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     _TEST = {
  20         'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
  21         'md5': '43ac06be9326f41912dc64ccf7a80320',
  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_id': 'bc168bee0d18dd1cb3b86c68706ab434',
  28         },
  29     }
  30
  31     def _login(self):
  32         (username, password) = self._get_login_info()
  33         if username is None:
  34             return
  35         self.report_login()
  36         form_data = {
  37             'username': username,
  38             'password': password,
  39         }
  40         payload = urlencode_postdata(form_data)
  41         request = sanitized_Request(self._LOGIN_URL, payload)
  42         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  43         login_page = self._download_webpage(
  44             request, None, False, 'Wrong login info')
  45         if not re.search(r'id="tubi-logout"', login_page):
  46             raise ExtractorError(
  47                 'Login failed (invalid username/password)', expected=True)
  48
  49     def _real_initialize(self):
  50         self._login()
  51
  52     def _real_extract(self, url):
  53         video_id = self._match_id(url)
  54         video_data = self._download_json(
  55             'http://tubitv.com/oz/videos/%s/content' % video_id, video_id)
  56         title = video_data['title']
  57
  58         formats = self._extract_m3u8_formats(
  59             self._proto_relative_url(video_data['url']),
  60             video_id, 'mp4', 'm3u8_native')
  61         self._sort_formats(formats)
  62
  63         thumbnails = []
  64         for thumbnail_url in video_data.get('thumbnails', []):
  65             if not thumbnail_url:
  66                 continue
  67             thumbnails.append({
  68                 'url': self._proto_relative_url(thumbnail_url),
  69             })
  70
  71         subtitles = {}
  72         for sub in video_data.get('subtitles', []):
  73             sub_url = sub.get('url')
  74             if not sub_url:
  75                 continue
  76             subtitles.setdefault(sub.get('lang', 'English'), []).append({
  77                 'url': self._proto_relative_url(sub_url),
  78             })
  79
  80         return {
  81             'id': video_id,
  82             'title': title,
  83             'formats': formats,
  84             'subtitles': subtitles,
  85             'thumbnails': thumbnails,
  86             'description': video_data.get('description'),
  87             'duration': int_or_none(video_data.get('duration')),
  88             'uploader_id': video_data.get('publisher_id'),
  89         }