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         'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
  38         'info_dict': {
  39             'id': '560057',
  40             'ext': 'mp4',
  41             'title': 'Penitentiary',
  42             'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
  43             'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
  44             'release_year': 1979,
  45         },
  46         'params': {
  47             'skip_download': True,
  48         },
  49     }]
  50
  51     def _login(self):
  52         username, password = self._get_login_info()
  53         if username is None:
  54             return
  55         self.report_login()
  56         form_data = {
  57             'username': username,
  58             'password': password,
  59         }
  60         payload = urlencode_postdata(form_data)
  61         request = sanitized_Request(self._LOGIN_URL, payload)
  62         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  63         login_page = self._download_webpage(
  64             request, None, False, 'Wrong login info')
  65         if not re.search(r'id="tubi-logout"', login_page):
  66             raise ExtractorError(
  67                 'Login failed (invalid username/password)', expected=True)
  68
  69     def _real_initialize(self):
  70         self._login()
  71
  72     def _real_extract(self, url):
  73         video_id = self._match_id(url)
  74         video_data = self._download_json(
  75             'http://tubitv.com/oz/videos/%s/content' % video_id, video_id)
  76         title = video_data['title']
  77
  78         formats = self._extract_m3u8_formats(
  79             self._proto_relative_url(video_data['url']),
  80             video_id, 'mp4', 'm3u8_native')
  81         self._sort_formats(formats)
  82
  83         thumbnails = []
  84         for thumbnail_url in video_data.get('thumbnails', []):
  85             if not thumbnail_url:
  86                 continue
  87             thumbnails.append({
  88                 'url': self._proto_relative_url(thumbnail_url),
  89             })
  90
  91         subtitles = {}
  92         for sub in video_data.get('subtitles', []):
  93             sub_url = sub.get('url')
  94             if not sub_url:
  95                 continue
  96             subtitles.setdefault(sub.get('lang', 'English'), []).append({
  97                 'url': self._proto_relative_url(sub_url),
  98             })
  99
 100         return {
 101             'id': video_id,
 102             'title': title,
 103             'formats': formats,
 104             'subtitles': subtitles,
 105             'thumbnails': thumbnails,
 106             'description': video_data.get('description'),
 107             'duration': int_or_none(video_data.get('duration')),
 108             'uploader_id': video_data.get('publisher_id'),
 109             'release_year': int_or_none(video_data.get('year')),
 110         }