krytyka polityczna

recipes/kp.recipe

@@ -0,0 +1,53 @@
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class KrytykaPolitycznaRecipe(BasicNewsRecipe):
+    __license__ = 'GPL v3'
+    __author__ = u'intromatyk <intromatyk@gmail.com>'
+    language = 'pl'
+    version = 1
+
+    title = u'Krytyka Polityczna'
+    category = u'News'
+    description = u' Lewicowe pismo zaangażowane w bieg spraw publicznych w Polsce.'
+    cover_url=''
+    remove_empty_feeds= True
+    no_stylesheets=True
+    oldest_article = 7
+    max_articles_per_feed = 100000
+    recursions = 0
+
+    no_stylesheets = True
+    remove_javascript = True
+    simultaneous_downloads = 3
+
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'h1', attrs = {'class' : 'print-title'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'print-content'}))
+
+    remove_tags =[]
+    remove_tags.append(dict(attrs = {'class' : ['field field-type-text field-field-story-switch', 'field field-type-filefield field-field-story-temp' , 'field field-type-text field-field-story-author', 'field field-type-text field-field-story-lead-switch']}))
+
+    extra_css = '''
+                    body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
+                    td.contentheading{font-size: large; font-weight: bold;}
+                    '''    
+
+    feeds          = [
+                            ('Wszystkie', 'http://www.krytykapolityczna.pl/rss.xml')
+                          ]
+      
+    def print_version(self, url):
+        soup = self.index_to_soup(url)
+        print_ico = soup.find(attrs = {'class' : 'print-page'})
+        print_uri = print_ico['href']
+        self.log('PRINT', print_uri)
+        return 'http://www.krytykapolityczna.pl/' + print_uri
+
+    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