Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-05 08:40:13 -04:00
Code Issues Packages Projects Releases Wiki Activity

Updated The Sun

Browse Source
This commit is contained in:
Kovid Goyal 2012-07-26 10:14:12 +05:30
parent 98cb8d88d1
commit fff1892577
1 changed files with 22 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
recipes/the_sun.recipe
View File

@ -1,4 +1,4 @@
import re, random
import random
from calibre import browser
from calibre.web.feeds.recipes import BasicNewsRecipe
@ -8,45 +8,43 @@ class AdvancedUserRecipe1325006965(BasicNewsRecipe):
title = u'The Sun UK'
description = 'Articles from The Sun tabloid UK'
__author__ = 'Dave Asbury'
# last updated 15/7/12
# last updated 25/7/12
language = 'en_GB'
oldest_article = 1
max_articles_per_feed = 15
max_articles_per_feed = 12
remove_empty_feeds = True
no_stylesheets = True
masthead_url = 'http://www.thesun.co.uk/sol/img/global/Sun-logo.gif'
encoding = 'UTF-8'
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
#preprocess_regexps = [
# (re.compile(r'<div class="foot-copyright".*?</div>', re.IGNORECASE | re.DOTALL), lambda match: '')]
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;}
'''
preprocess_regexps = [
(re.compile(r'<div class="foot-copyright".*?</div>', re.IGNORECASE | re.DOTALL), lambda match: '')]
'''
keep_only_tags = [
dict(name='h1'),dict(name='h2',attrs={'class' : ['large','large centered','medium centered','medium']}),dict(name='h3'),
dict(name='div',attrs={'class' : 'text-center'}),
dict(name='div',attrs={'id' : 'bodyText'})
# dict(name='p')
]
remove_tags=[
#dict(name='head'),
dict(attrs={'class' : ['mystery-meat-link','ltbx-container','ltbx-var ltbx-hbxpn','ltbx-var ltbx-nav-loop','ltbx-var ltbx-url']}),
dict(name='div',attrs={'class' : 'cf'}),
dict(attrs={'title' : 'download flash'}),
dict(attrs={'style' : 'padding: 5px'})
dict(name='div',attrs={'class' : 'intro'}),
dict(name='h3'),
dict(name='div',attrs={'id' : 'articlebody'}),
#dict(attrs={'class' : ['right_col_branding','related-stories','mystery-meat-link','ltbx-container','ltbx-var ltbx-hbxpn','ltbx-var ltbx-nav-loop','ltbx-var ltbx-url']}),
# dict(name='div',attrs={'class' : 'cf'}),
# dict(attrs={'title' : 'download flash'}),
# dict(attrs={'style' : 'padding: 5px'})
]
remove_tags_after = [dict(id='bodyText')]
remove_tags=[
dict(name='li'),
dict(attrs={'class' : 'grid-4 right-hand-column'}),
]
feeds = [
(u'News', u'http://www.thesun.co.uk/sol/homepage/news/rss'),