Add lepoint news website recipe

recipes/lepoint.recipe

@@ -0,0 +1,75 @@
+__license__   = 'GPL v3'
+__copyright__ = '2011 Aurélien Chabot <contact@aurelienchabot.fr>'
+'''
+LePoint.fr
+'''
+import re
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class lepoint(BasicNewsRecipe):
+
+    title                  = 'Le Point'
+    __author__             = 'calibre'
+    description            = 'Actualités'
+    encoding               = 'utf-8'
+    publisher              = 'LePoint.fr'
+    category               = 'news, France, world'
+    language               = 'fr'
+
+    use_embedded_content   = False
+    timefmt                = ' [%d %b %Y]'
+    max_articles_per_feed  = 15
+    no_stylesheets         = True
+    remove_empty_feeds     = True
+    filterDuplicates       = True
+
+    extra_css = '''
+                    h1 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;}
+                    .chapo {font-size:xx-small; font-family:Arial,Helvetica,sans-serif;}
+                    .info_article {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
+                    .media_article {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
+                    .article {font-size:medium; font-family:Arial,Helvetica,sans-serif;}
+                '''
+
+    remove_tags = [
+            dict(name='iframe'),
+            dict(name='div', attrs={'class':['entete_chroniqueur']}),
+            dict(name='div', attrs={'class':['col_article']}),
+            dict(name='div', attrs={'class':['signature_article']}),
+            dict(name='div', attrs={'class':['util_font util_article']}),
+            dict(name='div', attrs={'class':['util_article bottom']})
+    ]
+
+    keep_only_tags    = [dict(name='div', attrs={'class':['page_article']})]
+
+    remove_tags_after  = dict(name='div', attrs={'class':['util_article bottom']})
+
+    feeds = [
+        (u'À la une', 'http://www.lepoint.fr/rss.xml'),
+        ('International', 'http://www.lepoint.fr/monde/rss.xml'),
+        ('Tech/Web', 'http://www.lepoint.fr/high-tech-internet/rss.xml'),
+        ('Sciences', 'http://www.lepoint.fr/science/rss.xml'),
+        ('Economie', 'http://www.lepoint.fr/economie/rss.xml'),
+        (u'Socièté', 'http://www.lepoint.fr/societe/rss.xml'),
+        ('Politique', 'http://www.lepoint.fr/politique/rss.xml'),
+        (u'Médias', 'http://www.lepoint.fr/medias/rss.xml'),
+        ('Culture', 'http://www.lepoint.fr/culture/rss.xml'),
+        (u'Santé', 'http://www.lepoint.fr/sante/rss.xml'),
+        ('Sport', 'http://www.lepoint.fr/sport/rss.xml')
+    ]
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
+    def get_masthead_url(self):
+        masthead = 'http://www.lepoint.fr/images/commun/logo.png'
+        br = BasicNewsRecipe.get_browser()
+        try:
+            br.open(masthead)
+        except:
+            self.log("\nCover unavailable")
+            masthead = None
+        return masthead