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

fix parser + new pages

Browse source
This commit is contained in:
juke 2011-02-25 18:56:46 +01:00
commit 719d91a0dd
2 changed files with 11 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

1
weboob/backends/lefigaro/browser.py
View file

@ -44,6 +44,7 @@ class NewspaperFigaroBrowser(BaseBrowser):
"http://www.lefigaro.fr/programmes-tele/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/le-talk/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/sortir-paris/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/autres-sports/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/immobilier/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/environnement/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/rugby/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,

15
weboob/backends/lefigaro/pages/article.py
View file

@ -16,7 +16,7 @@
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
from weboob.tools.parsers.lxmlparser import select
from weboob.tools.parsers.lxmlparser import select, SelectElementException
from weboob.tools.genericArticle import GenericNewsPage, try_remove
class ArticlePage(GenericNewsPage):
@ -30,19 +30,24 @@ class ArticlePage(GenericNewsPage):
def get_body(self):
element_body = self.get_element_body()
h1_title = select(element_body, self.element_title_selector, 1)
div_infos = select(element_body, "div.infos", 1)
el_script = select(element_body, "script", 1)
try:
el_script = select(element_body, "script", 1)
except SelectElementException:
pass
else:
el_script.drop_tree()
element_body.remove(h1_title)
element_body.remove(div_infos)
try_remove(element_body, "div.infos")
try_remove(element_body, "div.photo")
try_remove(element_body, "div.art_bandeau_bottom")
try_remove(element_body, "div.view")
try_remove(element_body, "span.auteur_long")
try_remove(element_body, "#toolsbar")
el_script.drop_tree()
element_body.find_class("texte")[0].drop_tag()
element_body.tag = "div"
return self.browser.parser.tostring(element_body)