Пример #1
0
 def iter_threads(self):
     table = self.parser.select(self.document.getroot(), "table#listeMessages", 1)
     for tr in table.xpath("./tr"):
         if tr.attrib.get("class", "") not in ("msgLu", "msgNonLu"):
             continue
         author = unicode(self.parser.select(tr, "td.colEmetteur", 1).text)
         link = self.parser.select(tr, "td.colObjet a", 1)
         date_raw = self.parser.select(tr, "td.colDate1", 1).attrib["data"]
         jsparams = re.search("\((.+)\)", link.attrib["onclick"]).groups()[0]
         jsparams = [i.strip("'\" ") for i in jsparams.split(",")]
         page_id, _id, unread = jsparams
         # this means unread on the website
         unread = False if unread == "false" else True
         # 2012/02/29:01h30min45sec
         dt_match = re.match("(\d+)/(\d+)/(\d+):(\d+)h(\d+)min(\d+)sec", date_raw).groups()
         dt_match = [int(d) for d in dt_match]
         thread = Thread(_id)
         thread._link_id = (page_id, unread)
         thread.date = datetime(*dt_match)
         thread.title = unicode(link.text)
         message = Message(thread, 0)
         message.set_empty_fields(None)
         message.flags = message.IS_HTML
         message.title = thread.title
         message.date = thread.date
         message.sender = author
         message.content = NotLoaded  # This is the only thing we are missing
         thread.root = message
         yield thread
Пример #2
0
 def iter_threads(self):
     table = self.parser.select(self.document.getroot(),
                                'table#listeMessages', 1)
     for tr in table.xpath('./tr'):
         if tr.attrib.get('class', '') not in ('msgLu', 'msgNonLu'):
             continue
         author = unicode(self.parser.select(tr, 'td.colEmetteur', 1).text)
         link = self.parser.select(tr, 'td.colObjet a', 1)
         date_raw = self.parser.select(tr, 'td.colDate1', 1).attrib['data']
         jsparams = re.search('\((.+)\)',
                              link.attrib['onclick']).groups()[0]
         jsparams = [i.strip('\'" ') for i in jsparams.split(',')]
         page_id, _id, unread = jsparams
         # this means unread on the website
         unread = False if unread == "false" else True
         # 2012/02/29:01h30min45sec
         dt_match = re.match('(\d+)/(\d+)/(\d+):(\d+)h(\d+)min(\d+)sec',
                             date_raw).groups()
         dt_match = [int(d) for d in dt_match]
         thread = Thread(_id)
         thread._link_id = (page_id, unread)
         thread.date = datetime(*dt_match)
         thread.title = unicode(link.text)
         message = Message(thread, 0)
         message.set_empty_fields(None)
         message.flags = message.IS_HTML
         message.title = thread.title
         message.date = thread.date
         message.sender = author
         message.content = NotLoaded  # This is the only thing we are missing
         thread.root = message
         yield thread