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