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 )
  13
  14
  15 class TubiTvIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?:video|movies|tv-shows)/(?P<id>[0-9]+)'
  17     _LOGIN_URL = 'http://tubitv.com/login'
  18     _NETRC_MACHINE = 'tubitv'
  19     _GEO_COUNTRIES = ['US']
  20     _TESTS = [{
  21         'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
  22         'md5': '43ac06be9326f41912dc64ccf7a80320',
  23         'info_dict': {
  24             'id': '283829',
  25             'ext': 'mp4',
  26             'title': 'The Comedian at The Friday',
  27             '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.',
  28             'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434',
  29         },
  30     }, {
  31         'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://tubitv.com/movies/383676/tracker',
  35         'only_matching': True,
  36     }]
  37
  38     def _login(self):
  39         username, password = self._get_login_info()
  40         if username is None:
  41             return
  42         self.report_login()
  43         form_data = {
  44             'username': username,
  45             'password': password,
  46         }
  47         payload = urlencode_postdata(form_data)
  48         request = sanitized_Request(self._LOGIN_URL, payload)
  49         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  50         login_page = self._download_webpage(
  51             request, None, False, 'Wrong login info')
  52         if not re.search(r'id="tubi-logout"', login_page):
  53             raise ExtractorError(
  54                 'Login failed (invalid username/password)', expected=True)
  55
  56     def _real_initialize(self):
  57         self._login()
  58
  59     def _real_extract(self, url):
  60         video_id = self._match_id(url)
  61         video_data = self._download_json(
  62             'http://tubitv.com/oz/videos/%s/content' % video_id, video_id)
  63         title = video_data['title']
  64
  65         formats = self._extract_m3u8_formats(
  66             self._proto_relative_url(video_data['url']),
  67             video_id, 'mp4', 'm3u8_native')
  68         self._sort_formats(formats)
  69
  70         thumbnails = []
  71         for thumbnail_url in video_data.get('thumbnails', []):
  72             if not thumbnail_url:
  73                 continue
  74             thumbnails.append({
  75                 'url': self._proto_relative_url(thumbnail_url),
  76             })
  77
  78         subtitles = {}
  79         for sub in video_data.get('subtitles', []):
  80             sub_url = sub.get('url')
  81             if not sub_url:
  82                 continue
  83             subtitles.setdefault(sub.get('lang', 'English'), []).append({
  84                 'url': self._proto_relative_url(sub_url),
  85             })
  86
  87         return {
  88             'id': video_id,
  89             'title': title,
  90             'formats': formats,
  91             'subtitles': subtitles,
  92             'thumbnails': thumbnails,
  93             'description': video_data.get('description'),
  94             'duration': int_or_none(video_data.get('duration')),
  95             'uploader_id': video_data.get('publisher_id'),
  96         }