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

Fixed People/US Magazine mashup

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-13 00:11:43 -06:00
parent cf13881d08
commit 636496f1dd
1 changed files with 3 additions and 69 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
recipes/people_us_mashup.recipe
View File

@ -14,54 +14,10 @@ class PeopleMag(BasicNewsRecipe):
use_embedded_content = False
oldest_article = 2
max_articles_per_feed = 50
use_embedded_content = False
extra_css = '''
h1{font-family:verdana,arial,helvetica,sans-serif; font-size: large;}
h2{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
.body-content{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
.byline {font-size: small; color: #666666; font-style:italic; }
.lastline {font-size: small; color: #666666; font-style:italic;}
.contact {font-size: small; color: #666666;}
.contact p {font-size: small; color: #666666;}
.photoCaption { font-family:verdana,arial,helvetica,sans-serif; font-size:x-small;}
.photoCredit{ font-family:verdana,arial,helvetica,sans-serif; font-size:x-small; color:#666666;}
.article_timestamp{font-size:x-small; color:#666666;}
a {font-family:verdana,arial,helvetica,sans-serif; font-size: x-small;}
'''
keep_only_tags = [
dict(name='div', attrs={'class': 'panel_news_article_main'}),
dict(name='div', attrs={'class':'article_content'}),
dict(name='div', attrs={'class': 'headline'}),
dict(name='div', attrs={'class': 'post'}),
dict(name='div', attrs={'class': 'packageheadlines'}),
dict(name='div', attrs={'class': 'snap_preview'}),
dict(name='div', attrs={'id': 'articlebody'})
]
remove_tags = [
dict(name='div', attrs={'class':'share_comments'}),
dict(name='p', attrs={'class':'twitter_facebook'}),
dict(name='div', attrs={'class':'share_comments_bottom'}),
dict(name='h2', attrs={'id':'related_content'}),
dict(name='div', attrs={'class':'next_article'}),
dict(name='div', attrs={'class':'prev_article'}),
dict(name='ul', attrs={'id':'sharebar'}),
dict(name='div', attrs={'class':'sharelinkcont'}),
dict(name='div', attrs={'class':'categories'}),
dict(name='ul', attrs={'class':'categories'}),
dict(name='div', attrs={'class':'related_content'}),
dict(name='div', attrs={'id':'promo'}),
dict(name='div', attrs={'class':'linksWrapper'}),
dict(name='p', attrs={'class':'tag tvnews'}),
dict(name='p', attrs={'class':'tag movienews'}),
dict(name='p', attrs={'class':'tag musicnews'}),
dict(name='p', attrs={'class':'tag couples'}),
dict(name='p', attrs={'class':'tag gooddeeds'}),
dict(name='p', attrs={'class':'tag weddings'}),
dict(name='p', attrs={'class':'tag health'})
]
no_stylesheets = True
auto_cleanup = True
feeds = [
@ -69,26 +25,4 @@ class PeopleMag(BasicNewsRecipe):
('US Headlines', 'http://www.usmagazine.com/celebrity_news/rss')
]
def get_article_url(self, article):
ans = article.link
try:
self.log('Looking for full story link in', ans)
soup = self.index_to_soup(ans)
x = soup.find(text="View All")
if x is not None:
ans = ans + '?viewAll=y'
self.log('Found full story link', ans)
except:
pass
return ans
def postprocess_html(self, soup,first):
for tag in soup.findAll(name='div',attrs={'class':"container_ate_qandatitle"}):
tag.extract()
for tag in soup.findAll(name='br'):
tag.extract()
return soup