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