From 27cef8885de4ffaa33f96973df3c50b62504bd49 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 24 Jun 2019 23:01:43 +0700 Subject: [PATCH 1/2] [beeg] Add support for api/v6 v2 URLs (closes #21511) --- youtube_dl/extractor/beeg.py | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index 192f11ea6..c15a0ac8f 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -1,7 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_str, + compat_urlparse, +) from ..utils import ( int_or_none, unified_timestamp, @@ -11,6 +14,7 @@ from ..utils import ( class BeegIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P\d+)' _TESTS = [{ + # api/v6 v1 'url': 'http://beeg.com/5416503', 'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820', 'info_dict': { @@ -24,6 +28,10 @@ class BeegIE(InfoExtractor): 'tags': list, 'age_limit': 18, } + }, { + # api/v6 v2 + 'url': 'https://beeg.com/1941093077?t=911-1391', + 'only_matching': True, }, { 'url': 'https://beeg.porn/video/5416503', 'only_matching': True, @@ -41,11 +49,22 @@ class BeegIE(InfoExtractor): r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version', default='1546225636701') + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + t = qs.get('t', [''])[0].split('-') + if len(t) > 1: + query = { + 'v': 2, + 's': t[0], + 'e': t[1], + } + else: + query = {'v': 1} + for api_path in ('', 'api.'): video = self._download_json( 'https://%sbeeg.com/api/v6/%s/video/%s' % (api_path, beeg_version, video_id), video_id, - fatal=api_path == 'api.') + fatal=api_path == 'api.', query=query) if video: break From 1d83e9bd4b2dbc854f6f8b7f4baa14602a288c9f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 25 Jun 2019 00:12:31 +0700 Subject: [PATCH 2/2] [nfb] Remove extractor (closes #21518) Covered by generic extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/nfb.py | 112 ----------------------------- 2 files changed, 113 deletions(-) delete mode 100644 youtube_dl/extractor/nfb.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9cd7d3ac4..530474f3f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -745,7 +745,6 @@ from .nexx import ( NexxIE, NexxEmbedIE, ) -from .nfb import NFBIE from .nfl import NFLIE from .nhk import NhkVodIE from .nhl import NHLIE diff --git a/youtube_dl/extractor/nfb.py b/youtube_dl/extractor/nfb.py deleted file mode 100644 index adcc636bc..000000000 --- a/youtube_dl/extractor/nfb.py +++ /dev/null @@ -1,112 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - clean_html, - determine_ext, - int_or_none, - qualities, - urlencode_postdata, - xpath_text, -) - - -class NFBIE(InfoExtractor): - IE_NAME = 'nfb' - IE_DESC = 'National Film Board of Canada' - _VALID_URL = r'https?://(?:www\.)?(?:nfb|onf)\.ca/film/(?P[\da-z_-]+)' - - _TEST = { - 'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny', - 'info_dict': { - 'id': 'qallunaat_why_white_people_are_funny', - 'ext': 'flv', - 'title': 'Qallunaat! Why White People Are Funny ', - 'description': 'md5:6b8e32dde3abf91e58857b174916620c', - 'duration': 3128, - 'creator': 'Mark Sandiford', - 'uploader': 'Mark Sandiford', - }, - 'params': { - # rtmp download - 'skip_download': True, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - config = self._download_xml( - 'https://www.nfb.ca/film/%s/player_config' % video_id, - video_id, 'Downloading player config XML', - data=urlencode_postdata({'getConfig': 'true'}), - headers={ - 'Content-Type': 'application/x-www-form-urlencoded', - 'X-NFB-Referer': 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf' - }) - - title, description, thumbnail, duration, uploader, author = [None] * 6 - thumbnails, formats = [[]] * 2 - subtitles = {} - - for media in config.findall('./player/stream/media'): - if media.get('type') == 'posterImage': - quality_key = qualities(('low', 'high')) - thumbnails = [] - for asset in media.findall('assets/asset'): - asset_url = xpath_text(asset, 'default/url', default=None) - if not asset_url: - continue - quality = asset.get('quality') - thumbnails.append({ - 'url': asset_url, - 'id': quality, - 'preference': quality_key(quality), - }) - elif media.get('type') == 'video': - title = xpath_text(media, 'title', fatal=True) - for asset in media.findall('assets/asset'): - quality = asset.get('quality') - height = int_or_none(self._search_regex( - r'^(\d+)[pP]$', quality or '', 'height', default=None)) - for node in asset: - streamer = xpath_text(node, 'streamerURI', default=None) - if not streamer: - continue - play_path = xpath_text(node, 'url', default=None) - if not play_path: - continue - formats.append({ - 'url': streamer, - 'app': streamer.split('/', 3)[3], - 'play_path': play_path, - 'rtmp_live': False, - 'ext': 'flv', - 'format_id': '%s-%s' % (node.tag, quality) if quality else node.tag, - 'height': height, - }) - self._sort_formats(formats) - description = clean_html(xpath_text(media, 'description')) - uploader = xpath_text(media, 'author') - duration = int_or_none(media.get('duration')) - for subtitle in media.findall('./subtitles/subtitle'): - subtitle_url = xpath_text(subtitle, 'url', default=None) - if not subtitle_url: - continue - lang = xpath_text(subtitle, 'lang', default='en') - subtitles.setdefault(lang, []).append({ - 'url': subtitle_url, - 'ext': (subtitle.get('format') or determine_ext(subtitle_url)).lower(), - }) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnails': thumbnails, - 'duration': duration, - 'creator': uploader, - 'uploader': uploader, - 'formats': formats, - 'subtitles': subtitles, - }