yt_dlp/extractor/zee5.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     int_or_none,
   9     parse_age_limit,
  10     str_or_none,
  11     try_get,
  12     unified_strdate,
  13     unified_timestamp,
  14     url_or_none,
  15 )
  16
  17
  18 class Zee5IE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?zee5\.com/[^#?]*/(?P<display_id>[-\w]+)/(?P<id>[-\d]+)'
  20     _TESTS = [{
  21         'url': 'https://www.zee5.com/movies/details/krishna-the-birth/0-0-63098',
  22         'info_dict': {
  23             "id": "0-0-63098",
  24             "ext": "m3u8",
  25             "display_id": "krishna-the-birth",
  26             "title": "Krishna - The Birth",
  27             "duration": 4368,
  28             "average_rating": 4,
  29             "description": str,
  30             "alt_title": "Krishna - The Birth",
  31             "uploader": "Zee Entertainment Enterprises Ltd",
  32             "release_date": "20060101",
  33             "upload_date": "20060101",
  34             "timestamp": 1136073600,
  35             "thumbnail": "https://akamaividz.zee5.com/resources/0-0-63098/list/270x152/0063098_list_80888170.jpg",
  36             "tags": list
  37         },
  38         'params': {
  39             'format': 'bv',
  40         },
  41     }, {
  42         'url': 'https://zee5.com/tvshows/details/krishna-balram/0-6-1871/episode-1-the-test-of-bramha/0-1-233402',
  43         'info_dict': {
  44             "id": "0-1-233402",
  45             'ext': 'm3u8',
  46             "display_id": "episode-1-the-test-of-bramha",
  47             "title": "Episode 1 - The Test Of Bramha",
  48             "duration": 1336,
  49             "average_rating": 4,
  50             "description": str,
  51             "alt_title": "Episode 1 - The Test Of Bramha",
  52             "uploader": "Green Gold",
  53             "release_date": "20090101",
  54             "upload_date": "20090101",
  55             "timestamp": 1230768000,
  56             "thumbnail": "https://akamaividz.zee5.com/resources/0-1-233402/list/270x152/01233402_list.jpg",
  57             "series": "Krishna Balram",
  58             "season_number": 1,
  59             "episode_number": 1,
  60             "tags": list,
  61         },
  62         'params': {
  63             'format': 'bv',
  64         },
  65     }]
  66
  67     def _real_extract(self, url):
  68         video_id, display_id = re.match(self._VALID_URL, url).group('id', 'display_id')
  69         access_token_request = self._download_json(
  70             'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
  71             video_id, note="Downloading access token")
  72         token_request = self._download_json(
  73             'https://useraction.zee5.com/tokennd',
  74             video_id, note="Downloading video token")
  75         json_data = self._download_json(
  76             'https://gwapi.zee5.com/content/details/{}?translation=en&country=IN'.format(video_id),
  77             video_id, headers={'X-Access-Token': access_token_request['token']})
  78         m3u8_url = try_get(
  79             json_data,
  80             (lambda x: x['hls'][0], lambda x: x['video_details']['hls_url']),
  81             str)
  82         formats = self._extract_m3u8_formats(
  83             'https://zee5vodnd.akamaized.net' + m3u8_url.replace('/drm1/', '/hls1/') + token_request['video_token'],
  84             video_id, fatal=False)
  85         mpd_url = try_get(
  86             json_data,
  87             (lambda x: x['video'][0], lambda x: x['video_details']['url']),
  88             str)
  89         formats += self._extract_mpd_formats(
  90             'https://zee5vodnd.akamaized.net' + mpd_url + token_request['video_token'],
  91             video_id, fatal=False)
  92
  93         self._sort_formats(formats)
  94         return {
  95             'id': video_id,
  96             'display_id': display_id,
  97             'title': json_data['title'],
  98             'formats': formats,
  99             'duration': int_or_none(json_data.get('duration')),
 100             'average_rating': int_or_none(json_data.get('rating')),
 101             'description': str_or_none(json_data.get('description')),
 102             'alt_title': str_or_none(json_data.get('original_title')),
 103             'uploader': str_or_none(json_data.get('content_owner')),
 104             'age_limit': parse_age_limit(json_data.get('age_rating')),
 105             'release_date': unified_strdate(json_data.get('release_date')),
 106             'timestamp': unified_timestamp(json_data.get('release_date')),
 107             'thumbnail': url_or_none(json_data.get('image_url')),
 108             'series': try_get(json_data, lambda x: x['tvshow_details']['title'], str),
 109             'season': try_get(json_data, lambda x: x['season_details']['title'], str),
 110             'season_number': int_or_none(try_get(json_data, lambda x: x['season_details']['index'])),
 111             'episode_number': int_or_none(try_get(json_data, lambda x: x['index'])),
 112             'tags': try_get(json_data, lambda x: x['tags'], list)
 113         }