# -*- coding: utf-8 -*-
"""
Copyright(C) 2008-2010 Romain Bignon
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, version 3 of the License.
This program 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 General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
"""
import re
from datetime import datetime
from dateutil import tz
from logging import error, warning
from mechanize import FormNotFoundError
from weboob.backends.aum.pages.base import PageBase
from weboob.backends.aum.exceptions import AdopteCantPostMail
from weboob.backends.aum.mail import Mail
class MailParser(Mail):
"""
|
|
|
27 octobre 2008, 01:11:32, nouveau
Moi en g�n�ral j'aime sortir tout simplement dans des bars, pour discuter avec mes amis et/ou coll�gues, et rencontrer des gens. Sinon je fais de la guitare, et je d�veloppe des projets perso.
|
|
| | |
|
"""
DATETIME_REGEXP = re.compile(u'([0-9]{1,2}) ([a-zéû]*) ([0-9]{4}), ([0-9]{2}):([0-9]{2}):([0-9]{2})(.*)')
months = [u'', u'janvier', u'février', u'mars', u'avril', u'mai', u'juin', u'juillet', u'août', u'septembre', u'octobre', u'novembre', u'décembre']
SMILEY_REGEXP = re.compile('http://s.adopteunmec.com/img/smile/([0-9]+).gif')
smileys = {0: ':)',
1: ':D',
2: ':o',
3: ':p',
4: ';)',
5: ':(',
6: ':$',
7: ':\'(',
11: ':#',
14: ':\\',
15: ':|',
10: '(L)',
}
def __init__(self, id, name, tr):
# implicit
Mail.__init__(self, id, name)
self.tr = tr.childNodes[0].childNodes[1].childNodes[0].childNodes[0]
tds = self.tr.childNodes
counter = 0
for td in tds:
if not hasattr(td, 'tagName') or td.tagName != u'td':
continue
counter += 1
if counter == 3:
date = u''
for child in td.childNodes[1].childNodes:
if hasattr(child, 'data'):
date += child.data
self.parse_date(date)
content = ''
for c in td.childNodes[3].childNodes:
if hasattr(c, 'data'):
content += ''.join(c.data.split('\n')) # to strip \n
elif hasattr(c, 'tagName'):
if c.tagName == 'br':
content += '\n'
elif c.tagName == 'img' and c.hasAttribute('src'):
m = self.SMILEY_REGEXP.match(c.getAttribute('src'))
if m and self.smileys.has_key(int(m.group(1))):
try:
content += self.smileys[int(m.group(1))]
except KeyError:
error('Mail: unable to find this smiley: %s' % c.getAttribute('src'))
self.content = content
break
self.parse_profile_link()
self.parse_from()
def parse_date(self, date_str):
# To match regexp, we have to remove any return chars in string
# before the status ('nouveau', 'lu', etc)
date_str = u''.join(date_str.split(u'\n'))
m = self.DATETIME_REGEXP.match(date_str)
if m:
day = int(m.group(1))
month = self.months.index(m.group(2))
year = int(m.group(3))
hour = int(m.group(4))
minute = int(m.group(5))
sec = int(m.group(6))
# build datetime object with local timezone
d = datetime(year, month, day, hour, minute, sec, tzinfo=tz.tzlocal())
# then, convert it to UTC timezone
d = d.astimezone(tz.tzutc())
# and get timestamp
self.date = d
if m.group(7).find('nouveau') >= 0:
self.new = True
else:
error('Error: unable to parse the datetime string "%s"' % date_str)
def parse_profile_link(self):
tables = self.tr.getElementsByTagName('div')
for table in tables:
if table.hasAttribute('class') and table.getAttribute('class') == 'mini' and table.hasAttribute('onclick'):
text = table.getAttribute('onclick')
regexp = re.compile("window.location='(.*)'")
m = regexp.match(text)
if m:
self.profile_link = m.group(1)
return
warning('Unable to find the profile URL in the message %s@%s' % (self.get_from(), self.get_id()))
def parse_from(self):
tds = self.tr.getElementsByTagName('div')
for td in tds:
if not td.hasAttribute('class') or td.getAttribute('class') != 'mini_pseudo':
continue
if td.childNodes:
self.sender = td.childNodes[0].data
return
warning('Warning: unable to find from in the mail %s' % self.get_id())
class ContactThreadPage(PageBase):
"""
"""
def post(self, content):
try:
self.browser.select_form(name="sendMsg")
if isinstance(content, unicode):
content = content.encode('iso-8859-15', 'replace')
self.browser['message'] = content
self.browser.submit() # submit current form
except FormNotFoundError, e:
error = 'Unknown error (%s)' % e
p_list = self.document.getElementsByTagName('p')
for p in p_list:
if p.hasAttribute('align') and p.getAttribute('align') == 'center':
error = p.firstChild.data
break
raise AdopteCantPostMail(error)
"""
"""
id_regexp = re.compile("/thread.php\?id=([0-9]+)")
def loaded(self):
self.items = []
a_list = self.document.getElementsByTagName('a')
self.id = 0
for a in a_list:
if a.hasAttribute('href'):
m = self.id_regexp.match(a.getAttribute('href'))
if m:
self.id = int(m.group(1))
break
self.name = ''
big_list = self.document.getElementsByTagName('big')
for big in big_list:
child = big.firstChild
if hasattr(child, 'tagName') and child.tagName == u'b':
self.name = child.firstChild.data
break
tables = self.document.getElementsByTagName('table')
table = None
for t in tables:
if t.hasAttribute('style') and t.getAttribute('style') == 'width:700px;background:black':
table = t
break
if not table:
# It is probably the 'sent' page
return
for tag in table.childNodes[1].childNodes[1:]:
if not hasattr(tag, 'tagName') or tag.tagName != u'tr':
continue
if not tag.hasAttribute('valign'):
continue
mail = MailParser(self.id, self.name, tag)
if self.items:
self.items[-1].reply_date = mail.get_date_int()
self.items += [mail]
def get_mails(self):
return self.items
| 
