yt_dlp/extractor/shahid.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import math
   6 import re
   7
   8 from .aws import AWSIE
   9 from ..compat import compat_HTTPError
  10 from ..utils import (
  11     clean_html,
  12     ExtractorError,
  13     InAdvancePagedList,
  14     int_or_none,
  15     parse_iso8601,
  16     str_or_none,
  17     urlencode_postdata,
  18 )
  19
  20
  21 class ShahidBaseIE(AWSIE):
  22     _AWS_PROXY_HOST = 'api2.shahid.net'
  23     _AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
  24     _VALID_URL_BASE = r'https?://shahid\.mbc\.net/[a-z]{2}/'
  25
  26     def _handle_error(self, e):
  27         fail_data = self._parse_json(
  28             e.cause.read().decode('utf-8'), None, fatal=False)
  29         if fail_data:
  30             faults = fail_data.get('faults', [])
  31             faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
  32             if faults_message:
  33                 raise ExtractorError(faults_message, expected=True)
  34
  35     def _call_api(self, path, video_id, request=None):
  36         query = {}
  37         if request:
  38             query['request'] = json.dumps(request)
  39         try:
  40             return self._aws_execute_api({
  41                 'uri': '/proxy/v2/' + path,
  42                 'access_key': 'AKIAI6X4TYCIXM2B7MUQ',
  43                 'secret_key': '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',
  44             }, video_id, query)
  45         except ExtractorError as e:
  46             if isinstance(e.cause, compat_HTTPError):
  47                 self._handle_error(e)
  48             raise
  49
  50
  51 class ShahidIE(ShahidBaseIE):
  52     _NETRC_MACHINE = 'shahid'
  53     _VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
  54     _TESTS = [{
  55         'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AA%D8%AD%D9%81-%D8%A7%D9%84%D8%AF%D8%AD%D9%8A%D8%AD-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-816924',
  56         'info_dict': {
  57             'id': '816924',
  58             'ext': 'mp4',
  59             'title': 'متحف الدحيح الموسم 1 كليب 1',
  60             'timestamp': 1602806400,
  61             'upload_date': '20201016',
  62             'description': 'برومو',
  63             'duration': 22,
  64             'categories': ['كوميديا'],
  65         },
  66         'params': {
  67             # m3u8 download
  68             'skip_download': True,
  69         }
  70     }, {
  71         'url': 'https://shahid.mbc.net/ar/movies/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9/movie-151746',
  72         'only_matching': True
  73     }, {
  74         # shahid plus subscriber only
  75         'url': 'https://shahid.mbc.net/ar/series/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/episode-90511',
  76         'only_matching': True
  77     }, {
  78         'url': 'https://shahid.mbc.net/en/shows/Ramez-Fi-Al-Shallal-season-1-episode-1/episode-359319',
  79         'only_matching': True
  80     }]
  81
  82     def _perform_login(self, username, password):
  83         try:
  84             user_data = self._download_json(
  85                 'https://shahid.mbc.net/wd/service/users/login',
  86                 None, 'Logging in', data=json.dumps({
  87                     'email': username,
  88                     'password': password,
  89                     'basic': 'false',
  90                 }).encode('utf-8'), headers={
  91                     'Content-Type': 'application/json; charset=UTF-8',
  92                 })['user']
  93         except ExtractorError as e:
  94             if isinstance(e.cause, compat_HTTPError):
  95                 self._handle_error(e)
  96             raise
  97
  98         self._download_webpage(
  99             'https://shahid.mbc.net/populateContext',
 100             None, 'Populate Context', data=urlencode_postdata({
 101                 'firstName': user_data['firstName'],
 102                 'lastName': user_data['lastName'],
 103                 'userName': user_data['email'],
 104                 'csg_user_name': user_data['email'],
 105                 'subscriberId': user_data['id'],
 106                 'sessionId': user_data['sessionId'],
 107             }))
 108
 109     def _real_extract(self, url):
 110         page_type, video_id = self._match_valid_url(url).groups()
 111         if page_type == 'clip':
 112             page_type = 'episode'
 113
 114         playout = self._call_api(
 115             'playout/new/url/' + video_id, video_id)['playout']
 116
 117         if not self.get_param('allow_unplayable_formats') and playout.get('drm'):
 118             self.report_drm(video_id)
 119
 120         formats = self._extract_m3u8_formats(re.sub(
 121             # https://docs.aws.amazon.com/mediapackage/latest/ug/manifest-filtering.html
 122             r'aws\.manifestfilter=[\w:;,-]+&?',
 123             '', playout['url']), video_id, 'mp4')
 124         self._sort_formats(formats)
 125
 126         # video = self._call_api(
 127         #     'product/id', video_id, {
 128         #         'id': video_id,
 129         #         'productType': 'ASSET',
 130         #         'productSubType': page_type.upper()
 131         #     })['productModel']
 132
 133         response = self._download_json(
 134             'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
 135             video_id, 'Downloading video JSON', query={
 136                 'apiKey': 'sh@hid0nlin3',
 137                 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
 138             })
 139         data = response.get('data', {})
 140         error = data.get('error')
 141         if error:
 142             raise ExtractorError(
 143                 '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
 144                 expected=True)
 145
 146         video = data[page_type]
 147         title = video['title']
 148         categories = [
 149             category['name']
 150             for category in video.get('genres', []) if 'name' in category]
 151
 152         return {
 153             'id': video_id,
 154             'title': title,
 155             'description': video.get('description'),
 156             'thumbnail': video.get('thumbnailUrl'),
 157             'duration': int_or_none(video.get('duration')),
 158             'timestamp': parse_iso8601(video.get('referenceDate')),
 159             'categories': categories,
 160             'series': video.get('showTitle') or video.get('showName'),
 161             'season': video.get('seasonTitle'),
 162             'season_number': int_or_none(video.get('seasonNumber')),
 163             'season_id': str_or_none(video.get('seasonId')),
 164             'episode_number': int_or_none(video.get('number')),
 165             'episode_id': video_id,
 166             'formats': formats,
 167         }
 168
 169
 170 class ShahidShowIE(ShahidBaseIE):
 171     _VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
 172     _TESTS = [{
 173         'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187',
 174         'info_dict': {
 175             'id': '79187',
 176             'title': 'رامز قرش البحر',
 177             'description': 'md5:c88fa7e0f02b0abd39d417aee0d046ff',
 178         },
 179         'playlist_mincount': 32,
 180     }, {
 181         'url': 'https://shahid.mbc.net/ar/series/How-to-live-Longer-(The-Big-Think)/series-291861',
 182         'only_matching': True
 183     }]
 184     _PAGE_SIZE = 30
 185
 186     def _real_extract(self, url):
 187         show_id = self._match_id(url)
 188
 189         product = self._call_api(
 190             'playableAsset', show_id, {'showId': show_id})['productModel']
 191         playlist = product['playlist']
 192         playlist_id = playlist['id']
 193         show = product.get('show', {})
 194
 195         def page_func(page_num):
 196             playlist = self._call_api(
 197                 'product/playlist', show_id, {
 198                     'playListId': playlist_id,
 199                     'pageNumber': page_num,
 200                     'pageSize': 30,
 201                     'sorts': [{
 202                         'order': 'DESC',
 203                         'type': 'SORTDATE'
 204                     }],
 205                 })
 206             for product in playlist.get('productList', {}).get('products', []):
 207                 product_url = product.get('productUrl', []).get('url')
 208                 if not product_url:
 209                     continue
 210                 yield self.url_result(
 211                     product_url, 'Shahid',
 212                     str_or_none(product.get('id')),
 213                     product.get('title'))
 214
 215         entries = InAdvancePagedList(
 216             page_func,
 217             math.ceil(playlist['count'] / self._PAGE_SIZE),
 218             self._PAGE_SIZE)
 219
 220         return self.playlist_result(
 221             entries, show_id, show.get('title'), show.get('description'))