pages.py 2.63 KB
Newer Older
1 2 3 4 5
"ArticlePage object for presseurope"
# -*- coding: utf-8 -*-

# Copyright(C) 2012 Florent Fourcot
#
6
# This file is part of a weboob module.
7
#
8
# This weboob module is free software: you can redistribute it and/or modify
9 10 11 12
# 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.
#
13
# This weboob module is distributed in the hope that it will be useful,
14 15 16 17 18
# 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
19
# along with this weboob module. If not, see <http://www.gnu.org/licenses/>.
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 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71

from weboob.browser.pages import AbstractPage
from weboob.browser.filters.html import CSS, CleanHTML


class PresseuropPage(AbstractPage):
    "PresseuropPage object for presseurop"
    _selector = CSS
    PARENT = 'genericnewspaper'
    PARENT_URL = 'generic_news_page'

    def on_loaded(self):
        self.main_div = self.doc.getroot()
        self.element_title_selector = "title"
        self.element_author_selector = "a[rel=author], div.profilecartoontext>p>a"
        self.element_body_selector = "div.block, div.panel, div.bodytext"

    def get_body(self):
        element_body = self.get_element_body()
        self.try_drop_tree(element_body, "li.button-social")
        self.try_drop_tree(element_body, "div.sharecount")
        self.try_drop_tree(element_body, "p.ruledtop")
        self.try_drop_tree(element_body, "p.ctafeedback")
        self.try_drop_tree(element_body, "aside.articlerelated")
        self.try_drop_tree(element_body, "div.sharecount")
        self.try_drop_tree(element_body, "iframe")
        self.clean_relativ_urls(element_body, "http://presseurop.eu")
        return CleanHTML('.')(element_body)

    def get_title(self):
        title = super(self.__class__, self).get_title()
        title = title.split('|')[0]
        return title

    def get_author(self):
        author = super(self.__class__, self).get_author()
        try:
            source = self.doc.getroot().xpath(
                    "//span[@class='sourceinfo']/a")[0]
            source = source.text
            author = author + " | " + source
            return author
        except:
            return author

    def get_daily_date(self):
        plink = self.doc.getroot().xpath("//p[@class='w200']")
        if len(plink) > 0:
            link = plink[0].xpath('a')[0]
            date = link.attrib['href'].split('/')[3]
            return date
        return None