# -*- coding: utf-8 -*- # Copyright(C) 2008-2011 Romain Bignon # # 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 . import re from datetime import datetime, timedelta from dateutil import tz from logging import warning from weboob.backends.aum.pages.base import PageBase class ContactItem: u"""
 
Hen
19ans, Montreuil Comme ça, on est deux.
il y a 1 heure nouveau       """ fields = ['thread_link', 'photo', 'useless3', 'name', 'resume', 'status', 'useless', 'remove', 'useless2'] def __init__(self, tr): self.tr = tr self.id = 0 def __get_element(self, id): return self.tr.getElementsByTagName('td')[self.fields.index(id)] def get_name(self): tag = self.__get_element('name') node = tag.getElementsByTagName('b')[0].firstChild if node: name = node.data else: # it is possible if the user has left site and hasn't any nickname name = '' return name def get_status(self): tag = self.__get_element('status') return tag.firstChild.data def is_new(self): return self.get_status() == u'nouveau' def is_answered(self): return self.get_status() == u'répondu' def get_resume(self): tag = self.__get_element('resume') return tag.getElementsByTagName('b')[0].firstChild.data.strip() def get_suppr_id(self): tag = self.__get_element('remove') return tag.getElementsByTagName('input')[0].getAttribute('id').split('_')[-1] LASTMSG_RE = re.compile('il y a (\d+) (\w+)') def get_lastmsg_date(self): tag = self.__get_element('resume') s = tag.childNodes[3].data m = self.LASTMSG_RE.match(s) if m: d = {'secondes': 1, 'seconde': 1, 'minutes': 60, 'minute': 60, 'heures': 3600, 'heure': 3600, 'jours': 24*3600, 'jour': 24*3600, 'mois': 24*3600*30, } try: i = int(m.group(1)) * d[m.group(2)] except KeyError: warning('Unable to parse lastmsg ("%s" is not a valid unit)' % m.group(2)) return None else: return datetime.now(tz=tz.tzutc()) - timedelta(seconds=i) else: warning('Unable to parse lastmsg [%s]' % s) return None def get_id(self): if self.id: return self.id tag = self.__get_element('thread_link') text = tag.getAttribute('onclick') regexp = re.compile("window.location='/thread.php\?id=(\d+)'") m = regexp.match(text) if m: self.id = int(m.group(1)) return self.id warning('Unable to parse ID (%s)' % text) return 0 class ContactListPage(PageBase): def on_loaded(self): self.items = [] form = self.document.getElementsByTagName('form') if not form: return tags = form[0].childNodes[3].childNodes[1].childNodes for tag in tags: if not hasattr(tag, 'tagName') or tag.tagName != u'tr': continue if tag.hasAttribute('bgcolor'): continue self.items += [ContactItem(tag)] def get_contact_list(self): return self.items