...

resources/recipes/discover_magazine.recipe

@@ -14,35 +14,56 @@ class DiscoverMagazine(BasicNewsRecipe):
 
     title = u'Discover Magazine'
     description = u'Science, Technology and the Future'
-    __author__ = 'Starson17 and Sujata Raman'
+    __author__ = 'Starson17'
     language = 'en'
 
     oldest_article = 33
     max_articles_per_feed = 20
-
     no_stylesheets = True
     remove_javascript = True
     use_embedded_content  = False
-    linearize_tables = True
     encoding = 'utf-8'
-
     extra_css = '.headline {font-size: x-large;} \n .fact {padding-top: 10pt}'
 
-
-    keep_only_tags = [ dict(name='div', attrs={'class':['content']}),]
     remove_tags = [
-                   dict(name='div', attrs={'class':['navigation','socialcontainer']}),
+                   dict(name='div', attrs={'id':['searchModule', 'mainMenu', 'tool-box']}),
-                   dict(name='span', attrs={'class':['sociableButton']}),
+                   dict(name='div', attrs={'id':['footer','teaser','already-subscriber','teaser-suite','related-articles']}),
-                   dict(name='p', attrs={'class':'footerBlogResume'}),
+                   dict(name='div', attrs={'class':['column']}),
-                   dict(name='h3', attrs={'id':['comments','respond']}),
+                   dict(name='img', attrs={'src':'http://discovermagazine.com/onebyone.gif'})]
-                   dict(name='ol', attrs={'class':'commentlist'}),
+
-                   ]
+    remove_tags_after = [dict(name='div', attrs={'class':'listingBar'})]
+
+    def append_page(self, soup, appendtag, position):
+        pager = soup.find('span',attrs={'class':'next'})
+        if pager:
+           nexturl = pager.a['href']
+           soup2 = self.index_to_soup(nexturl)
+           texttag = soup2.find('div', attrs={'class':'articlebody'})
+           newpos = len(texttag.contents)
+           self.append_page(soup2,texttag,newpos)
+           texttag.extract()
+           appendtag.insert(position,texttag)
+
+    def preprocess_html(self, soup):
+        mtag = '<meta http-equiv="Content-Language" content="en-US"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
+        soup.head.insert(0,mtag)
+        self.append_page(soup, soup.body, 3)
+        pager = soup.find('div',attrs={'class':'listingBar'})
+        if pager:
+           pager.extract()
+        return soup
 
     def postprocess_html(self, soup, first_fetch):
-
+        for tag in soup.findAll(text=re.compile('^This article is a sample')):
-        for tag in soup.findAll(text=re.compile('Related content')):
             tag.parent.extract()
-
+        for tag in soup.findAll(['table', 'tr', 'td']):
+            tag.name = 'div'
+        for tag in soup.findAll('div', attrs={'class':'discreet advert'}):
+            tag.extract()
+        for tag in soup.findAll('hr', attrs={'size':'1'}):
+            tag.extract()
+        for tag in soup.findAll('br'):
+            tag.extract()
         return soup
 
     feeds = [