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 Daily Express

Browse Source
This commit is contained in:
Kovid Goyal 2015-08-02 14:57:54 +05:30
parent db54fbeca0
commit 0715c663f9
1 changed files with 35 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
recipes/daily_express.recipe
View File

@ -1,5 +1,6 @@
# vim:fileencoding=UTF-8
from __future__ import unicode_literals
import re
from calibre.web.feeds.news import BasicNewsRecipe
@ -8,6 +9,7 @@ from calibre import browser
class AdvancedUserRecipe1390132023(BasicNewsRecipe):
title = u'Daily Express'
__author__ = 'Dave Asbury'
# 1.8.15 official feedburner feeds live again
# 27.6.15 using feed43 as rss feeds dead
# feed 43 string = <div {*}<a href="{%}"{*}<h4>{%}</h4>
oldest_article = 1.5
@ -22,40 +24,56 @@ class AdvancedUserRecipe1390132023(BasicNewsRecipe):
preprocess_regexps = [
(re.compile(r'\| [\w].+?\| [\w].+?\| Daily Express', re.IGNORECASE | re.DOTALL), lambda match: ''),
]
feeds = [
(u'UK News', u'http://feed43.com/3460616116055543.xml'),
# http://feeds.feedburner.com/daily-express-uk-news'),#http://www.express.co.uk/posts/rss/1/uk'),
(u'World News',u'http://feed43.com/5650105317448722.xml'),
# http://www.express.co.uk/posts/rss/78/world'),
(u'Showbiz News',u'http://feed43.com/2564008080442425.xml'),
(u'Finance',u'http://feed43.com/8636615325246501.xml'),
# http://www.express.co.uk/posts/rss/21/finance'),
(u'Sport - Boxing',u'http://feed43.com/7570233481503246.xml'),
(u'Sport - Rugby Union',u'http://feed43.com/4235483647118470.xml'),
(u'Sport - Others',u'http://feed43.com/6106345668326737.xml'),
# http://www.express.co.uk/posts/rss/65/sport'),
(u'Entertainment',u'http://feed43.com/8864645080210731.xml'),
# http://www.express.co.uk/posts/rss/18/entertainment'),
(u'Lifestyle',u'http://feed43.com/8705161426770855.xml'),
# http://www.express.co.uk/posts/rss/8/life&style'),
(u'Travel',u'http://feed43.com/6547373884767554.xml'),
]
feeds = [
# (u'UK News', u'http://feed43.com/3460616116055543.xml'),
(u'UK News',u'http://feeds.feedburner.com/daily-express-uk-news'), # http://www.express.co.uk/posts/rss/1/uk'),
(u'World News',u'http://feeds.feedburner.com/daily-express-world-news'),
# (u'World News',u'http://feed43.com/5650105317448722.xml'),
# http://www.express.co.uk/posts/rss/78/world'),
(u'Showbiz News',u'http://feeds.feedburner.com/daily-express-showbiz-news'),
# (u'Showbiz News',u'http://feed43.com/2564008080442425.xml'),
(u'Finance',u'http://feeds.feedburner.com/daily-express-finance-news'),
# (u'Finance',u'http://feed43.com/8636615325246501.xml'),
# http://www.express.co.uk/posts/rss/21/finance'),
# (u'Sport - Boxing',u'http://feed43.com/7570233481503246.xml'),
(u'Sport - Boxing',u'http://feeds.feedburner.com/daily-express-boxing-news'),
(u'Sport - Rugby Union',u'http://feeds.feedburner.com/daily-express-rugby-union-news'),
# (u'Sport - Rugby Union',u'http://feed43.com/4235483647118470.xml'),
# (u'Sport - Others',u'http://feed43.com/6106345668326737.xml'),
(u'Sport - Others',u'http://feeds.feedburner.com/daily-express-other-sport-news'),
# http://www.express.co.uk/posts/rss/65/sport'),
(u'Entertainment',u'http://feeds.feedburner.com/daily-express-entertainment-news'),
# (u'Entertainment',u'http://feed43.com/8864645080210731.xml'),
# http://www.express.co.uk/posts/rss/18/entertainment'),
(u'Lifestyle',u'http://feeds.feedburner.com/daily-express-life-and-style-news'),
# (u'Lifestyle',u'http://feed43.com/8705161426770855.xml'),
# http://www.express.co.uk/posts/rss/8/life&style'),
(u'Travel',u'http://feeds.feedburner.com/daily-express-travel'),
# (u'Travel',u'http://feed43.com/6547373884767554.xml'),
]
# starsons code
def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for feed in feeds:
for article in feed.articles[:]:
print 'article.title is: ', article.title
if 'WATCH:' in article.title.upper():
feed.articles.remove(article)
return feeds
def get_cover_url(self):
print '============Cover ================='
print
soup = self.index_to_soup('http://www.express.co.uk/ourpaper/')
cov = soup.find(attrs={'src' : re.compile('http://cdn.images.express.co.uk/img/covers/')})
cov=str(cov)
print '^^^^^^^', cov
cov2 = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov)
cov=str(cov2)
cov=cov[2:len(cov)-2]
print '&&&&&&&&',cov,'***'
# cover_url=cov
br = browser()
br.set_handle_redirect(False)