X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9f2b33881274af98a9145c533a1d295fad71521a..acbcfdb2cbb57cd2ab6a5d73341cd077fa71f6c9:/youtube_dl/extractor/shahid.py?ds=sidebyside diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py index 1178b7a..5c2a620 100644 --- a/youtube_dl/extractor/shahid.py +++ b/youtube_dl/extractor/shahid.py @@ -1,99 +1,144 @@ # coding: utf-8 from __future__ import unicode_literals -from .common import InfoExtractor -from ..compat import compat_urllib_parse +import json +import math +import re + +from .aws import AWSIE +from ..compat import compat_HTTPError from ..utils import ( + clean_html, ExtractorError, + InAdvancePagedList, int_or_none, parse_iso8601, + str_or_none, + urlencode_postdata, ) -class ShahidIE(InfoExtractor): - _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P\d+)/?' +class ShahidBaseIE(AWSIE): + _AWS_PROXY_HOST = 'api2.shahid.net' + _AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh' + + def _handle_error(self, e): + fail_data = self._parse_json( + e.cause.read().decode('utf-8'), None, fatal=False) + if fail_data: + faults = fail_data.get('faults', []) + faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')]) + if faults_message: + raise ExtractorError(faults_message, expected=True) + + def _call_api(self, path, video_id, request=None): + query = {} + if request: + query['request'] = json.dumps(request) + try: + return self._aws_execute_api({ + 'uri': '/proxy/v2/' + path, + 'access_key': 'AKIAI6X4TYCIXM2B7MUQ', + 'secret_key': '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', + }, video_id, query) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError): + self._handle_error(e) + raise + + +class ShahidIE(ShahidBaseIE): + _NETRC_MACHINE = 'shahid' + _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?Pepisode|clip|movie)-(?P\d+)' _TESTS = [{ - 'url': 'https://shahid.mbc.net/ar/episode/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html', + 'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AC%D9%84%D8%B3-%D8%A7%D9%84%D8%B4%D8%A8%D8%A7%D8%A8-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-275286', 'info_dict': { - 'id': '90574', + 'id': '275286', 'ext': 'mp4', - 'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3', - 'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان', - 'duration': 2972, - 'timestamp': 1422057420, - 'upload_date': '20150123', + 'title': 'مجلس الشباب الموسم 1 كليب 1', + 'timestamp': 1506988800, + 'upload_date': '20171003', }, 'params': { # m3u8 download 'skip_download': True, } + }, { + 'url': 'https://shahid.mbc.net/ar/movies/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9/movie-151746', + 'only_matching': True }, { # shahid plus subscriber only - 'url': 'https://shahid.mbc.net/ar/episode/90511/%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.html', + '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', 'only_matching': True }] - def _handle_error(self, response): - if not isinstance(response, dict): + def _real_initialize(self): + email, password = self._get_login_info() + if email is None: return - error = response.get('error') - if error: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())), - expected=True) - def _download_json(self, url, video_id, note='Downloading JSON metadata'): - response = super(ShahidIE, self)._download_json(url, video_id, note)['data'] - self._handle_error(response) - return response + try: + user_data = self._download_json( + 'https://shahid.mbc.net/wd/service/users/login', + None, 'Logging in', data=json.dumps({ + 'email': email, + 'password': password, + 'basic': 'false', + }).encode('utf-8'), headers={ + 'Content-Type': 'application/json; charset=UTF-8', + })['user'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError): + self._handle_error(e) + raise + + self._download_webpage( + 'https://shahid.mbc.net/populateContext', + None, 'Populate Context', data=urlencode_postdata({ + 'firstName': user_data['firstName'], + 'lastName': user_data['lastName'], + 'userName': user_data['email'], + 'csg_user_name': user_data['email'], + 'subscriberId': user_data['id'], + 'sessionId': user_data['sessionId'], + })) def _real_extract(self, url): - video_id = self._match_id(url) + page_type, video_id = re.match(self._VALID_URL, url).groups() + if page_type == 'clip': + page_type = 'episode' - webpage = self._download_webpage(url, video_id) + playout = self._call_api( + 'playout/url/' + video_id, video_id)['playout'] - api_vars = { - 'id': video_id, - 'type': 'player', - 'url': 'http://api.shahid.net/api/v1_1', - 'playerType': 'episode', - } - - flashvars = self._search_regex( - r'var\s+flashvars\s*=\s*({[^}]+})', webpage, 'flashvars', default=None) - if flashvars: - for key in api_vars.keys(): - value = self._search_regex( - r'\b%s\s*:\s*(?P["\'])(?P.+?)(?P=q)' % key, - flashvars, 'type', default=None, group='value') - if value: - api_vars[key] = value - - player = self._download_json( - 'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-%s.html' - % (video_id, api_vars['type']), video_id, 'Downloading player JSON') - - if player.get('drm'): + if playout.get('drm'): raise ExtractorError('This video is DRM protected.', expected=True) - formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4') - - video = self._download_json( - '%s/%s/%s?%s' % ( - api_vars['url'], api_vars['playerType'], api_vars['id'], - compat_urllib_parse.urlencode({ - 'apiKey': 'sh@hid0nlin3', - 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=', - })), - video_id, 'Downloading video JSON') - - video = video[api_vars['playerType']] + formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4') + self._sort_formats(formats) + + # video = self._call_api( + # 'product/id', video_id, { + # 'id': video_id, + # 'productType': 'ASSET', + # 'productSubType': page_type.upper() + # })['productModel'] + + response = self._download_json( + 'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id), + video_id, 'Downloading video JSON', query={ + 'apiKey': 'sh@hid0nlin3', + 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=', + }) + data = response.get('data', {}) + error = data.get('error') + if error: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())), + expected=True) + video = data[page_type] title = video['title'] - description = video.get('description') - thumbnail = video.get('thumbnailUrl') - duration = int_or_none(video.get('duration')) - timestamp = parse_iso8601(video.get('referenceDate')) categories = [ category['name'] for category in video.get('genres', []) if 'name' in category] @@ -101,10 +146,70 @@ class ShahidIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, + 'description': video.get('description'), + 'thumbnail': video.get('thumbnailUrl'), + 'duration': int_or_none(video.get('duration')), + 'timestamp': parse_iso8601(video.get('referenceDate')), 'categories': categories, + 'series': video.get('showTitle') or video.get('showName'), + 'season': video.get('seasonTitle'), + 'season_number': int_or_none(video.get('seasonNumber')), + 'season_id': str_or_none(video.get('seasonId')), + 'episode_number': int_or_none(video.get('number')), + 'episode_id': video_id, 'formats': formats, } + + +class ShahidShowIE(ShahidBaseIE): + _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:show|serie)s/[^/]+/(?:show|series)-(?P\d+)' + _TESTS = [{ + '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', + 'info_dict': { + 'id': '79187', + 'title': 'رامز قرش البحر', + 'description': 'md5:c88fa7e0f02b0abd39d417aee0d046ff', + }, + 'playlist_mincount': 32, + }, { + 'url': 'https://shahid.mbc.net/ar/series/How-to-live-Longer-(The-Big-Think)/series-291861', + 'only_matching': True + }] + _PAGE_SIZE = 30 + + def _real_extract(self, url): + show_id = self._match_id(url) + + product = self._call_api( + 'playableAsset', show_id, {'showId': show_id})['productModel'] + playlist = product['playlist'] + playlist_id = playlist['id'] + show = product.get('show', {}) + + def page_func(page_num): + playlist = self._call_api( + 'product/playlist', show_id, { + 'playListId': playlist_id, + 'pageNumber': page_num, + 'pageSize': 30, + 'sorts': [{ + 'order': 'DESC', + 'type': 'SORTDATE' + }], + }) + for product in playlist.get('productList', {}).get('products', []): + product_url = product.get('productUrl', []).get('url') + if not product_url: + continue + yield self.url_result( + product_url, 'Shahid', + str_or_none(product.get('id')), + product.get('title')) + + entries = InAdvancePagedList( + page_func, + math.ceil(playlist['count'] / self._PAGE_SIZE), + self._PAGE_SIZE) + + return self.playlist_result( + entries, show_id, show.get('title'), show.get('description'))