From 6bde192bd770aa7e7abc541e025003cf3351a5f8 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 15 Dec 2012 14:48:45 +0530 Subject: [PATCH] Updated Birmingham Post --- recipes/birmingham_post.recipe | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) diff --git a/recipes/birmingham_post.recipe b/recipes/birmingham_post.recipe index b9b3c3fc57..49c86fe3b8 100644 --- a/recipes/birmingham_post.recipe +++ b/recipes/birmingham_post.recipe @@ -1,9 +1,11 @@ from calibre.web.feeds.news import BasicNewsRecipe +import re +import mechanize + class AdvancedUserRecipe1306097511(BasicNewsRecipe): title = u'Birmingham post' description = 'Author D.Asbury. News for Birmingham UK' #timefmt = '' - # last update 8/9/12 __author__ = 'Dave Asbury' cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg' oldest_article = 2 @@ -15,8 +17,30 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe): #auto_cleanup = True language = 'en_GB' + cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg' - masthead_url = 'http://www.pressgazette.co.uk/Pictures/web/t/c/g/birmingham_post.jpg' + masthead_url = 'http://www.trinitymirror.com/images/birminghampost-logo.gif' + def get_cover_url(self): + soup = self.index_to_soup('http://www.birminghampost.net') + # look for the block containing the sun button and url + cov = soup.find(attrs={'height' : re.compile('3'), 'alt' : re.compile('Birmingham Post')}) + print + print '%%%%%%%%%%%%%%%',cov + print + cov2 = str(cov['src']) + # cov2=cov2[7:] + print '88888888 ',cov2,' 888888888888' + + #cover_url=cov2 + #return cover_url + br = mechanize.Browser() + br.set_handle_redirect(False) + try: + br.open_novisit(cov2) + cover_url = cov2 + except: + cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg' + return cover_url keep_only_tags = [