Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2026-04-01 06:42:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
Kovid Goyal 2011-12-27 14:55:30 +05:30
parent 44ed7440f4
commit 78755c8640
1 changed files with 16 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
recipes/daily_mirror.recipe
View File

@ -5,7 +5,7 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
description = 'News as provide by The Daily Mirror -UK'
__author__ = 'Dave Asbury'
# last updated 30/10/11
# last updated 26/12/11
language = 'en_GB'
cover_url = 'http://yookeo.com/screens/m/i/mirror.co.uk.jpg'
@ -13,30 +13,22 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
masthead_url = 'http://www.nmauk.co.uk/nma/images/daily_mirror.gif'
oldest_article = 2
max_articles_per_feed = 30
oldest_article = 1
max_articles_per_feed = 20
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
extra_css = '''
body{ text-align: justify; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal;}
'''
keep_only_tags = [
dict(name='div',attrs={'id' : 'body-content'})
]
remove_tags_after = [dict (name='div',attrs={'class' : 'related'})]
auto_cleanup = True
remove_tags = [
dict(name='div',attrs={'id' : ['sidebar','menu','search-box','roffers-top']}),
dict(name='div',attrs={'class' :['inline-ad span-16 last','article-resize','related','list teasers']}),
dict(attrs={'class' : ['channellink','article-tags','replace','append-html']}),
dict(name='div',attrs={'class' : 'span-12 last sl-others addthis_toolbox addthis_default_style'})
dict(name='title'),
dict(name='div',attrs={'class' : ['inline-ad span-16 last','caption']}),
]
preprocess_regexps = [
(re.compile(r'<dl class="q-search">.*?</dl>', re.IGNORECASE | re.DOTALL), lambda match: '')]
(re.compile(r'- mirror.co.uk', re.IGNORECASE | re.DOTALL), lambda match: '')]
preprocess_regexps = [
(re.compile(r'Advertisement >>', re.IGNORECASE | re.DOTALL), lambda match: '')]
feeds = [
@ -53,5 +45,10 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
,(u'Travel','http://www.mirror.co.uk/advice/travel/rss.xml')
# example of commented out feed not needed ,(u'Travel','http://www.mirror.co.uk/advice/travel/rss.xml')
]
extra_css = '''
body{ text-align: justify; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal;}
h1{ font-size:18px;}
img { display:block}
'''