diff options
| author | cedricbonhomme <devnull@localhost> | 2010-02-23 21:47:02 +0100 |
|---|---|---|
| committer | cedricbonhomme <devnull@localhost> | 2010-02-23 21:47:02 +0100 |
| commit | 0b44fc9a8081af991e5335351b41c7a9a0221d61 (patch) | |
| tree | c6938e7e94e250ed5af46aba4679baae8e62ae65 /pyAggr3g470r.py | |
| parent | Bug fix: HTML tags are skipped for the search. Added a page _Management of fe... (diff) | |
| download | newspipe-0b44fc9a8081af991e5335351b41c7a9a0221d61.tar.gz newspipe-0b44fc9a8081af991e5335351b41c7a9a0221d61.tar.bz2 newspipe-0b44fc9a8081af991e5335351b41c7a9a0221d61.zip | |
Statistics on words are only processed on articles content.
Diffstat (limited to 'pyAggr3g470r.py')
| -rw-r--r-- | pyAggr3g470r.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/pyAggr3g470r.py b/pyAggr3g470r.py index 1ab9448b..d72a6008 100644 --- a/pyAggr3g470r.py +++ b/pyAggr3g470r.py @@ -152,7 +152,7 @@ class Root: article_content = "" for rss_feed_id in self.dic.keys(): for article in self.dic[rss_feed_id]: - article_content += remove_html_tags(article[4].encode('utf-8') + article[2].encode('utf-8')) + article_content += remove_html_tags(article[4].encode('utf-8')) words_gen = (word.strip(punctuation).lower() \ for word in article_content.split() \ |