Code:
import re
from calibre.web.feeds.news import BasicNewsRecipe
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
max_articles_per_feed = 10
compress_news_images = True
compress_news_images_max_size = 20
ignore_duplicate_articles = {'title', 'url'}
masthead_url = 'http://cdn.images.dailyexpress.co.uk/img/page/express_logo.png'
auto_cleanup_keep = '//*[@class="author"]|//section[@class="photo changeSpace"]'
auto_cleanup = True
no_stylesheets = False
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'),
(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)
try:
br.open_novisit(cov)
cover_url = cov
except:
cover_url ='http://cdn.images.express.co.uk/img/static/ourpaper/header-back-issue-papers.jpg'
return cover_url
extra_css = '''
#h1{font-weight:bold;font-size:175%;}
h2{display: block;margin-left: auto;margin-right: auto;width:100%;font-weight:bold;font-size:175%;}
#p{font-size:14px;}
#body{font-size:14px;}
.newsCaption {display: block;margin-left: auto;margin-right: auto;width:100%;font-size:40%;}
.publish-info {font-size:50%;}
.photo img {display: block;margin-left: auto;margin-right: auto;width:100%;}
'''
06-27-2015, 11:52 AM
Similar Threads