From 4f9cd4d36fa88758cdff822f03879c6e0b6aa42d Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 2 Nov 2016 13:55:40 +0100 Subject: [PATCH 1/4] [radiocanada] extract subtitle(closes #11096) --- youtube_dl/extractor/radiocanada.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index 6751270ee..321917ad0 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -125,6 +125,14 @@ class RadioCanadaIE(InfoExtractor): f4m_id='hds', fatal=False)) self._sort_formats(formats) + subtitles = {} + closed_caption_url = get_meta('closedCaption') or get_meta('closedCaptionHTML5') + if closed_caption_url: + subtitles['fr'] = [{ + 'url': closed_caption_url, + 'ext': determine_ext(closed_caption_url, 'vtt'), + }] + return { 'id': video_id, 'title': get_meta('Title'), @@ -135,6 +143,7 @@ class RadioCanadaIE(InfoExtractor): 'season_number': int_or_none('SrcSaison'), 'episode_number': int_or_none('SrcEpisode'), 'upload_date': unified_strdate(get_meta('Date')), + 'subtitles': subtitles, 'formats': formats, } From 26aae566902251f9674593a2b0f0ca7477b96a56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Nov 2016 23:34:37 +0700 Subject: [PATCH 2/4] [extractor/generic] Improve ISM extraction --- youtube_dl/extractor/generic.py | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index fc3d01eed..0bb263ce7 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2453,8 +2453,21 @@ class GenericIE(InfoExtractor): entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id) elif ext == 'f4m': entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id) - elif re.search(r'(?i)\.ism/manifest', video_url): - entry_info_dict['formats'] = self._extract_ism_formats(video_url, video_id) + elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url): + # Just matching .ism/manifest is not enough to be reliably sure + # whether it's actually an ISM manifest or some other streaming + # manifest since there are various streaming URL formats + # possible (see [1]) as well as some other shenanigans like + # .smil/manifest URLs that actually serve an ISM (see [2]) and + # so on. + # Thus the most reasonable way to solve this is to delegate + # to generic extractor in order to look into the contents of + # the manifest itself. + # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats + # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest + entry_info_dict = self.url_result( + smuggle_url(video_url, {'to_generic': True}), + GenericIE.ie_key()) else: entry_info_dict['url'] = video_url From 4119a96ce57b11437efd329a8c2602ee7fa7ea2c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Nov 2016 23:43:41 +0700 Subject: [PATCH 3/4] [extractor/generic] Skip URLs we came from when delegating ISM extraction --- youtube_dl/extractor/generic.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 0bb263ce7..a0a45dce0 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2453,7 +2453,7 @@ class GenericIE(InfoExtractor): entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id) elif ext == 'f4m': entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id) - elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url): + elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url: # Just matching .ism/manifest is not enough to be reliably sure # whether it's actually an ISM manifest or some other streaming # manifest since there are various streaming URL formats From 3b4b66b50c6605a7c878364e023776aa8ac7b8b8 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 3 Nov 2016 00:43:33 +0100 Subject: [PATCH 4/4] [shahid] add support for authentication(closes #11091) --- youtube_dl/extractor/shahid.py | 74 +++++++++++++++++++++++++++------- 1 file changed, 60 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py index ca286abb1..62d41e88a 100644 --- a/youtube_dl/extractor/shahid.py +++ b/youtube_dl/extractor/shahid.py @@ -1,17 +1,24 @@ # coding: utf-8 from __future__ import unicode_literals +import re +import json + from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, int_or_none, parse_iso8601, str_or_none, + urlencode_postdata, + clean_html, ) class ShahidIE(InfoExtractor): - _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P\d+)/?' + _NETRC_MACHINE = 'shahid' + _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?Pepisode|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', 'info_dict': { @@ -27,18 +34,54 @@ class ShahidIE(InfoExtractor): # m3u8 download 'skip_download': True, } + }, { + 'url': 'https://shahid.mbc.net/ar/movie/151746/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9.html', + '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', 'only_matching': True }] - def _call_api(self, path, video_id, note): - data = self._download_json( - 'http://api.shahid.net/api/v1_1/' + path, video_id, note, query={ - 'apiKey': 'sh@hid0nlin3', - 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=', - }).get('data', {}) + def _real_initialize(self): + email, password = self._get_login_info() + if email is None: + return + + 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): + 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) + 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 _get_api_data(self, response): + data = response.get('data', {}) error = data.get('error') if error: @@ -49,11 +92,11 @@ class ShahidIE(InfoExtractor): return data def _real_extract(self, url): - video_id = self._match_id(url) + page_type, video_id = re.match(self._VALID_URL, url).groups() - player = self._call_api( - 'Content/Episode/%s' % video_id, - video_id, 'Downloading player JSON') + player = self._get_api_data(self._download_json( + 'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-player.html' % video_id, + video_id, 'Downloading player JSON')) if player.get('drm'): raise ExtractorError('This video is DRM protected.', expected=True) @@ -61,9 +104,12 @@ class ShahidIE(InfoExtractor): formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4') self._sort_formats(formats) - video = self._call_api( - 'episode/%s' % video_id, video_id, - 'Downloading video JSON')['episode'] + video = self._get_api_data(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=', + }))[page_type] title = video['title'] categories = [