Showing 2 changed files with 11 additions and 0 deletions
+1
README.md
... ...
@@ -27,3 +27,4 @@ The article content (i.e. Feed link) is fetch automatically and the content is e
27 27
 - ./newsfetch.py --url http://www.vice.com/fr/rss
28 28
 - ./newsfetch.py --url http://www.lemonde.fr/rss/une.xml
29 29
 - ./newsfetch.py --url https://www.slate.fr/rss.xml
30
+- ./newsfetch.py --url http://www.lesinrocks.com/feeds/feed-a-la-une/
+10
newsfetch.py
... ...
@@ -175,6 +175,16 @@ for article in articles:
175 175
   content = soup_mysite.find("article")
176 176
   if content == None:
177 177
     content = soup_mysite.find('div', attrs={'class':'article-page'})
178
+  
179
+  if content == None:
180
+    #~ content = soup_mysite.find('div', attrs={'id':'block-article'})
181
+    only_text=soup_mysite.find('div', attrs={'id':'the-content'})
182
+    content = "<h1>{:s}</h1><h3>{:s}</h3>{:s}".format(article.title,article.summary,only_text)
183
+    #~ content += soup_mysite.find('div', attrs={'id':'the-content'})
184
+    #~ content = soup_mysite.find('div', attrs={'class':'article-top'})
185
+    #~ content = soup_mysite.find('div', attrs={'class':'inner clearfix'})
186
+    
187
+    #~ <div id="block-article" class="article" itemscope itemtype="Article">
178 188
     
179 189
   article.content_only = str(content)
180 190
   article.content_only = article.content_only.replace(" href=\"/", " href=\"http://www.lemonde.fr/")