Fix #6095 (Haaretz recipe broken)

resources/recipes/haaretz_en.recipe

@@ -1,56 +1,95 @@
 __license__   = 'GPL v3'
 __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
 '''
-haaretz.com
+www.haaretz.com
 '''
 
+import re
+from calibre import strftime
+from time import gmtime
 from calibre.web.feeds.news import BasicNewsRecipe
 
-class Haaretz_en(BasicNewsRecipe):
+class HaaretzPrint_en(BasicNewsRecipe):
-    title                 = 'Haaretz in English'
+    title                 = 'Haaretz - print edition'
     __author__            = 'Darko Miletic'
-    description           = 'Haaretz.com, the online edition of Haaretz Newspaper in Israel, and analysis from Israel and the Middle East. Haaretz.com provides extensive and in-depth coverage of Israel, the Jewish World and the Middle East, including defense, diplomacy, the Arab-Israeli conflict, the peace process, Israeli politics, Jerusalem affairs, international relations, Iran, Iraq, Syria, Lebanon, the Palestinian Authority, the West Bank and the Gaza Strip, the Israeli business world and Jewish life in Israel and the Diaspora. '
+    description           = "Haaretz.com is the world's leading English-language Website for real-time news and analysis of Israel and the Middle East."
-    publisher             = 'haaretz.com'
+    publisher             = 'Haaretz'
-    category              = 'news, politics, Israel'
+    category              = "news, Haaretz, Israel news, Israel newspapers, Israel business news, Israel financial news, Israeli news,Israeli newspaper, Israeli newspapers, news from Israel, news in Israel, news Israel, news on Israel, newspaper Israel, Israel sports news, Israel diplomacy news"
     oldest_article        = 2
     max_articles_per_feed = 200
     no_stylesheets        = True
-    encoding              = 'cp1252'
+    encoding              = 'utf8'
     use_embedded_content  = False
     language              = 'en_IL'
     publication_type      = 'newspaper'
-    remove_empty_feeds    = True
+    PREFIX                = 'http://www.haaretz.com'
-    masthead_url          = 'http://www.haaretz.com/images/logos/logoGrey.gif'
+    masthead_url          = PREFIX + '/images/logos/logoGrey.gif'
     extra_css             = ' body{font-family: Verdana,Arial,Helvetica,sans-serif } '
 
+    preprocess_regexps = [(re.compile(r'</body>.*?</html>', re.DOTALL|re.IGNORECASE),lambda match: '</body></html>')]
+
     conversion_options = {
-                          'comment'   : description
+                          'comment'  : description
-                        , 'tags'      : category
+                        , 'tags'     : category
-                        , 'publisher' : publisher
+                        , 'publisher': publisher
-                        , 'language'  : language
+                        , 'language' : language
                         }
 
-    remove_tags = [dict(name='div', attrs={'class':['rightcol']}),dict(name='table')]
+    keep_only_tags    = [dict(attrs={'id':'threecolumns'})]
-    remove_tags_before = dict(name='h1')
+    remove_attributes = ['width','height']
-    remove_tags_after  = dict(attrs={'id':'innerArticle'})
+    remove_tags       = [
-    keep_only_tags     = [dict(attrs={'id':'content'})]
+                           dict(name=['iframe','link','object','embed'])
+                          ,dict(name='div',attrs={'class':'rightcol'})
+                        ]
 
 
     feeds = [
-              (u'Opinion'               , u'http://www.haaretz.com/cmlink/opinion-rss-1.209234?localLinksEnabled=false'   )
+              (u'News'          , PREFIX + u'/print-edition/news'         )
-             ,(u'Defense and diplomacy' , u'http://www.haaretz.com/cmlink/defense-and-diplomacy-rss-1.208894?localLinksEnabled=false')
+             ,(u'Opinion'       , PREFIX + u'/print-edition/opinion'      )
-             ,(u'National'              , u'http://www.haaretz.com/cmlink/national-rss-1.208896?localLinksEnabled=false'       )
+             ,(u'Business'      , PREFIX + u'/print-edition/business'     )
-             ,(u'International'         , u'http://www.haaretz.com/cmlink/international-rss-1.208898?localLinksEnabled=false'      )
+             ,(u'Real estate'   , PREFIX + u'/print-edition/real-estate'  )
-             ,(u'Jewish World'          , u'http://www.haaretz.com/cmlink/jewish-world-rss-1.209085?localLinksEnabled=false'        )
+             ,(u'Sports'        , PREFIX + u'/print-edition/sports'       )
-             ,(u'Business'              , u'http://www.haaretz.com/cmlink/business-print-rss-1.264904?localLinksEnabled=false'     )
+             ,(u'Travel'        , PREFIX + u'/print-edition/travel'       )
-             ,(u'Real Estate'           , u'http://www.haaretz.com/cmlink/real-estate-print-rss-1.264977?localLinksEnabled=false'      )
+             ,(u'Books'         , PREFIX + u'/print-edition/books'        )
-             ,(u'Features'              , u'http://www.haaretz.com/cmlink/features-print-rss-1.264912?localLinksEnabled=false'          )
+             ,(u'Food & Wine'   , PREFIX + u'/print-edition/food-wine'    )
-             ,(u'Arts and leisure'      , u'http://www.haaretz.com/cmlink/arts-and-leisure-rss-1.286090?localLinksEnabled=false'       )
+             ,(u'Arts & Leisure', PREFIX + u'/print-edition/arts-leisure' )
-             ,(u'Books'                 , u'http://www.haaretz.com/cmlink/books-rss-1.264947?localLinksEnabled=false'         )
+             ,(u'Features'      , PREFIX + u'/print-edition/features'     )
-             ,(u'Food and Wine'         , u'http://www.haaretz.com/cmlink/food-and-wine-print-rss-1.265034?localLinksEnabled=false'      )
-             ,(u'Sports'                , u'http://www.haaretz.com/cmlink/sports-rss-1.286092?localLinksEnabled=false'          )
             ]
 
+
+    def print_version(self, url):
+        article = url.rpartition('/')[2]
+        return 'http://www.haaretz.com/misc/article-print-page/' + article
+
+    def parse_index(self):
+        totalfeeds = []
+        lfeeds = self.get_feeds()
+        for feedobj in lfeeds:
+            feedtitle, feedurl = feedobj
+            self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
+            articles = []
+            soup = self.index_to_soup(feedurl)
+            for item in soup.findAll(attrs={'class':'text'}):
+                sp = item.find('span',attrs={'class':'h3 font-weight-normal'})
+                desc = item.find('p')
+                description = ''
+                if sp:
+                    if desc:
+                       description = self.tag_to_string(desc)
+                    link        = sp.a
+                    url         = self.PREFIX + link['href']
+                    title       = self.tag_to_string(link)
+                    times        = strftime('%a, %d %b %Y %H:%M:%S +0000',gmtime())
+                    articles.append({
+                                          'title'      :title
+                                         ,'date'       :times
+                                         ,'url'        :url
+                                         ,'description':description
+                                        })
+            totalfeeds.append((feedtitle, articles))
+        return totalfeeds
+
+
     def preprocess_html(self, soup):
         for item in soup.findAll(style=True):
             del item['style']

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

@@ -22,7 +22,7 @@ E = ElementMaker(namespace=NS, nsmap={None:NS})
 
 def iterate_over_builtin_recipe_files():
     exclude = ['craigslist', 'iht', 'outlook_india', 'toronto_sun',
-            'indian_express', 'india_today']
+            'indian_express', 'india_today', 'livemint']
     d = os.path.dirname
     base = os.path.join(d(d(d(d(d(d(os.path.abspath(__file__))))))), 'resources', 'recipes')
     for x in os.walk(base):