From 6de89762ee42194e564d0c9fa546f20305c1b4c7 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Fri, 21 May 2010 09:47:48 -0600
Subject: [PATCH] Der Tagesspiegel by ipaschke

---
 resources/recipes/tagesspiegel.recipe | 86 +++++++++++++++++++++++++++
 1 file changed, 86 insertions(+)
 create mode 100644 resources/recipes/tagesspiegel.recipe

diff --git a/resources/recipes/tagesspiegel.recipe b/resources/recipes/tagesspiegel.recipe
new file mode 100644
index 0000000000..e5d2600ae0
--- /dev/null
+++ b/resources/recipes/tagesspiegel.recipe
@@ -0,0 +1,86 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010 Ingo Paschke <ipaschke@gmail.com>'
+
+'''
+Fetch Tagesspiegel.
+'''
+import string, re
+from calibre import strftime
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class TagesspiegelRSS(BasicNewsRecipe):
+    title          = u'Der Tagesspiegel'
+    __author__ = 'ipaschke'
+    language = 'de'
+    oldest_article = 7
+    max_articles_per_feed = 100
+
+    extra_css = '''
+                .hcf-overline{color:#990000; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;display:block}
+                .hcf-teaser{font-family:Verdana,Arial,Helvetica;font-size:x-small;margin-top:0}
+                h1{font-family:Arial,Helvetica,sans-serif;font-size:large;clear:right;}
+                .hcf-caption{color:#666666; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
+                .hcf-copyright{color:#666666; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
+                .hcf-article{font-family:Arial,Helvetica;font-size:x-small}
+                .quote{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:x-small}
+                .quote .cite{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:xx-small}
+                .hcf-inline-left{float:left;margin-right:15px;position:relative;}
+                .hcf-inline-right{float:right;margin-right:15px;position:relative;}
+	            .hcf-smart-box{font-family: Arial, Helvetica, sans-serif; font-size: xx-small; margin: 0px 15px 8px 0px; width: 300px;}
+                '''
+
+    no_stylesheets = True
+    no_javascript = True
+    remove_empty_feeds = True
+    encoding = 'utf-8'
+
+    keep_only_tags = dict(name='div', attrs={'class':["hcf-article"]})
+    remove_tags = [
+                    dict(name='link'), dict(name='iframe'),dict(name='style'),dict(name='meta'),dict(name='button'),
+                    dict(name='div', attrs={'class':["hcf-jump-to-comments","hcf-clear","hcf-magnify hcf-media-control"] }),
+                    dict(name='span', attrs={'class':["hcf-mainsearch",] }),
+                    dict(name='ul', attrs={'class':["hcf-tools"] }),
+                  ]
+
+    def parse_index(self):
+        soup = self.index_to_soup('http://www.tagesspiegel.de/zeitung/')
+
+        def feed_title(div):
+            return ''.join(div.findAll(text=True, recursive=False)).strip()
+
+        articles = {}
+        key = None
+        ans = []
+
+        for div in soup.findAll(True, attrs={'class':['hcf-teaser', 'hcf-header', 'story headline']}):
+
+             if div['class'] == 'hcf-header':
+                 key = string.capwords(feed_title(div.em.a))
+                 articles[key] = []
+                 ans.append(key)
+
+             elif div['class'] == 'hcf-teaser' and getattr(div.contents[0],'name','') == 'h2':
+                 a = div.find('a', href=True)
+                 if not a:
+                     continue
+                 url = 'http://www.tagesspiegel.de' + a['href']
+                 title = self.tag_to_string(a, use_alt=True).strip()
+                 description = ''
+                 pubdate = strftime('%a, %d %b')
+                 summary = div.find('p', attrs={'class':'hcf-teaser'})
+                 if summary:
+                     description = self.tag_to_string(summary, use_alt=False)
+
+                 feed = key if key is not None else 'Uncategorized'
+                 if not articles.has_key(feed):
+                     articles[feed] = []
+                 if not 'podcasts' in url:
+                     articles[feed].append(
+                               dict(title=title, url=url, date=pubdate,
+                                    description=re.sub('mehr$', '', description),
+                                    content=''))
+
+        ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
+
+        return ans
+