nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Better cleanup of generic articles and lefigaro

Browse source 
try_drop_tree() was only removing the first result.
closes #725
This commit is contained in:
Laurent Bachelier 2012-02-01 01:10:26 +01:00
commit 57ce35cef1
3 changed files with 47 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

30
modules/lefigaro/pages/article.py
View file

@ -33,10 +33,36 @@ class ArticlePage(GenericNewsPage):
remove_from_selector_list(self.parser, element_body, [self.element_title_selector])
drop_comments(element_body)
try_drop_tree(self.parser, element_body, "script")
try_drop_tree(self.parser, element_body, "liste")
try_remove_from_selector_list(self.parser, element_body, ["div.infos", "div.photo", "div.art_bandeau_bottom", "div.view", "span.auteur_long", "#toolsbar", 'link'])
try_remove_from_selector_list(self.parser, element_body, ["div#article-comments", "div.infos", "div.photo", "div.art_bandeau_bottom", "div.view", "span.auteur_long", "#toolsbar", 'link'])
for image in self.parser.select(element_body, 'img'):
if image.attrib['src'].endswith('coeur-.gif'):
image.drop_tree()
for div in self.parser.select(element_body, 'div'):
if div.text == ' Player Figaro BFM ':
obj = div.getnext()
a = obj.getnext()
if obj.tag == 'object':
obj.drop_tree()
if a.tag == 'a' and 'BFM' in a.text:
a.drop_tree()
div.drop_tree()
# This part of the article seems manually generated.
for crappy_title in self.parser.select(element_body, 'p strong'):
if crappy_title.text == 'LIRE AUSSI :' or crappy_title.text == 'LIRE AUSSI:':
# Remove if it has only links
for related in crappy_title.getparent().itersiblings(tag='p'):
if len(related) == len(list(related.iterchildren(tag='a'))):
related.drop_tree()
else:
break
crappy_title.drop_tree()
element_body.find_class("texte")[0].drop_tag()
element_body.tag = "div"
return self.parser.tostring(element_body)