Updating for new site layout & combining Sunday ed

recipes/times_online.recipe

@@ -1,45 +1,51 @@
 
 __license__ = 'GPL v3'
-__copyright__ = '2009-2013, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2010-2017, Bobby Steel <bob at xdca.com>, Darko Miletic'
 '''
 www.thetimes.co.uk
 '''
 import urllib
+import html5lib
+from lxml import html
 from calibre.web.feeds.news import BasicNewsRecipe
 
+def classes(classes):
+    q = frozenset(classes.split(' '))
+    return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
 
 class TimesOnline(BasicNewsRecipe):
-    title = 'The Times UK'
+    title = 'The Times & Sunday Times (UK)'
-    __author__ = 'Darko Miletic'
+    __author__ = 'Bobby Steel'
     description = 'news from United Kingdom and World'
     language = 'en_GB'
     publisher = 'Times Newspapers Ltd'
     category = 'news, politics, UK'
-    oldest_article = 3
+    excludeSections = ['Puzzles']
+    oldest_article = 1
     max_articles_per_feed = 100
     no_stylesheets = True
     use_embedded_content = False
     encoding = 'utf-8'
     delay = 1
     needs_subscription = True
-    auto_cleanup = False
     publication_type = 'newspaper'
-    masthead_url = 'http://www.thetimes.co.uk/tto/public/img/the_times_460.gif'
+    INDEX = 'http://www.thetimes.co.uk/'
-    INDEX = 'http://www.thetimes.co.uk'
+    PREFIX = u'http://www.thetimes.co.uk'
-    PREFIX = u'http://www.thetimes.co.uk/tto/'
     extra_css             = """
-                                .f-ha{font-size: xx-large; font-weight: bold}
+                                .author-name,.authorName{font-style: italic}
-                                .f-author{font-family: Arial,Helvetica,sans-serif}
+                                .published-date,.multi-position-photo-text{font-family: Arial,Helvetica,sans-serif;
-                                .caption{font-size: small}
+                                                                           font-size: small; color: gray;
+                                                                           display:block; margin-bottom: 0.5em}
                                 body{font-family: Georgia,"Times New Roman",Times,serif}
                             """
+
     conversion_options = {
         'comment': description, 'tags': category, 'publisher': publisher, 'language': language
     }
 
     def get_browser(self):
         br = BasicNewsRecipe.get_browser(self)
-        br.open('http://www.thetimes.co.uk/tto/news/')
+        br.open('http://www.thetimes.co.uk/')
         if self.username is not None and self.password is not None:
             data = urllib.urlencode({
                 'gotoUrl': self.INDEX, 'username': self.username, 'password': self.password
@@ -48,49 +54,51 @@ class TimesOnline(BasicNewsRecipe):
         return br
 
     remove_tags = [
-        dict(name=['object', 'link', 'iframe', 'base', 'meta']), dict(
+        {'name': ['object', 'link', 'iframe', 'base', 'meta', 'script']},
-            attrs={'class': 'tto-counter'})
+        {'attrs': {'class': ['tools comments-parent','u-hide','Tooltip','Toolbar Toolbar--bottom','Comments Article-container','ArticlePager','Media-caption']}},
+        {'attrs': {'class': lambda x: x and 'Toolbar' in x}} 
     ]
     remove_attributes = ['lang']
     keep_only_tags = [
-        dict(attrs={'class': 'heading'}), dict(attrs={'class': 'f-author'}), dict(
+        dict(attrs={'class': 'Article Article--default'}
-            attrs={'class': ['media', 'byline-timestamp']}), dict(attrs={'id': 'bodycopy'})
+             ), dict(attrs={'class': 'f-author'}), dict(attrs={'id': 'bodycopy'})
     ]
+    remove_tags_after = dict(attrs={'class': 'Article-content'})
 
     feeds = [
-
+    (u'All News', u'http://www.thetimes.co.uk/')
-    (u'UK News', PREFIX + u'news/uk/?view=list'),
-    (u'World', PREFIX + u'news/world/?view=list'),
-    (u'Politics', PREFIX + u'news/politics/?view=list'),
-    (u'Health', PREFIX + u'health/news/?view=list'),
-    (u'Education', PREFIX + u'education/?view=list'),
-    (u'Technology', PREFIX + u'technology/?view=list'),
-    (u'Science', PREFIX + u'science/?view=list'),
-    (u'Environment', PREFIX + u'environment/?view=list'),
-    (u'Faith', PREFIX + u'faith/?view=list'),
-    (u'Opinion', PREFIX + u'opinion/?view=list'),
-    (u'Sport', PREFIX + u'sport/?view=list'),
-    (u'Business', PREFIX + u'business/?view=list'),
-    (u'Money', PREFIX + u'money/?view=list'),
-    (u'Life', PREFIX + u'life/?view=list'),
-    (u'Arts', PREFIX + u'arts/?view=list')
     ]
+    
+    def preprocess_raw_html(self, raw, url):
+        return html.tostring(html5lib.parse(raw, treebuilder='lxml', namespaceHTMLElements=False), method='html', encoding=unicode)
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return self.adeify_images(soup)
 
     def parse_index(self):
-        totalfeeds = []
+        soup = self.index_to_soup(self.INDEX)
-        lfeeds = self.get_feeds()
+        totalfeeds = []                
-        for feedobj in lfeeds:
+        current_section = []
-            feedtitle, feedurl = feedobj
+        div = []
-            self.report_progress(0, _('Fetching feed') + ' %s...' %
+        for div in soup.findAll('section', attrs={'data-text': True}):
-                                 (feedtitle if feedtitle else feedurl))
+            current_articles = []
-            articles = []
+            self.log('in section: ', div['data-text'])
-            soup = self.index_to_soup(feedurl)
+            current_section = div['data-text']
-            for item in soup.findAll('td', attrs={'class': 'title'}):
+            if current_section not in self.excludeSections:
-                atag = item.find('a')
+                for article in div.findAll('div', attrs={'class': 'Item-content'}):
-                url = self.INDEX + atag['href']
+                    h3 = article.find('h3')
-                title = self.tag_to_string(atag)
+                    if h3 is not None:
-                articles.append({
+                        title = self.tag_to_string(h3)
-                    'title': title, 'date': '', 'url': url, 'description': ''
+                        aurl = h3.find('a')
-                })
+                        if aurl is not None:
-            totalfeeds.append((feedtitle, articles))
+                            url = aurl['href']
+                            if url.startswith('/'):
+                               url = 'http://www.thetimes.co.uk' + url
+                            desc = title         
+                            self.log('section: ', current_section, 'title: ', title, 'url: ', url, 'desc: ', desc, '\n')   
+                            current_articles.append({'title': title, 'url': url, 'description': desc})
+                if current_articles:
+                    totalfeeds.append((current_section, current_articles))  
         return totalfeeds