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

Replace relative link to complete link

Browse source
This commit is contained in:
Florent 2012-04-30 11:55:46 +02:00
commit c9aadbfb34
1 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

11
modules/ecrans/pages/article.py
View file

@ -1,4 +1,4 @@
"ArticlePage object for inrocks" "ArticlePage object for ecrans"
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright(C) 2011 Julien Hebert # Copyright(C) 2011 Julien Hebert
@ -22,7 +22,7 @@ from weboob.tools.capabilities.messages.genericArticle import GenericNewsPage, r
class ArticlePage(GenericNewsPage): class ArticlePage(GenericNewsPage):
"ArticlePage object for inrocks" "ArticlePage object for ecrans"
def on_loaded(self): def on_loaded(self):
self.main_div = self.document.getroot() self.main_div = self.document.getroot()
self.element_title_selector = "title" self.element_title_selector = "title"
@ -34,5 +34,12 @@ class ArticlePage(GenericNewsPage):
remove_from_selector_list(self.parser, element_body, ["p.auteur", "h4"]) remove_from_selector_list(self.parser, element_body, ["p.auteur", "h4"])
try_remove_from_selector_list(self.parser, element_body, ["p.tag", "div.alire", self.element_title_selector, "h4"]) try_remove_from_selector_list(self.parser, element_body, ["p.tag", "div.alire", self.element_title_selector, "h4"])
try_drop_tree(self.parser, element_body, "script") try_drop_tree(self.parser, element_body, "script")
for a in element_body.findall('.//a'):
if a.attrib["href"][0:7] != "http://":
a.attrib["href"] = "http://ecrans.fr/" + a.attrib["href"]
for img in element_body.xpath('.//img'):
if img.attrib["src"][0:7] != "http://":
img.attrib["src"] = "http://ecrans.fr/" + img.attrib["src"]
return self.parser.tostring(element_body) return self.parser.tostring(element_body)