_ Git - youtube-dl/blob - youtube_dl/extractor/tubitv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import codecs
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_urllib_parse,
  10     compat_urllib_request
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     int_or_none,
  15 )
  16
  17
  18 class TubiTvIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?tubitv\.com/video\?id=(?P<id>[0-9]+)'
  20     _LOGIN_URL = 'http://tubitv.com/login'
  21     _NETRC_MACHINE = 'tubitv'
  22     _TEST = {
  23         'url': 'http://tubitv.com/video?id=54411&title=The_Kitchen_Musical_-_EP01',
  24         'info_dict': {
  25             'id': '54411',
  26             'ext': 'mp4',
  27             'title': 'The Kitchen Musical - EP01',
  28             'thumbnail': 're:^https?://.*\.png$',
  29             'description': 'md5:37532716166069b353e8866e71fefae7',
  30             'duration': 2407,
  31         },
  32         'params': {
  33             'skip_download': 'HLS download',
  34         },
  35     }
  36
  37     def _login(self):
  38         (username, password) = self._get_login_info()
  39         if username is None:
  40             return
  41         self.report_login()
  42         form_data = {
  43             'username': username,
  44             'password': password,
  45         }
  46         payload = compat_urllib_parse.urlencode(form_data).encode('utf-8')
  47         request = compat_urllib_request.Request(self._LOGIN_URL, payload)
  48         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  49         login_page = self._download_webpage(
  50             request, None, False, 'Wrong login info')
  51         if not re.search(r'id="tubi-logout"', login_page):
  52             raise ExtractorError(
  53                 'Login failed (invalid username/password)', expected=True)
  54
  55     def _real_initialize(self):
  56         self._login()
  57
  58     def _real_extract(self, url):
  59         video_id = self._match_id(url)
  60
  61         webpage = self._download_webpage(url, video_id)
  62         if re.search(r"<(?:DIV|div) class='login-required-screen'>", webpage):
  63             self.raise_login_required('This video requires login')
  64
  65         title = self._og_search_title(webpage)
  66         description = self._og_search_description(webpage)
  67         thumbnail = self._og_search_thumbnail(webpage)
  68         duration = int_or_none(self._html_search_meta(
  69             'video:duration', webpage, 'duration'))
  70
  71         apu = self._search_regex(r"apu='([^']+)'", webpage, 'apu')
  72         m3u8_url = codecs.decode(apu, 'rot_13')[::-1]
  73         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
  74
  75         return {
  76             'id': video_id,
  77             'title': title,
  78             'formats': formats,
  79             'thumbnail': thumbnail,
  80             'description': description,
  81             'duration': duration,
  82         }