Update various French Belgian recipes

resources/recipes/cinebel_be.recipe

@@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
+__copyright__ = '2008-2011, Lionel Bergeret <lbergeret at gmail.com>'
 '''
 cinebel.be
 '''
@@ -14,14 +14,14 @@ class Cinebel(BasicNewsRecipe):
     description           = u'Cinema news from Belgium in French'
     publisher             = u'cinebel.be'
     category              = 'news, cinema, movie, Belgium'
-    oldest_article        = 3
+    oldest_article        = 15
-    encoding              = 'utf8'
+    language              = 'fr'
-    language              = 'fr_BE'
 
     max_articles_per_feed = 20
     no_stylesheets        = True
     use_embedded_content  = False
     timefmt               = ' [%d %b %Y]'
+    filterDuplicates      = True
 
     keep_only_tags = [
 	 dict(name = 'span', attrs = {'class': 'movieMainTitle'})
@@ -35,6 +35,13 @@ class Cinebel(BasicNewsRecipe):
         ,(u'Top 10'                    , u'http://www.cinebel.be/Servlets/RssServlet?languageCode=fr&rssType=2' )
     ]
 
+    def preprocess_html(self, soup):
+        for alink in soup.findAll('a'):
+            if alink.has_key('href'):
+               tstr = "Site officiel: " + alink['href']
+               alink.replaceWith(tstr)
+        return soup
+
     def get_cover_url(self):
         cover_url = 'http://www.cinebel.be/portal/resources/common/logo_index.gif'
         return cover_url

resources/recipes/dhnet_be.recipe

@@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
+__copyright__ = '2008-2011, Lionel Bergeret <lbergeret at gmail.com>'
 '''
 dhnet.be
 '''
@@ -16,7 +16,8 @@ class DHNetBe(BasicNewsRecipe):
     publisher             = u'dhnet.be'
     category              = 'news, Belgium'
     oldest_article        = 3
-    language              = 'fr_BE'
+    language              = 'fr'
+    masthead_url          = 'http://www.dhnet.be/images/homepage_logo_dh.gif'
 
     max_articles_per_feed = 20
     no_stylesheets        = True
@@ -34,6 +35,13 @@ class DHNetBe(BasicNewsRecipe):
         ,(u'La Une Info'    , u'http://www.dhnet.be/rss/dhinfos/' )
     ]
 
+    def preprocess_html(self, soup):
+        for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
+        return soup
+
     def get_cover_url(self):
         cover_url = strftime('http://pdf-online.dhnet.be/pdfonline/image/%Y%m%d/dh_%Y%m%d_nam_infoge_001.pdf.L.jpg')
         return cover_url

resources/recipes/lalibre_be.recipe

@@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
+__copyright__ = '2008-2011, Lionel Bergeret <lbergeret at gmail.com>'
 '''
 lalibre.be
 '''
@@ -16,18 +16,18 @@ class LaLibre(BasicNewsRecipe):
     publisher             = u'lalibre.be'
     category              = 'news, Belgium'
     oldest_article        = 3
-    language              = 'fr_BE'
+    language              = 'fr'
+    masthead_url          = 'http://www.lalibre.be/img/logoLaLibre.gif'
 
     max_articles_per_feed = 20
     no_stylesheets        = True
     use_embedded_content  = False
     timefmt               = ' [%d %b %Y]'
 
-    keep_only_tags = [
+    remove_tags_before = dict(name = 'div', attrs = {'class': 'extraMainContent'})
-	 dict(name = 'div', attrs = {'id': 'articleHat'})
+    remove_tags_after  = dict(name = 'div', attrs = {'id': 'articleText'})
-	,dict(name = 'p', attrs = {'id': 'publicationDate'})
+
-        ,dict(name = 'div', attrs = {'id': 'articleText'})
+    remove_tags = [dict(name = 'div', attrs = {'id': 'strongArticleLinks'})]
-    ]
 
     feeds = [
          (u'L\'actu'           , u'http://www.lalibre.be/rss/?section=10' )
@@ -38,6 +38,13 @@ class LaLibre(BasicNewsRecipe):
         ,(u'Societe'           , u'http://www.lalibre.be/rss/?section=12' )
     ]
 
+    def preprocess_html(self, soup):
+        for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
+        return soup
+
     def get_cover_url(self):
         cover_url = strftime('http://pdf-online.lalibre.be/pdfonline/image/%Y%m%d/llb_%Y%m%d_nam_libre_001.pdf.L.jpg')
         return cover_url

resources/recipes/lameuse_be.recipe

@@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
+__copyright__ = '2008-2011, Lionel Bergeret <lbergeret at gmail.com>'
 '''
 lameuse.be
 '''
@@ -16,8 +16,8 @@ class LaMeuse(BasicNewsRecipe):
     publisher             = u'lameuse.be'
     category              = 'news, Belgium'
     oldest_article        = 3
-    encoding              = 'utf8'
+    language              = 'fr'
-    language              = 'fr_BE'
+    masthead_url          = 'http://www.lameuse.be/images/SPV3/logo_header_LM.gif'
 
     max_articles_per_feed = 20
     no_stylesheets        = True
@@ -32,6 +32,11 @@ class LaMeuse(BasicNewsRecipe):
          dict(name = 'div', attrs = {'class': 'sb-group'})
         ,dict(name = 'div', attrs = {'id': 'share'})
         ,dict(name = 'div', attrs = {'id': 'commentaires'})
+        ,dict(name = 'ul', attrs = {'class': 'right liensutiles'})
+        ,dict(name = 'ul', attrs = {'class': 'bas liensutiles'})
+        ,dict(name = 'p', attrs = {'class': 'ariane'})
+        ,dict(name = 'div', attrs = {'class': 'inner-bloc'})
+        ,dict(name = 'div', attrs = {'class': 'block-01'})
     ]
 
     feeds = [

resources/recipes/lavenir_be.recipe

@@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
+__copyright__ = '2008-2011, Lionel Bergeret <lbergeret at gmail.com>'
 '''
 lavenir.net
 '''
@@ -15,8 +15,7 @@ class LAvenir(BasicNewsRecipe):
     publisher             = u'lavenir.net'
     category              = 'news, Belgium'
     oldest_article        = 3
-    encoding              = 'utf8'
+    language              = 'fr'
-    language              = 'fr_BE'
 
     max_articles_per_feed = 20
     no_stylesheets        = True
@@ -35,6 +34,13 @@ class LAvenir(BasicNewsRecipe):
         ,(u'Societe'        , u'http://www.lavenir.net/rss.aspx?foto=1&intro=1&section=info&info=12e1a2f4-7e03-4cf1-afec-016869072317' )
     ]
 
+    def preprocess_html(self, soup):
+        for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
+        return soup
+
     def get_cover_url(self):
         cover_url = 'http://www.lavenir.net/extra/Static/journal/Pdf/1/UNE_Nationale.PDF'
         return cover_url

resources/recipes/lesoir_be.recipe

@@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
+__copyright__ = '2008-2011, Lionel Bergeret <lbergeret at gmail.com>'
 '''
 lesoir.be
 '''
@@ -16,7 +16,8 @@ class LeSoirBe(BasicNewsRecipe):
     publisher             = u'lesoir.be'
     category              = 'news, Belgium'
     oldest_article        = 3
-    language              = 'fr_BE'
+    language              = 'fr'
+    masthead_url          = 'http://pdf.lesoir.be/pdf/images/SOIR//logo.gif'
 
     max_articles_per_feed = 20
     no_stylesheets        = True