From c576ef1e7cfd31ca94ca6025c054b3ae4f611b21 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Aug 2015 18:13:37 +0600 Subject: [PATCH] [shahid] Improve and simplify --- youtube_dl/extractor/shahid.py | 140 ++++++++++++++++++--------------- 1 file changed, 78 insertions(+), 62 deletions(-) diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py index 399140189..6e9903d5e 100644 --- a/youtube_dl/extractor/shahid.py +++ b/youtube_dl/extractor/shahid.py @@ -2,90 +2,106 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_urllib_parse from ..utils import ( - js_to_json, ExtractorError, - int_or_none + int_or_none, + parse_iso8601, ) 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, - } + _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, + 'timestamp': 1422057420, + 'upload_date': '20150123', }, - { - # 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 + '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 _handle_error(self, response): + if not isinstance(response, dict): + 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 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] + api_vars = { + 'id': video_id, + 'type': 'player', + 'url': 'http://api.shahid.net/api/v1_1', + 'playerType': 'episode', + } - 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) + 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 - 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')) + 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') + + 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=', + }).encode('utf-8')), + video_id, 'Downloading video JSON') + + video = video[api_vars['playerType']] + + 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] return { 'id': video_id, 'title': title, - 'thumbnail': thumbnail, - 'categories': categories, 'description': description, + 'thumbnail': thumbnail, 'duration': duration, + 'timestamp': timestamp, + 'categories': categories, 'formats': formats, }