youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

shahid.py (8448B)

      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 _real_initialize(self):
     83         email, password = self._get_login_info()
     84         if email is None:
     85             return
     86 
     87         try:
     88             user_data = self._download_json(
     89                 'https://shahid.mbc.net/wd/service/users/login',
     90                 None, 'Logging in', data=json.dumps({
     91                     'email': email,
     92                     'password': password,
     93                     'basic': 'false',
     94                 }).encode('utf-8'), headers={
     95                     'Content-Type': 'application/json; charset=UTF-8',
     96                 })['user']
     97         except ExtractorError as e:
     98             if isinstance(e.cause, compat_HTTPError):
     99                 self._handle_error(e)
    100             raise
    101 
    102         self._download_webpage(
    103             'https://shahid.mbc.net/populateContext',
    104             None, 'Populate Context', data=urlencode_postdata({
    105                 'firstName': user_data['firstName'],
    106                 'lastName': user_data['lastName'],
    107                 'userName': user_data['email'],
    108                 'csg_user_name': user_data['email'],
    109                 'subscriberId': user_data['id'],
    110                 'sessionId': user_data['sessionId'],
    111             }))
    112 
    113     def _real_extract(self, url):
    114         page_type, video_id = re.match(self._VALID_URL, url).groups()
    115         if page_type == 'clip':
    116             page_type = 'episode'
    117 
    118         playout = self._call_api(
    119             'playout/new/url/' + video_id, video_id)['playout']
    120 
    121         if playout.get('drm'):
    122             raise ExtractorError('This video is DRM protected.', expected=True)
    123 
    124         formats = self._extract_m3u8_formats(re.sub(
    125             # https://docs.aws.amazon.com/mediapackage/latest/ug/manifest-filtering.html
    126             r'aws\.manifestfilter=[\w:;,-]+&?',
    127             '', playout['url']), video_id, 'mp4')
    128         self._sort_formats(formats)
    129 
    130         # video = self._call_api(
    131         #     'product/id', video_id, {
    132         #         'id': video_id,
    133         #         'productType': 'ASSET',
    134         #         'productSubType': page_type.upper()
    135         #     })['productModel']
    136 
    137         response = self._download_json(
    138             'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
    139             video_id, 'Downloading video JSON', query={
    140                 'apiKey': 'sh@hid0nlin3',
    141                 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
    142             })
    143         data = response.get('data', {})
    144         error = data.get('error')
    145         if error:
    146             raise ExtractorError(
    147                 '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
    148                 expected=True)
    149 
    150         video = data[page_type]
    151         title = video['title']
    152         categories = [
    153             category['name']
    154             for category in video.get('genres', []) if 'name' in category]
    155 
    156         return {
    157             'id': video_id,
    158             'title': title,
    159             'description': video.get('description'),
    160             'thumbnail': video.get('thumbnailUrl'),
    161             'duration': int_or_none(video.get('duration')),
    162             'timestamp': parse_iso8601(video.get('referenceDate')),
    163             'categories': categories,
    164             'series': video.get('showTitle') or video.get('showName'),
    165             'season': video.get('seasonTitle'),
    166             'season_number': int_or_none(video.get('seasonNumber')),
    167             'season_id': str_or_none(video.get('seasonId')),
    168             'episode_number': int_or_none(video.get('number')),
    169             'episode_id': video_id,
    170             'formats': formats,
    171         }
    172 
    173 
    174 class ShahidShowIE(ShahidBaseIE):
    175     _VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
    176     _TESTS = [{
    177         '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',
    178         'info_dict': {
    179             'id': '79187',
    180             'title': 'رامز قرش البحر',
    181             'description': 'md5:c88fa7e0f02b0abd39d417aee0d046ff',
    182         },
    183         'playlist_mincount': 32,
    184     }, {
    185         'url': 'https://shahid.mbc.net/ar/series/How-to-live-Longer-(The-Big-Think)/series-291861',
    186         'only_matching': True
    187     }]
    188     _PAGE_SIZE = 30
    189 
    190     def _real_extract(self, url):
    191         show_id = self._match_id(url)
    192 
    193         product = self._call_api(
    194             'playableAsset', show_id, {'showId': show_id})['productModel']
    195         playlist = product['playlist']
    196         playlist_id = playlist['id']
    197         show = product.get('show', {})
    198 
    199         def page_func(page_num):
    200             playlist = self._call_api(
    201                 'product/playlist', show_id, {
    202                     'playListId': playlist_id,
    203                     'pageNumber': page_num,
    204                     'pageSize': 30,
    205                     'sorts': [{
    206                         'order': 'DESC',
    207                         'type': 'SORTDATE'
    208                     }],
    209                 })
    210             for product in playlist.get('productList', {}).get('products', []):
    211                 product_url = product.get('productUrl', []).get('url')
    212                 if not product_url:
    213                     continue
    214                 yield self.url_result(
    215                     product_url, 'Shahid',
    216                     str_or_none(product.get('id')),
    217                     product.get('title'))
    218 
    219         entries = InAdvancePagedList(
    220             page_func,
    221             math.ceil(playlist['count'] / self._PAGE_SIZE),
    222             self._PAGE_SIZE)
    223 
    224         return self.playlist_result(
    225             entries, show_id, show.get('title'), show.get('description'))