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 Chicago Tribune multipage articles

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-28 09:16:25 -06:00
parent 8d4d33253f
commit 7445edba1b
1 changed files with 18 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/chicago_tribune.recipe
View File

@ -8,21 +8,25 @@ from calibre.web.feeds.news import BasicNewsRecipe
class ChicagoTribune(BasicNewsRecipe): class ChicagoTribune(BasicNewsRecipe):
title = 'Chicago Tribune' title = 'Chicago Tribune'
__author__ = 'Kovid Goyal and Sujata Raman' __author__ = 'Kovid Goyal and Sujata Raman, a.peter'
description = 'Politics, local and business news from Chicago' description = 'Politics, local and business news from Chicago'
language = 'en' language = 'en'
version = 2
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
recursions = 1
keep_only_tags = [dict(name='div', attrs={'class':["story","entry-asset asset hentry"]}), keep_only_tags = [dict(name='div', attrs={'class':["story","entry-asset asset hentry"]}),
dict(name='div', attrs={'id':["pagebody","story","maincontentcontainer"]}), dict(name='div', attrs={'id':["pagebody","story","maincontentcontainer"]}),
] ]
remove_tags_after = [ {'class':['photo_article',]} ] remove_tags_after = [{'class':['photo_article',]}]
remove_tags = [{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet","relatedrailcontent","div-wrapper","beta","atp-comments","footer"]}, match_regexps = [r'page=[0-9]+']
{'class':["clearfix","relatedTitle","articleRelates module","asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground","clearfix fullSpan brownBackground","curvedContent"]},
remove_tags = [{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet","relatedrailcontent","div-wrapper","beta","atp-comments","footer",'gallery-subcontent','subFooter']},
{'class':["clearfix","relatedTitle","articleRelates module","asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground","clearfix fullSpan brownBackground","curvedContent",'nextgen-share-tools','outbrainTools', 'google-ad-story-bottom']},
dict(name='font',attrs={'id':["cr-other-headlines"]})] dict(name='font',attrs={'id':["cr-other-headlines"]})]
extra_css = ''' extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
@ -76,8 +80,12 @@ class ChicagoTribune(BasicNewsRecipe):
print article.get('feedburner_origlink', article.get('guid', article.get('link'))) print article.get('feedburner_origlink', article.get('guid', article.get('link')))
return article.get('feedburner_origlink', article.get('guid', article.get('link'))) return article.get('feedburner_origlink', article.get('guid', article.get('link')))
def postprocess_html(self, soup, first_fetch): def postprocess_html(self, soup, first_fetch):
# Remove the navigation bar. It was kept until now to be able to follow
# the links to further pages. But now we don't need them anymore.
for nav in soup.findAll(attrs={'class':['toppaginate','article-nav clearfix']}):
nav.extract()
for t in soup.findAll(['table', 'tr', 'td']): for t in soup.findAll(['table', 'tr', 'td']):
t.name = 'div' t.name = 'div'
@ -88,4 +96,3 @@ class ChicagoTribune(BasicNewsRecipe):
return soup return soup