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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import time
   5 import hashlib
   6 import json
   7
   8 from .adobepass import AdobePassIE
   9 from ..compat import compat_HTTPError
  10 from ..utils import (
  11     int_or_none,
  12     parse_age_limit,
  13     str_or_none,
  14     parse_duration,
  15     ExtractorError,
  16     extract_attributes,
  17 )
  18
  19
  20 class VicelandIE(AdobePassIE):
  21     _VALID_URL = r'https?://(?:www\.)?viceland\.com/[^/]+/video/[^/]+/(?P<id>[a-f0-9]+)'
  22     _TEST = {
  23         'url': 'https://www.viceland.com/en_us/video/cyberwar-trailer/57608447973ee7705f6fbd4e',
  24         'info_dict': {
  25             'id': '57608447973ee7705f6fbd4e',
  26             'ext': 'mp4',
  27             'title': 'CYBERWAR (Trailer)',
  28             'description': 'Tapping into the geopolitics of hacking and surveillance, Ben Makuch travels the world to meet with hackers, government officials, and dissidents to investigate the ecosystem of cyberwarfare.',
  29             'age_limit': 14,
  30             'timestamp': 1466008539,
  31             'upload_date': '20160615',
  32             'uploader_id': '11',
  33             'uploader': 'Viceland',
  34         },
  35         'params': {
  36             # m3u8 download
  37             'skip_download': True,
  38         },
  39         'add_ie': ['UplynkPreplay'],
  40     }
  41
  42     def _real_extract(self, url):
  43         video_id = self._match_id(url)
  44
  45         webpage = self._download_webpage(url, video_id)
  46         watch_hub_data = extract_attributes(self._search_regex(
  47             r'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage, 'watch hub'))
  48         video_id = watch_hub_data['vms-id']
  49         title = watch_hub_data['video-title']
  50
  51         query = {}
  52         if watch_hub_data.get('video-locked') == '1':
  53             resource = self._get_mvpd_resource(
  54                 'VICELAND', title, video_id,
  55                 watch_hub_data.get('video-rating'))
  56             query['tvetoken'] = self._extract_mvpd_auth(url, video_id, 'VICELAND', resource)
  57
  58         # signature generation algorithm is reverse engineered from signatureGenerator in
  59         # webpack:///../shared/~/vice-player/dist/js/vice-player.js in
  60         # https://www.viceland.com/assets/common/js/web.vendor.bundle.js
  61         exp = int(time.time()) + 14400
  62         query.update({
  63             'exp': exp,
  64             'sign': hashlib.sha512(('%s:GET:%d' % (video_id, exp)).encode()).hexdigest(),
  65         })
  66
  67         try:
  68             preplay = self._download_json('https://www.viceland.com/en_us/preplay/%s' % video_id, video_id, query=query)
  69         except ExtractorError as e:
  70             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
  71                 error = json.loads(e.cause.read().decode())
  72                 raise ExtractorError('%s said: %s' % (self.IE_NAME, error['details']), expected=True)
  73             raise
  74
  75         video_data = preplay['video']
  76         base = video_data['base']
  77         uplynk_preplay_url = preplay['preplayURL']
  78         episode = video_data.get('episode', {})
  79         channel = video_data.get('channel', {})
  80
  81         subtitles = {}
  82         cc_url = preplay.get('ccURL')
  83         if cc_url:
  84             subtitles['en'] = [{
  85                 'url': cc_url,
  86             }]
  87
  88         return {
  89             '_type': 'url_transparent',
  90             'url': uplynk_preplay_url,
  91             'id': video_id,
  92             'title': title,
  93             'description': base.get('body'),
  94             'thumbnail': watch_hub_data.get('cover-image') or watch_hub_data.get('thumbnail'),
  95             'duration': parse_duration(video_data.get('video_duration') or watch_hub_data.get('video-duration')),
  96             'timestamp': int_or_none(video_data.get('created_at')),
  97             'age_limit': parse_age_limit(video_data.get('video_rating')),
  98             'series': video_data.get('show_title') or watch_hub_data.get('show-title'),
  99             'episode_number': int_or_none(episode.get('episode_number') or watch_hub_data.get('episode')),
 100             'episode_id': str_or_none(episode.get('id') or video_data.get('episode_id')),
 101             'season_number': int_or_none(watch_hub_data.get('season')),
 102             'season_id': str_or_none(episode.get('season_id')),
 103             'uploader': channel.get('base', {}).get('title') or watch_hub_data.get('channel-title'),
 104             'uploader_id': str_or_none(channel.get('id')),
 105             'subtitles': subtitles,
 106             'ie_key': 'UplynkPreplay',
 107         }