(name='td', attrs={'class':["prepsfacts"]}),
dict(name='img', attrs={'height':["1"]}),
dict(name='img', attrs={'alt':["Advertisement"]}),
dict(name='img', attrs={'src':["/gcicommonfiles/sr/graphics/common/adlabel_horz.gif","/gcicommonfiles/sr/graphics/common/icon_whatsthis.gif",]}),
]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-size:large; color:#000000; }
.hon_article_timestamp{font-family:Arial,Helvetica,sans-serif; font-size:70%; }
.postedStoryDate{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.postedDate{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.credit{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.hon_article_top{font-family:Arial,Helvetica,sans-serif; color:#666666; font-size:30%; font-weight:bold;}
.grayBackground{font-family:Arial,Helvetica,sans-serif; color:#666666; font-size:30%;}
.hon_photocaption{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.photoCaption{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.hon_photocredit{font-family:Arial,Helvetica,sans-serif; font-size:30%; color:#666666;}
.storyphoto{font-family:Arial,Helvetica,sans-serif; font-size:30%; color:#666666;}
.article-bodytext{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
.storycontentleft{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
#article{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
.contentarea{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
.storytext{font-family:Verdana,Arial,Helvetica,sans-serif; font-size:xx-small;}
.storyHeadline{font-family:Arial,Helvetica,sans-serif; font-size:large; color:#000000; font-weight:bold;}
.source{font-family:Arial,Helvetica,sans-serif; color:#333333; font-style: italic; font-weight:bold; }
'''
feeds = [
(u'Breaking news', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS01&MIME=XML' )
@ -43,13 +78,19 @@ class Honoluluadvertiser(BasicNewsRecipe):
]
def preprocess_html(self, soup):
st = soup.find('td')
if st:
st.name = 'div'
for item in soup.findAll(style=True):
del item['style']
mtag = '\n<meta http-equiv="Content-Language" content="en"/>\n'
soup.head.insert(0,mtag)
for tag in soup.findAll(name=['span','table','font']):
tag.name = 'div'
return soup
def print_version(self, url):
ubody, sep, rest = url.rpartition('?source')
root, sep2, article_id = ubody.partition('/article/')
return u'http://www.honoluluadvertiser.com/apps/pbcs.dll/article?AID=/' + article_id + '&template=printart'
# def print_version(self, url):
# ubody, sep, rest = url.rpartition('/-1/')
# root, sep2, article_id = ubody.partition('/article/')
# return u'http://www.honoluluadvertiser.com/apps/pbcs.dll/article?AID=/' + article_id + '&template=printart'

52
src/calibre/web/feeds/recipes/recipe_miami_herald.py
View File

@ -1,4 +1,3 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
@ -10,7 +9,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TheMiamiHerald(BasicNewsRecipe):
title = 'The Miami Herald'
__author__ = 'Darko Miletic'
__author__ = 'Darko Miletic and Sujata Raman'
description = "Miami-Dade and Broward's source for the latest breaking local news on sports, weather, business, jobs, real estate, shopping, health, travel, entertainment, & more."
oldest_article = 1
max_articles_per_feed = 100
@ -22,19 +21,28 @@ class TheMiamiHerald(BasicNewsRecipe):
use_embedded_content = False
encoding = 'cp1252'
remove_javascript = True
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher' , publisher
]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-size:large; color:#1A272F; }
.subheadline{font-family:Arial,Helvetica,sans-serif; font-size:30%; color: #666666;}
#storyBodyContent{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
.byline{font-family:Arial,Helvetica,sans-serif; font-size:30%; color:#58595B; }
.credit_line{font-family:Arial,Helvetica,sans-serif; font-size:30%; color:#58595B; }
.storyPublishDate{font-family:Arial,Helvetica,sans-serif; font-size:30%; color:#666666; }
.shirttail{font-family:Arial,Helvetica,sans-serif; font-size:30%; color:#666666;font-style:italic }
.imageCaption{font-family:Arial,Helvetica,sans-serif; font-size:30%; color:#666666; }
'''
keep_only_tags = [dict(name='div', attrs={'id':['storyBody','storyPhotoContentArea']}),
]
remove_tags = [dict(name=['object','link','embed']),
dict(name='div', attrs={'class':["imageBuyButton","shareLinksArea","storyTools","spill_navigation pagination","circPromoArea","storyTools_footer","storyYahooContentMatch"]}) ,
dict(name='div', attrs={'id':["pluck","mlt","storyAssets"]}) ]
keep_only_tags = [dict(name='div', attrs={'id':'pageContainer'})]
feeds = [
(u'Breaking News' , u'http://www.miamiherald.com/416/index.xml' )
(u'Breaking News' , u'http://www.miamiherald.com/416/index.xml' )
,(u'Miami-Dade' , u'http://www.miamiherald.com/460/index.xml' )
,(u'Broward' , u'http://www.miamiherald.com/467/index.xml' )
,(u'Florida Keys' , u'http://www.miamiherald.com/505/index.xml' )
@ -49,6 +57,26 @@ class TheMiamiHerald(BasicNewsRecipe):
,(u'Environment' , u'http://www.miamiherald.com/573/index.xml' )
]
def print_version(self, url):
return url.replace('/story/','/v-print/story/')
def get_article_url(self, article):
ans = article.get('guid', None)
print ans
try:
self.log('Looking for full story link in', ans)
soup = self.index_to_soup(ans)
x = soup.find(text="Full Story")
if x is not None:
a = x.parent
if a and a.has_key('href'):
ans = 'http://www.miamiherald.com'+a['href']
self.log('Found full story link', ans)
except:
pass
return ans

56
src/calibre/web/feeds/recipes/recipe_moscow_times.py
View File

@ -10,18 +10,64 @@ from calibre.web.feeds.news import BasicNewsRecipe
class Moscowtimes(BasicNewsRecipe):
title = u'The Moscow Times'
__author__ = 'Darko Miletic'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'News from Russia'
language = 'en'
lang = 'en'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
#encoding = 'utf-8'
encoding = 'cp1252'
remove_javascript = True
conversion_options = {
'comment' : description
, 'language' : lang
}
extra_css = '''
h1{ color:#0066B3; font-family: Georgia,serif ; font-size: large}
.article_date{ font-family:Arial,Tahoma,Verdana,Helvetica,sans-serif ; color:#000000; font-size: x-small;}
.autors{color:#999999 ; font-weight: bold ; font-family:Arial,Tahoma,Verdana,Helvetica,sans-serif ; font-size: x-small; }
.photoautors{ color:#999999 ; font-family:Arial,Tahoma,Verdana,Helvetica,sans-serif ; font-size: x-small; }
.text{font-family:Arial,Tahoma,Verdana,Helvetica,sans-serif ; font-size:75%; }
'''
feeds = [
(u'The Moscow Times' , u'http://www.themoscowtimes.com/rss.xml' )
(u'The Moscow Times Top Stories' , u'http://www.themoscowtimes.com/rss/top'),
(u'The Moscow Times Current Issue' , u'http://www.themoscowtimes.com/rss/issue'),
(u'The Moscow Times News' , u'http://www.themoscowtimes.com/rss/news'),
(u'The Moscow Times Business' , u'http://www.themoscowtimes.com/rss/business'),
(u'The Moscow Times Art and Ideas' , u'http://www.themoscowtimes.com/rss/art'),
(u'The Moscow Times Opinion' , u'http://www.themoscowtimes.com/rss/opinion')
]
def print_version(self, url):
return url + '&print=Y'
keep_only_tags = [
dict(name='div', attrs={'class':['newstextblock']})
]
remove_tags = [
dict(name='div', attrs={'class':['photo_nav']})
]
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
soup.head.insert(0,mtag)
return self.adeify_images(soup)
def get_cover_url(self):
href = 'http://www.themoscowtimes.com/pdf/'
soup = self.index_to_soup(href)
div = soup.find('div',attrs={'class':'left'})
a = div.find('a')
print a
if a :
cover_url = a.img['src']
return cover_url

25
src/calibre/web/feeds/recipes/recipe_msdnmag_en.py
View File

@ -18,38 +18,19 @@ class MSDNMagazine_en(BasicNewsRecipe):
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
remove_javascript = True
current_issue = 'http://msdn.microsoft.com/en-us/magazine/default.aspx'
language = 'en'
language = 'en'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
feeds = [(u'Articles', u'http://msdn.microsoft.com/en-us/magazine/rss/default.aspx?z=z&iss=1')]
keep_only_tags = [dict(name='div', attrs={'class':'topic'})]
keep_only_tags = [dict(name='div', attrs={'class':'navpage'})]
remove_tags = [
dict(name=['object','link','base','table'])
,dict(name='div', attrs={'class':'MTPS_CollapsibleRegion'})
]
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.current_issue)
link_item = soup.find('span',attrs={'class':'ContentsImageSpacer'})
if link_item:
imgt = link_item.find('img')
if imgt:
cover_url = imgt['src']
return cover_url
remove_tags_after = dict(name='div', attrs={'class':'navpage'})
def preprocess_html(self, soup):
for item in soup.findAll('div',attrs={'class':['FeatureSmallHead','ColumnTypeSubTitle']}):

30
src/calibre/web/feeds/recipes/recipe_ourdailybread.py
View File

@ -10,10 +10,11 @@ from calibre.web.feeds.news import BasicNewsRecipe
class OurDailyBread(BasicNewsRecipe):
title = 'Our Daily Bread'
__author__ = 'Darko Miletic'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'Religion'
oldest_article = 15
language = 'en'
lang = 'en'
max_articles_per_feed = 100
no_stylesheets = True
@ -30,7 +31,34 @@ class OurDailyBread(BasicNewsRecipe):
keep_only_tags = [dict(name='div', attrs={'class':['altbg','text']})]
remove_tags = [dict(name='div', attrs={'id':['ctl00_cphPrimary_pnlBookCover']}),
dict(name='div', attrs={'class':['devotionalLinks']})
]
extra_css = '''
.text{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
.devotionalTitle{font-family:Arial,Helvetica,sans-serif; font-size:large; font-weight: bold;}
.devotionalDate{font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
.devotionalVerse{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
'''
feeds = [(u'Our Daily Bread', u'http://www.rbc.org/rss.ashx?id=50398')]
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
soup.head.insert(0,mtag)
return self.adeify_images(soup)
def get_cover_url(self):
href = 'http://www.rbc.org/index.aspx'
soup = self.index_to_soup(href)
a = soup.find('a',attrs={'id':'ctl00_hlTodaysDevotionalImage'})
if a :
cover_url = a.img['src']
return cover_url

27
src/calibre/web/feeds/recipes/recipe_straitstimes.py
View File

@ -19,23 +19,19 @@ class StraitsTimes(BasicNewsRecipe):
encoding = 'cp1252'
publisher = 'Singapore Press Holdings Ltd.'
category = 'news, politics, singapore, asia'
language = 'en'
language = 'en'
extra_css = ' .top_headline{font-size: x-large; font-weight: bold} '
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
remove_tags = [dict(name=['object','link','map'])]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
remove_tags = [
dict(name=['object','link'])
,dict(name='table', attrs={'width':'980'})
,dict(name='td' , attrs={'class':'padlrt10'})
]
keep_only_tags = [dict(name='div', attrs={'class':['top_headline','story_text']})]
feeds = [
(u'Singapore' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_singapore.xml' )
@ -52,6 +48,3 @@ class StraitsTimes(BasicNewsRecipe):
del item['style']
return soup
def print_version(self, url):
return url.replace('http://www.straitstimes.com','http://www.straitstimes.com/print')

50
src/calibre/web/feeds/recipes/recipe_toronto_sun.py Normal file
View File

@ -0,0 +1,50 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.torontosun.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class TorontoSun(BasicNewsRecipe):
title = 'Toronto SUN'
__author__ = 'Darko Miletic'
description = 'News from Canada'
publisher = 'Toronto Sun'
category = 'news, politics, Canada'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
language = 'en_CA'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags =[
dict(name='div', attrs={'class':'articleHead'})
,dict(name='div', attrs={'id':'channelContent'})
]
remove_tags = [
dict(name='div',attrs={'class':['leftBox','bottomBox clear','bottomBox','breadCrumb']})
,dict(name=['link','iframe','object'])
,dict(name='a',attrs={'rel':'swap'})
,dict(name='ul',attrs={'class':'tabs dl contentSwap'})
]
remove_tags_after = dict(name='div',attrs={'class':'bottomBox clear'})
feeds = [
(u'News' , u'http://www.torontosun.com/news/rss.xml' )
,(u'Canada' , u'http://www.torontosun.com/news/canada/rss.xml' )
,(u'Columnists' , u'http://www.torontosun.com/news/columnists/rss.xml')
,(u'World' , u'http://www.torontosun.com/news/world/rss.xml' )
,(u'Money' , u'http://www.torontosun.com/money/rss.xml' )
]

1
src/cherrypy/lib/httpauth.py
View File

@ -83,6 +83,7 @@ SUPPORTED_QOP = (AUTH, AUTH_INT)
#
DIGEST_AUTH_ENCODERS = {
MD5: lambda val: md5(val).hexdigest(),
'md5': lambda val:md5(val).hexdigest(),
MD5_SESS: lambda val: md5(val).hexdigest(),
# SHA: lambda val: sha(val).hexdigest(),
}