Big Oven by Starson17 and estadao updated. Another fix for metadata download with null titles

resources/recipes/big_oven.recipe

@@ -0,0 +1,64 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class BigOven(BasicNewsRecipe):
+    title               = 'BigOven'
+    __author__          = 'Starson17'
+    description         = 'Recipes for the Foodie in us all. Registration is free. A fake username and password just gives smaller photos.'
+    language            = 'en'
+    category            = 'news, food, recipes, gourmet'
+    publisher           = 'Starson17'
+    use_embedded_content= False
+    no_stylesheets      = True
+    oldest_article      = 24
+    remove_javascript   = True
+    remove_empty_feeds    = True
+    cover_url           = 'http://www.software.com/images/products/BigOven%20Logo_177_216.JPG'
+    max_articles_per_feed = 30
+    needs_subscription = True
+
+    conversion_options = {'linearize_tables'  : True
+                        , 'comment'           : description
+                        , 'tags'              : category
+                        , 'publisher'         : publisher
+                        , 'language'          : language
+                        }
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        if self.username is not None and self.password is not None:
+            br.open('http://www.bigoven.com/')
+            br.select_form(name='form1')
+            br['TopMenu_bo1$email']  = self.username
+            br['TopMenu_bo1$password'] = self.password
+            br.submit()
+        return br
+
+    remove_attributes = ['style', 'font']
+
+    keep_only_tags     = [dict(name='h1')
+                          ,dict(name='div', attrs={'class':'img'})
+                          ,dict(name='div', attrs={'id':'intro'})
+                          ]
+
+    remove_tags = [dict(name='div', attrs={'style':["overflow: visible;"]})
+                   ,dict(name='div', attrs={'class':['ctas']})
+                   #,dict(name='a', attrs={'class':['edit']})
+                   ,dict(name='p', attrs={'class':['byline']})
+                   ]
+
+    feeds = [(u'4 & 5 Star Rated Recipes', u'http://feeds.feedburner.com/Bigovencom-RecipeRaves?format=xml')]
+
+    def preprocess_html(self, soup):
+        for tag in soup.findAll(name='a', attrs={'class':['edit']}):
+          tag.parent.extract()
+        for tag in soup.findAll(name='a', attrs={'class':['deflink']}):
+          tag.replaceWith(tag.string)
+        return soup
+
+    extra_css = '''
+                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:medium;}
+                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+		            '''
+

resources/recipes/estadao.recipe

@@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2010, elsuave'
 '''
 estadao.com.br
 '''
@@ -10,12 +10,12 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class Estadao(BasicNewsRecipe):
     title                 = 'O Estado de S. Paulo'
-    __author__            = 'Darko Miletic'
+    __author__            = 'elsuave (modified from Darko Miletic)'
     description           = 'News from Brasil in Portuguese'
     publisher             = 'O Estado de S. Paulo'
     category              = 'news, politics, Brasil'
     oldest_article        = 2
-    max_articles_per_feed = 100
+    max_articles_per_feed = 25
     no_stylesheets        = True
     use_embedded_content  = False
     encoding              = 'utf8'
@@ -30,13 +30,14 @@ class Estadao(BasicNewsRecipe):
 
     html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
 
-    keep_only_tags = [dict(name='div', attrs={'id':'c1'})]
+    keep_only_tags = [
+                          dict(name='div', attrs={'class':['bb-md-noticia','c5']})
+                     ]
 
     remove_tags = [
                      dict(name=['script','object','form','ul'])
-                    ,dict(name='div', attrs={'id':['votacao','estadaohoje']})
-                    ,dict(name='p', attrs={'id':'ctrl_texto'})
-                    ,dict(name='p', attrs={'class':'texto'})
+                    ,dict(name='div', attrs={'class':['fnt2 Color_04 bold','right fnt2 innerTop15 dvTmFont','™_01 right outerLeft15','tituloBox','tags']})
+                    ,dict(name='div', attrs={'id':['bb-md-noticia-subcom']})
                   ]
 
     feeds = [
@@ -51,13 +52,12 @@ class Estadao(BasicNewsRecipe):
               ,(u'Vida &', u'http://www.estadao.com.br/rss/vidae.xml')
             ]
 
-    def preprocess_html(self, soup):
-        ifr = soup.find('iframe')
-        if ifr:
-           ifr.extract()
-        for item in soup.findAll(style=True):
-            del item['style']
-        return soup
+
 
     language = 'pt'
 
+    def get_article_url(self, article):
+        url = BasicNewsRecipe.get_article_url(self, article)
+        if '/Multimidia/' not in url:
+            return url
+

src/calibre/ebooks/metadata/fetch.py

@@ -351,9 +351,13 @@ def search(title=None, author=None, publisher=None, isbn=None, isbndb_key=None,
     if len(results) > 1:
         if not results[0].comments or len(results[0].comments) == 0:
             for r in results[1:]:
-                if title.lower() == r.title[:len(title)].lower() and r.comments and len(r.comments):
-                    results[0].comments = r.comments
-                    break
+                try:
+                    if title and title.lower() == r.title[:len(title)].lower() \
+                            and r.comments and len(r.comments):
+                        results[0].comments = r.comments
+                        break
+                except:
+                    pass
         # Find a pubdate
         pubdate = None
         for r in results: