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

Fix #872945 (Geek and poke small update)

Browse Source
This commit is contained in:
Kovid Goyal 2011-10-13 08:06:05 +05:30
parent b6fab126dc
commit dff33cf99b
1 changed files with 22 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
recipes/geek_poke.recipe
View File

@ -1,6 +1,6 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import re import re
from calibre.utils.magick import Image from calibre.utils.magick import Image, create_canvas
class AdvancedUserRecipe1307556816(BasicNewsRecipe): class AdvancedUserRecipe1307556816(BasicNewsRecipe):
title = u'Geek and Poke' title = u'Geek and Poke'
@ -11,7 +11,7 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe):
oldest_article = 31 oldest_article = 31
max_articles_per_feed = 100 max_articles_per_feed = 100
language = u'en' language = u'en'
simultaneous_downloads = 5 simultaneous_downloads = 1
#delay = 1 #delay = 1
timefmt = ' [%a, %d %B, %Y]' timefmt = ' [%a, %d %B, %Y]'
summary_length = -1 summary_length = -1
@ -22,6 +22,7 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
remove_empty_feeds = True remove_empty_feeds = True
publication_type = 'blog' publication_type = 'blog'
masthead_url = None
conversion_options = { conversion_options = {
'comments' : '' 'comments' : ''
,'tags' : category ,'tags' : category
@ -44,28 +45,38 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe):
(r'yimg\.com'), (r'yimg\.com'),
(r'scorecardresearch\.com')] (r'scorecardresearch\.com')]
preprocess_regexps = [(re.compile(r'(<p>(&nbsp;|\s)*</p>|<a[^>]*>Tweet</a>|<a[^>]*>|</a>)', re.DOTALL|re.IGNORECASE),lambda match: ''), preprocess_regexps = [(re.compile(r'(<p>(&nbsp;|\s)*</p>|<a[^>]*>Tweet</a>|<a[^>]*>|</a>|<!--.*?-->|<h2[^>]*>[^<]*</h2>[^<]*)', re.DOTALL|re.IGNORECASE),lambda match: ''),
(re.compile(r'(&nbsp;|\s\s)+\s*', re.DOTALL|re.IGNORECASE),lambda match: ' '), (re.compile(r'(&nbsp;|\s\s)+\s*', re.DOTALL|re.IGNORECASE),lambda match: ' '),
(re.compile(r'<h2[^>]*>([^<]*)</h2>[^>]*(<div[^>]*>)', re.DOTALL|re.IGNORECASE), lambda match: match.group(2) + '<div id="MERRYdate">' + match.group(1) + '</div>'),
(re.compile(r'(<h3[^>]*>)<a[^>]>((?!</a)*)</a></h3>', re.DOTALL|re.IGNORECASE),lambda match: match.group(1) + match.group(2) + '</h3>'), (re.compile(r'(<h3[^>]*>)<a[^>]>((?!</a)*)</a></h3>', re.DOTALL|re.IGNORECASE),lambda match: match.group(1) + match.group(2) + '</h3>'),
(re.compile(r'(<img[^>]*alt="([^"]*)"[^>]*>)', re.DOTALL|re.IGNORECASE),lambda match: match.group(1) + '<br><cite>' + match.group(2) + '</cite>'), (re.compile(r'(<img[^>]*alt="([^"]*)"[^>]*>)', re.DOTALL|re.IGNORECASE),lambda match: '<div id="merryImage"><cite>' + match.group(2) + '</cite><br>' + match.group(1) + '</div>'),
(re.compile(r'<br( /)?>(<br( /)?>)+', re.DOTALL|re.IGNORECASE),lambda match: '<br>'), (re.compile(r'<br( /)?>(<br( /)?>)+', re.DOTALL|re.IGNORECASE),lambda match: '<br>'),
(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')
] ]
extra_css = 'body, h3, p, #MERRYdate, h1, div, span{margin:0px; padding:0px} h3.entry-header{font-size: 0.8em} div.entry-body{font-size: 0.7em} #MERRYdate {font-size: 0.5em}' extra_css = 'body, h3, p, div, span{margin:0px; padding:0px} h3.entry-header{font-size: 0.8em} div.entry-body{font-size: 0.7em}'
def postprocess_html(self, soup, first): def postprocess_html(self, soup, first):
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')): for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
iurl = tag['src'] iurl = tag['src']
img = Image() img = Image()
img.open(iurl) img.open(iurl)
width, height = img.size #width, height = img.size
#print 'img is: ', iurl, 'width is: ', width, 'height is: ', height #print '***img is: ', iurl, '\n****width is: ', width, 'height is: ', height
img.trim(0) img.trim(0)
img.save(iurl) #width, height = img.size
#print '***TRIMMED img width is: ', width, 'height is: ', height
left=0
top=0
border_color='#ffffff'
width, height = img.size width, height = img.size
#print 'img is: ', iurl, 'width is: ', width, 'height is: ', height #print '***retrieved img width is: ', width, 'height is: ', height
height_correction = 1.17
canvas = create_canvas(width, height*height_correction,border_color)
canvas.compose(img, left, top)
#img = canvas
#img.save(iurl)
canvas.save(iurl)
#width, height = canvas.size
#print '***NEW img width is: ', width, 'height is: ', height
return soup return soup
feeds = ['http://feeds.feedburner.com/GeekAndPoke?format=xml'] feeds = ['http://feeds.feedburner.com/GeekAndPoke?format=xml']