Fix #2257 (Updated recipes with fixes for epub image problem)

src/calibre/web/feeds/recipes/recipe_24sata_rs.py

@@ -9,6 +9,7 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
 
 import re
 from calibre.web.feeds.recipes import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
 class Ser24Sata(BasicNewsRecipe):
     title                 = '24 Sata - Sr'
@@ -39,14 +40,30 @@ class Ser24Sata(BasicNewsRecipe):
 
     feeds = [(u'Vesti Dana', u'http://www.24sata.rs/rss.php')]
 
+    def cleanup_image_tags(self,soup):
+        for item in soup.findAll('img'):
+            for attrib in ['height','width','border','align']:
+                if item.has_key(attrib):
+                   del item[attrib]
+            oldParent = item.parent
+            myIndex = oldParent.contents.index(item)
+            item.extract()
+            divtag = Tag(soup,'div')
+            brtag  = Tag(soup,'br')
+            oldParent.insert(myIndex,divtag)
+            divtag.append(item)
+            divtag.append(brtag)
+        return soup
+
     def preprocess_html(self, soup):
         soup.html['xml:lang'] = 'sr-Latn-RS'
         soup.html['lang']     = 'sr-Latn-RS'
         mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
         soup.head.insert(0,mtag)
-        return soup
+        return self.cleanup_image_tags(soup)
 
     def print_version(self, url):
         article, sep, rest = url.partition('#')
-        return article.replace('/show.php','/_print.php')
+        article_base, sep2, article_id = article.partition('id=')
+        return 'http://www.24sata.co.rs/_print.php?id=' + article_id
 

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

@@ -8,11 +8,12 @@ blic.rs
 
 import re
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
 class Blic(BasicNewsRecipe):
-    title                 = u'Blic'
-    __author__            = u'Darko Miletic'
-    description           = u'Blic.co.yu online verzija najtiraznije novine u Srbiji donosi najnovije vesti iz Srbije i sveta, komentare, politicke analize, poslovne i ekonomske vesti, vesti iz regiona, intervjue, informacije iz kulture, reportaze, pokriva sve sportske dogadjaje, detaljan tv program, nagradne igre, zabavu, fenomenalni Blic strip, dnevni horoskop, arhivu svih dogadjaja'    
+    title                 = 'Blic'
+    __author__            = 'Darko Miletic'
+    description           = 'Blic.co.yu online verzija najtiraznije novine u Srbiji donosi najnovije vesti iz Srbije i sveta, komentare, politicke analize, poslovne i ekonomske vesti, vesti iz regiona, intervjue, informacije iz kulture, reportaze, pokriva sve sportske dogadjaje, detaljan tv program, nagradne igre, zabavu, fenomenalni Blic strip, dnevni horoskop, arhivu svih dogadjaja'    
     publisher             = 'RINGIER d.o.o.'
     category              = 'news, politics, Serbia'
     oldest_article        = 2
@@ -30,7 +31,7 @@ class Blic(BasicNewsRecipe):
                         , '--ignore-tables'
                         ]
     
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em} "' 
     
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 
@@ -44,10 +45,26 @@ class Blic(BasicNewsRecipe):
         start_url, question, rest_url = url.partition('?')
         return u'http://www.blic.rs/_print.php?' + rest_url
 
+    def cleanup_image_tags(self,soup):
+        for item in soup.findAll('img'):
+            for attrib in ['height','width','border','align']:
+                if item.has_key(attrib):
+                   del item[attrib]
+            oldParent = item.parent
+            myIndex = oldParent.contents.index(item)
+            item.extract()
+            divtag = Tag(soup,'div')
+            brtag  = Tag(soup,'br')
+            oldParent.insert(myIndex,divtag)
+            divtag.append(item)
+            divtag.append(brtag)
+        return soup
+      
+    
     def preprocess_html(self, soup):
         mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
         soup.head.insert(0,mtag)    
         for item in soup.findAll(style=True):
             del item['style']
-        return soup
+        return self.cleanup_image_tags(soup)
         

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

@@ -8,9 +8,10 @@ nspm.rs
 
 import re
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
 class Nspm(BasicNewsRecipe):
-    title                 = u'Nova srpska politicka misao'
+    title                 = 'Nova srpska politicka misao'
     __author__            = 'Darko Miletic'
     description           = 'Casopis za politicku teoriju i drustvena istrazivanja'    
     publisher             = 'NSPM'
@@ -36,7 +37,7 @@ class Nspm(BasicNewsRecipe):
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
     remove_tags        = [
-                            dict(name=['a','img','link','object','embed'])
+                            dict(name=['link','object','embed'])
                            ,dict(name='td', attrs={'class':'buttonheading'})
                          ]
     
@@ -50,6 +51,21 @@ class Nspm(BasicNewsRecipe):
     def print_version(self, url):
         return url.replace('.html','/stampa.html')
 
+    def cleanup_image_tags(self,soup):
+        for item in soup.findAll('img'):
+            for attrib in ['height','width','border','align']:
+                if item.has_key(attrib):
+                   del item[attrib]
+            oldParent = item.parent
+            myIndex = oldParent.contents.index(item)
+            item.extract()
+            divtag = Tag(soup,'div')
+            brtag  = Tag(soup,'br')
+            oldParent.insert(myIndex,divtag)
+            divtag.append(item)
+            divtag.append(brtag)
+        return soup
+
     def preprocess_html(self, soup):
         lng = 'sr-Latn-RS'
         soup.html['xml:lang'] = lng
@@ -59,4 +75,4 @@ class Nspm(BasicNewsRecipe):
            ftag['content'] = lng
         for item in soup.findAll(style=True):
             del item['style']     
-        return soup
+        return self.cleanup_image_tags(soup)

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

@@ -63,6 +63,17 @@ class Tomshardware(BasicNewsRecipe):
            rind = 'http://www.tomshardware.com/review_print.php?p1='
         return rind + article_id        
 
+    def cleanup_image_tags(self,soup):
+        for item in soup.findAll('img'):
+            for attrib in ['height','width','border','align']:
+                if item.has_key(attrib):
+                   del item[attrib]
+        return soup
+
     def preprocess_html(self, soup):
         del(soup.body['onload'])
-        return soup
+        for item in soup.findAll(style=True):
+            del item['style']
+        for it in soup.findAll('span'):
+            it.name="div"
+        return self.cleanup_image_tags(soup)