1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
|
"ArticlePage object for ecrans"
# -*- coding: utf-8 -*-
# Copyright(C) 2011 Julien Hebert
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
from weboob.tools.capabilities.messages.genericArticle import GenericNewsPage, remove_from_selector_list, try_remove_from_selector_list, try_drop_tree
class ArticlePage(GenericNewsPage):
"ArticlePage object for ecrans"
def on_loaded(self):
self.main_div = self.document.getroot()
self.element_title_selector = "title"
self.element_author_selector = "p.auteur>a"
self.element_body_selector = "div.bloc_article_01"
def get_body(self):
element_body = self.get_element_body()
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_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)
|
