From c23352fc224e7ad2c2bb09bcb72cc4cbb867377c Mon Sep 17 00:00:00 2001
From: Julien Veyssier <julien.veyssier@aiur.fr>
Date: Wed, 6 Mar 2013 15:29:13 +0100
Subject: [PATCH] [imdb] biography purified

---
 modules/imdb/pages.py                  | 12 ++++++------
 weboob/applications/cineoob/cineoob.py |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/modules/imdb/pages.py b/modules/imdb/pages.py
index 2b9c96dc..3e9dd7f4 100644
--- a/modules/imdb/pages.py
+++ b/modules/imdb/pages.py
@@ -48,13 +48,13 @@ class BiographyPage(BasePage):
     ''' Page containing biography of a person
     '''
     def get_biography(self):
-        bio = ''
+        bio = unicode()
         tn = self.parser.select(self.document.getroot(),'div#tn15content',1)
-        #for p in self.parser.select(tn,'p'):
-        #    bio += '\n\n%s'%p.text_content().strip()
-        # get children, append if label or tag = a,p,h...
-        bio = tn.text_content().strip()
-        if bio == "":
+        # we only read paragraphs, titles and links
+        for ch in tn.getchildren():
+            if ch.tag in ['p','h5','a']:
+                bio += '%s\n\n'%ch.text_content().strip()
+        if bio == u'':
             bio = NotAvailable
         return bio
 
diff --git a/weboob/applications/cineoob/cineoob.py b/weboob/applications/cineoob/cineoob.py
index fbebe677..1ab5e0bf 100644
--- a/weboob/applications/cineoob/cineoob.py
+++ b/weboob/applications/cineoob/cineoob.py
@@ -367,6 +367,6 @@ class Cineoob(ReplApplication):
             return 3
 
         for backend, bio in self.do('get_person_biography', person.id):
-            print bio
+            print '%s :\n\n%s' % (person.name,bio)
         if bio != NotAvailable:
             self.flush()