Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Birmingham Post

Browse Source
This commit is contained in:
Kovid Goyal 2013-02-02 18:25:22 +05:30
parent 2a16dba0d6
commit 20c98b34a3
1 changed files with 2 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
recipes/birmingham_post.recipe
View File

@ -14,7 +14,7 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
remove_empty_feeds = True remove_empty_feeds = True
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
#auto_cleanup = True auto_cleanup = True
language = 'en_GB' language = 'en_GB'
cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg' cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg'
@ -23,7 +23,7 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
def get_cover_url(self): def get_cover_url(self):
soup = self.index_to_soup('http://www.birminghampost.net') soup = self.index_to_soup('http://www.birminghampost.net')
# look for the block containing the sun button and url # look for the block containing the sun button and url
cov = soup.find(attrs={'height' : re.compile('3'), 'alt' : re.compile('Birmingham Post')}) cov = soup.find(attrs={'height' : re.compile('3'), 'alt' : re.compile('Post')})
print print
print '%%%%%%%%%%%%%%%',cov print '%%%%%%%%%%%%%%%',cov
print print
@ -43,20 +43,7 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
return cover_url return cover_url
keep_only_tags = [
dict(attrs={'id' : 'article-header'}),
#dict(name='h1',attrs={'id' : 'article-header'}),
dict(attrs={'class':['article-meta-author','article-meta-date','article main','art-o art-align-center otm-1 ']}),
dict(name='div',attrs={'class' : 'article-image full'}),
dict(attrs={'clas' : 'art-o art-align-center otm-1 '}),
dict(name='div',attrs={'class' : 'article main'}),
#dict(name='p')
#dict(attrs={'id' : 'three-col'})
]
remove_tags = [
# dict(name='div',attrs={'class' : 'span-33 last header-links'})
]
feeds = [ feeds = [
#(u'News',u'http://www.birminghampost.net/news/rss.xml'), #(u'News',u'http://www.birminghampost.net/news/rss.xml'),
(u'West Mids. News', u'http://www.birminghampost.net/news/west-midlands-news/rss.xml'), (u'West Mids. News', u'http://www.birminghampost.net/news/west-midlands-news/rss.xml'),
@ -65,9 +52,3 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
(u'Bloggs & Comments',u'http://www.birminghampost.net/comment/rss.xml') (u'Bloggs & Comments',u'http://www.birminghampost.net/comment/rss.xml')
] ]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;text-align:center;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''