Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tubitv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     sanitized_Request,
  11     urlencode_postdata,
  12     parse_iso8601,
  13 )
  14
  15
  16 class TubiTvIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?tubitv\.com/video/(?P<id>[0-9]+)'
  18     _LOGIN_URL = 'http://tubitv.com/login'
  19     _NETRC_MACHINE = 'tubitv'
  20     _TEST = {
  21         'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
  22         'info_dict': {
  23             'id': '283829',
  24             'ext': 'mp4',
  25             'title': 'The Comedian at The Friday',
  26             'description': 'A stand up comedian is forced to look at the decisions in his life while on a one week trip to the west coast.',
  27             'uploader': 'Indie Rights Films',
  28             'upload_date': '20160111',
  29             'timestamp': 1452555979,
  30         },
  31         'params': {
  32             'skip_download': 'HLS download',
  33         },
  34     }
  35
  36     def _login(self):
  37         (username, password) = self._get_login_info()
  38         if username is None:
  39             return
  40         self.report_login()
  41         form_data = {
  42             'username': username,
  43             'password': password,
  44         }
  45         payload = urlencode_postdata(form_data)
  46         request = sanitized_Request(self._LOGIN_URL, payload)
  47         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  48         login_page = self._download_webpage(
  49             request, None, False, 'Wrong login info')
  50         if not re.search(r'id="tubi-logout"', login_page):
  51             raise ExtractorError(
  52                 'Login failed (invalid username/password)', expected=True)
  53
  54     def _real_initialize(self):
  55         self._login()
  56
  57     def _real_extract(self, url):
  58         video_id = self._match_id(url)
  59         video_data = self._download_json(
  60             'http://tubitv.com/oz/videos/%s/content' % video_id, video_id)
  61         title = video_data['n']
  62
  63         formats = self._extract_m3u8_formats(
  64             video_data['mh'], video_id, 'mp4', 'm3u8_native')
  65         self._sort_formats(formats)
  66
  67         subtitles = {}
  68         for sub in video_data.get('sb', []):
  69             sub_url = sub.get('u')
  70             if not sub_url:
  71                 continue
  72             subtitles.setdefault(sub.get('l', 'en'), []).append({
  73                 'url': sub_url,
  74             })
  75
  76         return {
  77             'id': video_id,
  78             'title': title,
  79             'formats': formats,
  80             'subtitles': subtitles,
  81             'thumbnail': video_data.get('ph'),
  82             'description': video_data.get('d'),
  83             'duration': int_or_none(video_data.get('s')),
  84             'timestamp': parse_iso8601(video_data.get('u')),
  85             'uploader': video_data.get('on'),
  86         }