diff --git a/recipes/guardian.recipe b/recipes/guardian.recipe index 6211997b06..c5021cb91d 100644 --- a/recipes/guardian.recipe +++ b/recipes/guardian.recipe @@ -28,7 +28,7 @@ class Guardian(BasicNewsRecipe): # List of section titles to ignore # For example: ['Sport'] ignore_sections = [] - + timefmt = ' [%a, %d %b %Y]' keep_only_tags = [ dict(name='div', attrs={'id':["content","article_header","main-article-info",]}), @@ -87,8 +87,14 @@ class Guardian(BasicNewsRecipe): idx = soup.find('div', id='book-index') for s in idx.findAll('strong', attrs={'class':'book'}): a = s.find('a', href=True) - yield (self.tag_to_string(a), a['href']) - + section_title = self.tag_to_string(a) + if not section_title in self.ignore_sections: + prefix = '' + if section_title != 'Main section': + prefix = section_title + ': ' + for subsection in s.parent.findAll('a', attrs={'class':'book-section'}): + yield (prefix + self.tag_to_string(subsection), subsection['href']) + def find_articles(self, url): soup = self.index_to_soup(url) div = soup.find('div', attrs={'class':'book-index'}) @@ -109,15 +115,12 @@ class Guardian(BasicNewsRecipe): 'title': title, 'url':url, 'description':desc, 'date' : strftime('%a, %d %b'), } - + def parse_index(self): try: feeds = [] for title, href in self.find_sections(): - if not title in self.ignore_sections: - feeds.append((title, list(self.find_articles(href)))) + feeds.append((title, list(self.find_articles(href)))) return feeds except: raise NotImplementedError - - diff --git a/recipes/telegraph_uk.recipe b/recipes/telegraph_uk.recipe index f79f0fa50c..5fe5b168b8 100644 --- a/recipes/telegraph_uk.recipe +++ b/recipes/telegraph_uk.recipe @@ -49,6 +49,7 @@ class TelegraphUK(BasicNewsRecipe): (u'UK News' , u'http://www.telegraph.co.uk/news/uknews/rss' ) ,(u'World News' , u'http://www.telegraph.co.uk/news/worldnews/rss' ) ,(u'Politics' , u'http://www.telegraph.co.uk/news/newstopics/politics/rss' ) + ,(u'Finance' , u'http://www.telegraph.co.uk/finance/rss' ) ,(u'Technology News', u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologynews/rss' ) ,(u'UK News' , u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologyreviews/rss') ,(u'Science News' , u'http://www.telegraph.co.uk/scienceandtechnology/science/sciencenews/rss' ) diff --git a/recipes/time_magazine.recipe b/recipes/time_magazine.recipe index 380bf71f8c..ac7821b65a 100644 --- a/recipes/time_magazine.recipe +++ b/recipes/time_magazine.recipe @@ -10,8 +10,8 @@ import re from calibre.web.feeds.news import BasicNewsRecipe class Time(BasicNewsRecipe): - recipe_disabled = ('This recipe has been disabled as TIME no longer' - ' publish complete articles on the web.') + #recipe_disabled = ('This recipe has been disabled as TIME no longer' + # ' publish complete articles on the web.') title = u'Time' __author__ = 'Kovid Goyal and Sujata Raman' description = 'Weekly magazine' diff --git a/recipes/zaobao.recipe b/recipes/zaobao.recipe index 91a5459e18..a6d7d2e08e 100644 --- a/recipes/zaobao.recipe +++ b/recipes/zaobao.recipe @@ -82,7 +82,7 @@ class ZAOBAO(BasicNewsRecipe): return soup def parse_feeds(self): - self.log_debug(_('ZAOBAO overrided parse_feeds()')) + self.log(_('ZAOBAO overrided parse_feeds()')) parsed_feeds = BasicNewsRecipe.parse_feeds(self) for id, obj in enumerate(self.INDEXES): @@ -99,7 +99,7 @@ class ZAOBAO(BasicNewsRecipe): a_title = self.tag_to_string(a) date = '' description = '' - self.log_debug(_('adding %s at %s')%(a_title,a_url)) + self.log(_('adding %s at %s')%(a_title,a_url)) articles.append({ 'title':a_title, 'date':date, @@ -110,23 +110,23 @@ class ZAOBAO(BasicNewsRecipe): pfeeds = feeds_from_index([(title, articles)], oldest_article=self.oldest_article, max_articles_per_feed=self.max_articles_per_feed) - self.log_debug(_('adding %s to feed')%(title)) + self.log(_('adding %s to feed')%(title)) for feed in pfeeds: - self.log_debug(_('adding feed: %s')%(feed.title)) + self.log(_('adding feed: %s')%(feed.title)) feed.description = self.DESC_SENSE parsed_feeds.append(feed) for a, article in enumerate(feed): - self.log_debug(_('added article %s from %s')%(article.title, article.url)) - self.log_debug(_('added feed %s')%(feed.title)) + self.log(_('added article %s from %s')%(article.title, article.url)) + self.log(_('added feed %s')%(feed.title)) for i, feed in enumerate(parsed_feeds): # workaorund a strange problem: Somethimes the xml encoding is not apllied correctly by parse() weired_encoding_detected = False if not isinstance(feed.description, unicode) and self.encoding and feed.description: - self.log_debug(_('Feed %s is not encoded correctly, manually replace it')%(feed.title)) + self.log(_('Feed %s is not encoded correctly, manually replace it')%(feed.title)) feed.description = feed.description.decode(self.encoding, 'replace') elif feed.description.find(self.DESC_SENSE) == -1 and self.encoding and feed.description: - self.log_debug(_('Feed %s is weired encoded, manually redo all')%(feed.title)) + self.log(_('Feed %s is weired encoded, manually redo all')%(feed.title)) feed.description = feed.description.encode('cp1252', 'replace').decode(self.encoding, 'replace') weired_encoding_detected = True @@ -148,7 +148,7 @@ class ZAOBAO(BasicNewsRecipe): article.text_summary = article.text_summary.encode('cp1252', 'replace').decode(self.encoding, 'replace') if article.title == "Untitled article": - self.log_debug(_('Removing empty article %s from %s')%(article.title, article.url)) + self.log(_('Removing empty article %s from %s')%(article.title, article.url)) # remove the article feed.articles[a:a+1] = [] return parsed_feeds