diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a8be636240..7459a19445 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -523,6 +523,7 @@ from .senateisvp import SenateISVPIE from .servingsys import ServingSysIE from .sexu import SexuIE from .sexykarma import SexyKarmaIE +from .shahid import ShahidIE from .shared import SharedIE from .sharesix import ShareSixIE from .sina import SinaIE diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py new file mode 100644 index 0000000000..3991401899 --- /dev/null +++ b/youtube_dl/extractor/shahid.py @@ -0,0 +1,91 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + js_to_json, + ExtractorError, + int_or_none +) + + +class ShahidIE(InfoExtractor): + _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?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', + 'info_dict': { + 'id': '90574', + 'ext': 'm3u8', + 'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3', + 'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان', + 'duration': 2972, + }, + 'params': { + # m3u8 download + 'skip_download': 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', + 'only_matching': True + } + ] + + _api_vars = { + 'type': 'player', + 'url': 'http://api.shahid.net/api/v1_1', + 'playerType': 'episode', + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + player_info = '' + flash_vars = self._search_regex('var flashvars = ({[^}]+})', webpage, 'flashvars', None) + if flash_vars is not None: + for line in flash_vars.splitlines(): + if '+' not in line and '(' not in line and ')' not in line: + player_info += line + player_info = self._parse_json(player_info, video_id, js_to_json, False) + if player_info is not None: + for key in self._api_vars: + if key in player_info: + self._api_vars[key] = player_info[key] + + player_json_data = self._download_json( + 'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-' + video_id + '.type-' + self._api_vars['type'] + '.html', + video_id + )['data'] + if 'url' in player_json_data: + m3u8_url = player_json_data['url'] + else: + for error in player_json_data['error'].values(): + raise ExtractorError(error) + formats = self._extract_m3u8_formats(m3u8_url, video_id) + + video_info = self._download_json( + self._api_vars['url'] + '/' + self._api_vars['playerType'] + '/' + video_id + '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D', + video_id + )['data'] + if video_info.get('error'): + for error in video_info['error']: + raise ExtractorError(error) + video_info = video_info[self._api_vars['playerType']] + title = video_info['title'] + thumbnail = video_info.get('thumbnailUrl') + categories = [category['name'] for category in video_info.get('genres')] + description = video_info.get('description') + duration = int_or_none(video_info.get('duration')) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'categories': categories, + 'description': description, + 'duration': duration, + 'formats': formats, + }