Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #6950 (Fixed Broken Recipe for Popular Science)

Browse Source
This commit is contained in:
Kovid Goyal 2010-09-25 12:24:59 -06:00
parent b00e241477
commit 4978f616e8
1 changed files with 14 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
resources/recipes/popscience.recipe
View File

@ -1,5 +1,5 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, re
class AdvancedUserRecipe1282101454(BasicNewsRecipe): class AdvancedUserRecipe1282101454(BasicNewsRecipe):
title = 'Popular Science' title = 'Popular Science'
@ -12,38 +12,36 @@ class AdvancedUserRecipe1282101454(BasicNewsRecipe):
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
use_embedded_content = True
masthead_url = 'http://www.raytheon.com/newsroom/rtnwcm/groups/Public/documents/masthead/rtn08_popscidec_masthead.jpg' masthead_url = 'http://www.raytheon.com/newsroom/rtnwcm/groups/Public/documents/masthead/rtn08_popscidec_masthead.jpg'
remove_tags = [dict(name='div', attrs={'id':['toolbar','main_supplements']}),
dict(name='span', attrs={'class':['comments']}),
dict(name='div', attrs={'class':['relatedinfo related-right','node_navigation','content2']}),
dict(name='ul', attrs={'class':['item-list clear-block']})]
feeds = [ feeds = [
('Gadgets', 'http://www.popsci.com/full-feed/gadgets'), ('Gadgets', 'http://www.popsci.com/full-feed/gadgets'),
('Cars', 'http://www.popsci.com/full-feed/cars'), ('Cars', 'http://www.popsci.com/full-feed/cars'),
('Science', 'http://www.popsci.com/full-feed/science'), ('Science', 'http://www.popsci.com/full-feed/science'),
('Technology', 'http://www.popsci.com/full-feed/technology'), ('Technology', 'http://www.popsci.com/full-feed/technology'),
('DIY', 'http://www.popsci.com/full-feed/diy'), ('DIY', 'http://www.popsci.com/full-feed/diy'),
] ]
#The following will get read of the Gallery: links when found #The following will get read of the Gallery: links when found
def preprocess_html(self, soup) : def preprocess_html(self, soup) :
print 'SOUP IS: ', soup print 'SOUP IS: ', soup
weblinks = soup.findAll(['head','h2']) weblinks = soup.findAll(['head','h2'])
if weblinks is not None: if weblinks is not None:
for link in weblinks: for link in weblinks:
if re.search('(Gallery)(:)',str(link)): if re.search('(Gallery)(:)',str(link)):
link.parent.extract() link.parent.extract()
return soup return soup
#----------------------------------------------------------------- #-----------------------------------------------------------------