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

Update Daily Express

Browse Source
This commit is contained in:
Kovid Goyal 2013-09-10 08:00:42 +05:30
parent c390b2e0ec
commit 778edcbab8
1 changed files with 30 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
recipes/daily_express.recipe
View File

@ -1,10 +1,9 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1376229553(BasicNewsRecipe):
title = u'Daily Express'
__author__ = 'Dave Asbury'
language = 'en_GB'
# 13-08-17 remove quoted text from article
# 9-9-13 added article author and now use (re.compile(r'>[\w].+? News<'
encoding = 'utf-8'
remove_empty_feeds = True
#remove_javascript = True
@ -15,33 +14,49 @@ class AdvancedUserRecipe1376229553(BasicNewsRecipe):
compress_news_images = True
compress_news_images_max_size = 30
ignore_duplicate_articles = {'title', 'url'}
masthead_url = 'http://cdn.images.dailyexpress.co.uk/img/page/express_logo.png'
preprocess_regexps = [
(re.compile(r'widget', re.IGNORECASE | re.DOTALL), lambda match: ''),
(re.compile(r'Related articles', re.IGNORECASE | re.DOTALL), lambda match: ''),
(re.compile(r'Add Your Comment<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
(re.compile(r'>More [\w].+?<', re.IGNORECASE), lambda match: '><'),
(re.compile(r'>[\w].+? News<', re.IGNORECASE), lambda match: '><'),
#(re.compile(r'Health News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
#(re.compile(r'Car News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
#(re.compile(r'TV & Radio News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
#(re.compile(r'Food & Recipe News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
#(re.compile(r'More City & Business<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
#(re.compile(r'Travel News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
#(re.compile(r'Garden News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
#(re.compile(r'Fashion & Beauty News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
#(re.compile(r'More Personal Finance<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
#(re.compile(r'<h3>More UK</h3>', re.IGNORECASE | re.DOTALL), lambda match: ''),
]
remove_tags = [
dict(attrs={'class' : 'quote'}),
dict(attrs={'class' : 'author'}),
#dict(attrs={'class' : 'author'}),
dict(name='footer'),
dict(attrs={'id' : 'header_addons'}),
dict(attrs={'class' : 'hoverException'}),
dict(name='_li'),dict(name='li'),
dict(attrs={'class' : 'box related-articles clear'}),
dict(attrs={'class' : 'news-list'}),
dict(attrs={'class' : 'sponsored-section'}),
dict(attrs={'class' : 'pull-quote on-right'}),
dict(attrs={'class' : 'pull-quote on-left'}),
]
keep_only_tags = [
dict(name='h1'),
dict(attrs={'class' : 'publish-info'}),
# dict(name='h3'),
#dict(name='section',attrs={'class' : 'photo'}),
#dict(name='section',attrs={'class' : 'text-description'}),
dict(attrs={'class' : 'clearfix hR new-style'}),
dict(name='h3', limit=2),
dict(attrs={'class' : 'clearfix hR new-style'}),
]
preprocess_regexps = [
(re.compile(r'widget', re.IGNORECASE | re.DOTALL), lambda match: '')]
preprocess_regexps = [
(re.compile(r'<h3>More UK</h3>', re.IGNORECASE | re.DOTALL), lambda match: '')]
feeds = [(u'UK News', u'http://www.express.co.uk/posts/rss/1/uk'),
(u'World News',u'http://www.express.co.uk/posts/rss/78/world'),
(u'Finance',u'http://www.express.co.uk/posts/rss/21/finance'),