Fix #7583 (Updated recipe for Al Jazeera in English)

resources/recipes/al_jazeera.recipe

@@ -1,10 +1,8 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
 
 '''
-aljazeera.net
+english.aljazeera.net
 '''
 from calibre.web.feeds.news import BasicNewsRecipe
 
@@ -13,40 +11,58 @@ class AlJazeera(BasicNewsRecipe):
     __author__             = 'Darko Miletic'
     description            = 'News from Middle East'
     language               = 'en'
-
     publisher              = 'Al Jazeera'
     category               = 'news, politics, middle east'
-    simultaneous_downloads = 1
-    delay                  = 4
-    oldest_article         = 1
+    delay                  = 1
+    oldest_article         = 2
     max_articles_per_feed  = 100
     no_stylesheets         = True
     encoding               = 'iso-8859-1'
-    remove_javascript      = True
     use_embedded_content   = False
+    extra_css              = """
+                                body{font-family: Arial,sans-serif}
+                                #ctl00_cphBody_dvSummary{font-weight: bold}
+                                #dvArticleDate{font-size: small; color: #999999}
+                             """
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
 
-    html2lrf_options = [
-                          '--comment', description
-                        , '--category', category
-                        , '--publisher', publisher
-                        , '--ignore-tables'
+    keep_only_tags = [
+                         dict(attrs={'id':['DetailedTitle','ctl00_cphBody_dvSummary','dvArticleDate']})
+                        ,dict(name='td',attrs={'class':'DetailedSummary'})
                      ]
 
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_table=True'
-
-    keep_only_tags = [dict(name='div', attrs={'id':'ctl00_divContent'})]
-
     remove_tags = [
-                     dict(name=['object','link'])
+                     dict(name=['object','link','table','meta','base','iframe','embed'])
                     ,dict(name='td', attrs={'class':['MostActiveDescHeader','MostActiveDescBody']})
                   ]
 
     feeds = [(u'AL JAZEERA ENGLISH (AJE)', u'http://english.aljazeera.net/Services/Rss/?PostingId=2007731105943979989' )]
 
+    def get_article_url(self, article):
+        artlurl =  article.get('link',  None)
+        return artlurl.replace('http://english.aljazeera.net//','http://english.aljazeera.net/')
+
     def preprocess_html(self, soup):
         for item in soup.findAll(style=True):
             del item['style']
         for item in soup.findAll(face=True):
             del item['face']
+        td = soup.find('td',attrs={'class':'DetailedSummary'})
+        if td:
+           td.name = 'div'
+        spn = soup.find('span',attrs={'id':'DetailedTitle'})
+        if spn:
+           spn.name='h1'
+        for itm in soup.findAll('span', attrs={'id':['dvArticleDate','ctl00_cphBody_lblDate']}):
+            itm.name = 'div'
+        for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
         return soup