From e27bff194201a7d3b0c6aabfe5c9cf65bc276f59 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 27 Jun 2015 23:45:50 +0530 Subject: [PATCH] Update Daily Express --- recipes/daily_express.recipe | 43 +++++++++++++++++++++++------------- 1 file changed, 28 insertions(+), 15 deletions(-) diff --git a/recipes/daily_express.recipe b/recipes/daily_express.recipe index 2bd290b7bd..5b79baab2f 100644 --- a/recipes/daily_express.recipe +++ b/recipes/daily_express.recipe @@ -1,19 +1,19 @@ # vim:fileencoding=UTF-8 from __future__ import unicode_literals - import re from calibre.web.feeds.news import BasicNewsRecipe +from calibre import browser class AdvancedUserRecipe1390132023(BasicNewsRecipe): title = u'Daily Express' - language = 'en_GB' __author__ = 'Dave Asbury' - # 21.11.14 written due to website changes - oldest_article = 1 + # 27.6.15 using feed43 as rss feeds dead + # feed 43 string =
{%} + oldest_article = 1.5 max_articles_per_feed = 10 compress_news_images = True - compress_news_images_max_size = 30 + 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"]' @@ -21,30 +21,43 @@ class AdvancedUserRecipe1390132023(BasicNewsRecipe): no_stylesheets = False 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 = [ - (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'), - (u'Sport',u'http://www.express.co.uk/posts/rss/65/sport'), - (u'Entertainment',u'http://www.express.co.uk/posts/rss/18/entertainment'), - (u'Lifestyle',u'http://www.express.co.uk/posts/rss/8/life&style'), - (u'Fun',u'http://www.express.co.uk/posts/rss/110/fun'), + (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'), ] 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 = self.get_browser() + br = browser() br.set_handle_redirect(False) try: br.open_novisit(cov)