Updated recipe ro the Times Online

src/calibre/web/feeds/recipes/recipe_newsweek.py

@@ -2,7 +2,7 @@
 
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
-import re, time
+import re
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 
@@ -12,6 +12,7 @@ class Newsweek(BasicNewsRecipe):
     __author__     = 'Kovid Goyal'
     description    = 'Weekly news and current affairs in the US'
     no_stylesheets = True
+    encoding       = 'utf-8'
     language = _('English')
     remove_tags = [
             {'class':['navbar', 'ad', 'sponsorLinksArticle', 'mm-content',
@@ -30,12 +31,12 @@ class Newsweek(BasicNewsRecipe):
 
     def find_title(self, section):
         d = {'scope':'Scope', 'thetake':'The Take', 'features':'Features',
-        None:'Departments'}
+                None:'Departments', 'culture':'Culture'}
         ans = None
         a = section.find('a', attrs={'name':True})
         if a is not None:
             ans = a['name']
-        return d[ans]
+        return d.get(ans, ans)
 
 
     def find_articles(self, section):
@@ -64,14 +65,6 @@ class Newsweek(BasicNewsRecipe):
         soup = self.get_current_issue()
         if not soup:
             raise RuntimeError('Unable to connect to newsweek.com. Try again later.')
-        img = soup.find(alt='Cover')
-        if img is not None and img.has_key('src'):
-            small = img['src']
-            match = re.search(r'(\d+)_', small.rpartition('/')[-1])
-            if match is not None:
-                self.timefmt = strftime(' [%d %b, %Y]', time.strptime(match.group(1), '%y%m%d'))
-            self.cover_url = small.replace('coversmall', 'coverlarge')
-
         sections = soup.findAll('div', attrs={'class':'featurewell'})
         titles = map(self.find_title, sections)
         articles = map(self.find_articles, sections)
@@ -114,3 +107,12 @@ class Newsweek(BasicNewsRecipe):
             href = a['href'].split('#')[0]
             return self.index_to_soup(href)
 
+    def get_cover_url(self):
+        cover_url = None
+        soup = self.index_to_soup(self.INDEX)
+        link_item = soup.find('div',attrs={'class':'cover-image'})
+        if link_item and link_item.a and link_item.a.img:
+           cover_url = link_item.a.img['src']
+        return cover_url
+
+

src/calibre/web/feeds/recipes/recipe_times_online.py

@@ -1,28 +1,39 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
 '''
 timesonline.co.uk
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
-class TimesOnline(BasicNewsRecipe):
-    title                 = u'The Times Online'
-    __author__            = 'Darko Miletic'
-    description           = 'UK news'    
-    oldest_article        = 7
-    max_articles_per_feed = 100
-    no_stylesheets        = True
-    use_embedded_content  = False
-    language = _('English')
+class Timesonline(BasicNewsRecipe):
+    title                  = 'The Times Online'
+    __author__             = 'Darko Miletic'
+    description            = 'UK news' 
+    publisher              = 'timesonline.co.uk'
+    category               = 'news, politics, UK'        
+    oldest_article         = 2
+    max_articles_per_feed  = 100
+    no_stylesheets         = True
+    use_embedded_content   = False
     simultaneous_downloads = 1
+    encoding               = 'cp1252'
+    lang                   = 'en-UK'
+    language               = _('English')
 
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    
+    remove_tags        = [dict(name=['embed','object'])]
     remove_tags_after  = dict(name='div', attrs={'class':'bg-666'})
-    remove_tags = [
-                     dict(name='div'  , attrs={'class':'hide-from-print padding-bottom-7' })
-                  ]
 
     feeds          = [
                         (u'Top stories from Times Online', u'http://www.timesonline.co.uk/tol/feeds/rss/topstories.xml'     ),
@@ -38,5 +49,17 @@ class TimesOnline(BasicNewsRecipe):
                      ]
 
     def print_version(self, url):
-        main = url.partition('#')[0]
-        return main + '?print=yes'
+        return url + '?print=yes'
+
+    def get_article_url(self, article):
+        return article.get('guid',  None)
+
+    def preprocess_html(self, soup):
+        soup.html['xml:lang'] = self.lang
+        soup.html['lang']     = self.lang
+        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=UTF-8")])
+        soup.head.insert(0,mlang)
+        soup.head.insert(1,mcharset)
+        return self.adeify_images(soup)
+