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 2015-06-27 23:45:50 +05:30
parent c61c330e6d
commit e27bff1942
1 changed files with 28 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
recipes/daily_express.recipe
View File

@ -1,19 +1,19 @@
# vim:fileencoding=UTF-8 # vim:fileencoding=UTF-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre import browser
class AdvancedUserRecipe1390132023(BasicNewsRecipe): class AdvancedUserRecipe1390132023(BasicNewsRecipe):
title = u'Daily Express' title = u'Daily Express'
language = 'en_GB'
__author__ = 'Dave Asbury' __author__ = 'Dave Asbury'
# 21.11.14 written due to website changes # 27.6.15 using feed43 as rss feeds dead
oldest_article = 1 # feed 43 string = <div {*}<a href="{%}"{*}<h4>{%}</h4>
oldest_article = 1.5
max_articles_per_feed = 10 max_articles_per_feed = 10
compress_news_images = True compress_news_images = True
compress_news_images_max_size = 30 compress_news_images_max_size = 20
ignore_duplicate_articles = {'title', 'url'} ignore_duplicate_articles = {'title', 'url'}
masthead_url = 'http://cdn.images.dailyexpress.co.uk/img/page/express_logo.png' masthead_url = 'http://cdn.images.dailyexpress.co.uk/img/page/express_logo.png'
auto_cleanup_keep = '//*[@class="author"]|//section[@class="photo changeSpace"]' auto_cleanup_keep = '//*[@class="author"]|//section[@class="photo changeSpace"]'
@ -21,30 +21,43 @@ class AdvancedUserRecipe1390132023(BasicNewsRecipe):
no_stylesheets = False no_stylesheets = False
preprocess_regexps = [ preprocess_regexps = [
(re.compile(r'\| [\w].+?\| [\w].+?\| Daily Express', re.IGNORECASE | re.DOTALL), lambda match: ''), (re.compile(r'\| [\w].+?\| [\w].+?\| Daily Express', re.IGNORECASE | re.DOTALL), lambda match: ''),
]
]
feeds = [ feeds = [
(u'UK News', u'http://www.express.co.uk/posts/rss/1/uk'), (u'UK News', u'http://feed43.com/3460616116055543.xml'),
(u'World News',u'http://www.express.co.uk/posts/rss/78/world'), # http://feeds.feedburner.com/daily-express-uk-news'),#http://www.express.co.uk/posts/rss/1/uk'),
(u'Finance',u'http://www.express.co.uk/posts/rss/21/finance'), (u'World News',u'http://feed43.com/5650105317448722.xml'),
(u'Sport',u'http://www.express.co.uk/posts/rss/65/sport'), # http://www.express.co.uk/posts/rss/78/world'),
(u'Entertainment',u'http://www.express.co.uk/posts/rss/18/entertainment'), (u'Showbiz News',u'http://feed43.com/2564008080442425.xml'),
(u'Lifestyle',u'http://www.express.co.uk/posts/rss/8/life&style'), (u'Finance',u'http://feed43.com/8636615325246501.xml'),
(u'Fun',u'http://www.express.co.uk/posts/rss/110/fun'), # 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'),
] ]
def get_cover_url(self): def get_cover_url(self):
print '============Cover ================='
print
soup = self.index_to_soup('http://www.express.co.uk/ourpaper/') 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 = soup.find(attrs={'src' : re.compile('http://cdn.images.express.co.uk/img/covers/')})
cov=str(cov) cov=str(cov)
print '^^^^^^^', cov
cov2 = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov) cov2 = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov)
cov=str(cov2) cov=str(cov2)
cov=cov[2:len(cov)-2] cov=cov[2:len(cov)-2]
print '&&&&&&&&',cov,'***'
# cover_url=cov # cover_url=cov
br = self.get_browser() br = browser()
br.set_handle_redirect(False) br.set_handle_redirect(False)
try: try:
br.open_novisit(cov) br.open_novisit(cov)