diff options
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/aol.py | 28 | ||||
-rw-r--r-- | youtube_dl/extractor/dispeak.py | 11 | ||||
-rw-r--r-- | youtube_dl/extractor/extractors.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/gdcvault.py | 100 | ||||
-rw-r--r-- | youtube_dl/extractor/jwplatform.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/kaltura.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/linkedin.py | 9 | ||||
-rw-r--r-- | youtube_dl/extractor/mgtv.py | 46 | ||||
-rw-r--r-- | youtube_dl/extractor/stv.py | 94 | ||||
-rw-r--r-- | youtube_dl/extractor/tiktok.py | 35 | ||||
-rw-r--r-- | youtube_dl/extractor/yourporn.py | 9 |
11 files changed, 257 insertions, 80 deletions
diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index cb9279193..dffa9733d 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -4,6 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse, +) from ..utils import ( ExtractorError, int_or_none, @@ -12,12 +16,12 @@ from ..utils import ( class AolIE(InfoExtractor): - IE_NAME = 'on.aol.com' - _VALID_URL = r'(?:aol-video:|https?://(?:(?:www|on)\.)?aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)' + IE_NAME = 'aol.com' + _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.com/video/(?:[^/]+/)*)(?P<id>[0-9a-f]+)' _TESTS = [{ # video with 5min ID - 'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img', + 'url': 'https://www.aol.com/video/view/u-s--official-warns-of-largest-ever-irs-phone-scam/518167793/', 'md5': '18ef68f48740e86ae94b98da815eec42', 'info_dict': { 'id': '518167793', @@ -34,7 +38,7 @@ class AolIE(InfoExtractor): } }, { # video with vidible ID - 'url': 'http://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/', + 'url': 'https://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/', 'info_dict': { 'id': '5707d6b8e4b090497b04f706', 'ext': 'mp4', @@ -49,16 +53,16 @@ class AolIE(InfoExtractor): 'skip_download': True, } }, { - 'url': 'http://on.aol.com/partners/abc-551438d309eab105804dbfe8/sneak-peek-was-haley-really-framed-570eaebee4b0448640a5c944', + 'url': 'https://www.aol.com/video/view/park-bench-season-2-trailer/559a1b9be4b0c3bfad3357a7/', 'only_matching': True, }, { - 'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763', + 'url': 'https://www.aol.com/video/view/donald-trump-spokeswoman-tones-down-megyn-kelly-attacks/519442220/', 'only_matching': True, }, { - 'url': 'http://on.aol.com/video/519442220', + 'url': 'aol-video:5707d6b8e4b090497b04f706', 'only_matching': True, }, { - 'url': 'aol-video:5707d6b8e4b090497b04f706', + 'url': 'https://www.aol.com/video/playlist/PL8245/5ca79d19d21f1a04035db606/', 'only_matching': True, }] @@ -73,7 +77,7 @@ class AolIE(InfoExtractor): video_data = response['data'] formats = [] - m3u8_url = video_data.get('videoMasterPlaylist') + m3u8_url = url_or_none(video_data.get('videoMasterPlaylist')) if m3u8_url: formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) @@ -96,6 +100,12 @@ class AolIE(InfoExtractor): 'width': int(mobj.group(1)), 'height': int(mobj.group(2)), }) + else: + qs = compat_parse_qs(compat_urllib_parse_urlparse(video_url).query) + f.update({ + 'width': int_or_none(qs.get('w', [None])[0]), + 'height': int_or_none(qs.get('h', [None])[0]), + }) formats.append(f) self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id')) diff --git a/youtube_dl/extractor/dispeak.py b/youtube_dl/extractor/dispeak.py index c05f601e2..c345e0274 100644 --- a/youtube_dl/extractor/dispeak.py +++ b/youtube_dl/extractor/dispeak.py @@ -58,10 +58,17 @@ class DigitallySpeakingIE(InfoExtractor): stream_name = xpath_text(a_format, 'streamName', fatal=True) video_path = re.match(r'mp4\:(?P<path>.*)', stream_name).group('path') url = video_root + video_path - vbr = xpath_text(a_format, 'bitrate') + bitrate = xpath_text(a_format, 'bitrate') + tbr = int_or_none(bitrate) + vbr = int_or_none(self._search_regex( + r'-(\d+)\.mp4', video_path, 'vbr', default=None)) + abr = tbr - vbr if tbr and vbr else None video_formats.append({ + 'format_id': bitrate, 'url': url, - 'vbr': int_or_none(vbr), + 'tbr': tbr, + 'vbr': vbr, + 'abr': abr, }) return video_formats diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 41ab36213..cc19af5c4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1093,6 +1093,7 @@ from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE from .streetvoice import StreetVoiceIE from .stretchinternet import StretchInternetIE +from .stv import STVPlayerIE from .sunporno import SunPornoIE from .svt import ( SVTIE, diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py index 8806dc48a..2f555c1d4 100644 --- a/youtube_dl/extractor/gdcvault.py +++ b/youtube_dl/extractor/gdcvault.py @@ -3,22 +3,24 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from .kaltura import KalturaIE from ..utils import ( HEADRequest, sanitized_Request, + smuggle_url, urlencode_postdata, ) class GDCVaultIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)?' + _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)(?:/(?P<name>[\w-]+))?' _NETRC_MACHINE = 'gdcvault' _TESTS = [ { 'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple', 'md5': '7ce8388f544c88b7ac11c7ab1b593704', 'info_dict': { - 'id': '1019721', + 'id': '201311826596_AWNY', 'display_id': 'Doki-Doki-Universe-Sweet-Simple', 'ext': 'mp4', 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)' @@ -27,7 +29,7 @@ class GDCVaultIE(InfoExtractor): { 'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of', 'info_dict': { - 'id': '1015683', + 'id': '201203272_1330951438328RSXR', 'display_id': 'Embracing-the-Dark-Art-of', 'ext': 'flv', 'title': 'Embracing the Dark Art of Mathematical Modeling in AI' @@ -56,7 +58,7 @@ class GDCVaultIE(InfoExtractor): 'url': 'http://gdcvault.com/play/1023460/Tenacious-Design-and-The-Interface', 'md5': 'a8efb6c31ed06ca8739294960b2dbabd', 'info_dict': { - 'id': '1023460', + 'id': '840376_BQRC', 'ext': 'mp4', 'display_id': 'Tenacious-Design-and-The-Interface', 'title': 'Tenacious Design and The Interface of \'Destiny\'', @@ -66,26 +68,38 @@ class GDCVaultIE(InfoExtractor): # Multiple audios 'url': 'http://www.gdcvault.com/play/1014631/Classic-Game-Postmortem-PAC', 'info_dict': { - 'id': '1014631', - 'ext': 'flv', + 'id': '12396_1299111843500GMPX', + 'ext': 'mp4', 'title': 'How to Create a Good Game - From My Experience of Designing Pac-Man', }, - 'params': { - 'skip_download': True, # Requires rtmpdump - 'format': 'jp', # The japanese audio - } + # 'params': { + # 'skip_download': True, # Requires rtmpdump + # 'format': 'jp', # The japanese audio + # } }, { # gdc-player.html 'url': 'http://www.gdcvault.com/play/1435/An-American-engine-in-Tokyo', 'info_dict': { - 'id': '1435', + 'id': '9350_1238021887562UHXB', 'display_id': 'An-American-engine-in-Tokyo', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'An American Engine in Tokyo:/nThe collaboration of Epic Games and Square Enix/nFor THE LAST REMINANT', }, + }, + { + # Kaltura Embed + 'url': 'https://www.gdcvault.com/play/1026180/Mastering-the-Apex-of-Scaling', + 'info_dict': { + 'id': '0_h1fg8j3p', + 'ext': 'mp4', + 'title': 'Mastering the Apex of Scaling Game Servers (Presented by Multiplay)', + 'timestamp': 1554401811, + 'upload_date': '20190404', + 'uploader_id': 'joe@blazestreaming.com', + }, 'params': { - 'skip_download': True, # Requires rtmpdump + 'format': 'mp4-408', }, }, ] @@ -114,10 +128,8 @@ class GDCVaultIE(InfoExtractor): return start_page def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - display_id = mobj.group('name') or video_id + video_id, name = re.match(self._VALID_URL, url).groups() + display_id = name or video_id webpage_url = 'http://www.gdcvault.com/play/' + video_id start_page = self._download_webpage(webpage_url, display_id) @@ -127,12 +139,12 @@ class GDCVaultIE(InfoExtractor): start_page, 'url', default=None) if direct_url: title = self._html_search_regex( - r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>', + r'<td><strong>Session Name:?</strong></td>\s*<td>(.*?)</td>', start_page, 'title') video_url = 'http://www.gdcvault.com' + direct_url # resolve the url so that we can detect the correct extension - head = self._request_webpage(HEADRequest(video_url), video_id) - video_url = head.geturl() + video_url = self._request_webpage( + HEADRequest(video_url), video_id).geturl() return { 'id': video_id, @@ -141,34 +153,36 @@ class GDCVaultIE(InfoExtractor): 'title': title, } - PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/(?:gdc-)?player.*?\.html.*?".*?</iframe>' - - xml_root = self._html_search_regex( - PLAYER_REGEX, start_page, 'xml root', default=None) - if xml_root is None: - # Probably need to authenticate - login_res = self._login(webpage_url, display_id) - if login_res is None: - self.report_warning('Could not login.') - else: - start_page = login_res - # Grab the url from the authenticated page - xml_root = self._html_search_regex( - PLAYER_REGEX, start_page, 'xml root') - - xml_name = self._html_search_regex( - r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>', - start_page, 'xml filename', default=None) - if xml_name is None: - # Fallback to the older format + embed_url = KalturaIE._extract_url(start_page) + if embed_url: + embed_url = smuggle_url(embed_url, {'source_url': url}) + ie_key = 'Kaltura' + else: + PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/(?:gdc-)?player.*?\.html.*?".*?</iframe>' + + xml_root = self._html_search_regex( + PLAYER_REGEX, start_page, 'xml root', default=None) + if xml_root is None: + # Probably need to authenticate + login_res = self._login(webpage_url, display_id) + if login_res is None: + self.report_warning('Could not login.') + else: + start_page = login_res + # Grab the url from the authenticated page + xml_root = self._html_search_regex( + PLAYER_REGEX, start_page, 'xml root') + xml_name = self._html_search_regex( - r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', + r'<iframe src=".*?\?xml(?:=|URL=xml/)(.+?\.xml).*?".*?</iframe>', start_page, 'xml filename') + embed_url = '%s/xml/%s' % (xml_root, xml_name) + ie_key = 'DigitallySpeaking' return { '_type': 'url_transparent', 'id': video_id, 'display_id': display_id, - 'url': '%s/xml/%s' % (xml_root, xml_name), - 'ie_key': 'DigitallySpeaking', + 'url': embed_url, + 'ie_key': ie_key, } diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index d19a6a774..647b905f1 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -7,7 +7,7 @@ from .common import InfoExtractor class JWPlatformIE(InfoExtractor): - _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' + _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' _TESTS = [{ 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index fdf7f5bbc..79162f665 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -145,6 +145,8 @@ class KalturaIE(InfoExtractor): ) if mobj: embed_info = mobj.groupdict() + for k, v in embed_info.items(): + embed_info[k] = v.strip() url = 'kaltura:%(partner_id)s:%(id)s' % embed_info escaped_pid = re.escape(embed_info['partner_id']) service_url = re.search( diff --git a/youtube_dl/extractor/linkedin.py b/youtube_dl/extractor/linkedin.py index 5a86b0064..26fc703d1 100644 --- a/youtube_dl/extractor/linkedin.py +++ b/youtube_dl/extractor/linkedin.py @@ -9,11 +9,13 @@ from ..utils import ( float_or_none, int_or_none, urlencode_postdata, + urljoin, ) class LinkedInLearningBaseIE(InfoExtractor): _NETRC_MACHINE = 'linkedin' + _LOGIN_URL = 'https://www.linkedin.com/uas/login?trk=learning' def _call_api(self, course_slug, fields, video_slug=None, resolution=None): query = { @@ -50,11 +52,10 @@ class LinkedInLearningBaseIE(InfoExtractor): return login_page = self._download_webpage( - 'https://www.linkedin.com/uas/login?trk=learning', - None, 'Downloading login page') - action_url = self._search_regex( + self._LOGIN_URL, None, 'Downloading login page') + action_url = urljoin(self._LOGIN_URL, self._search_regex( r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, 'post url', - default='https://www.linkedin.com/uas/login-submit', group='url') + default='https://www.linkedin.com/uas/login-submit', group='url')) data = self._hidden_inputs(login_page) data.update({ 'session_key': email, diff --git a/youtube_dl/extractor/mgtv.py b/youtube_dl/extractor/mgtv.py index d53d96aae..84137df50 100644 --- a/youtube_dl/extractor/mgtv.py +++ b/youtube_dl/extractor/mgtv.py @@ -1,22 +1,32 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 +import time +import uuid + from .common import InfoExtractor -from ..compat import compat_str -from ..utils import int_or_none +from ..compat import ( + compat_HTTPError, + compat_str, +) +from ..utils import ( + ExtractorError, + int_or_none, +) class MGTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html' IE_DESC = '芒果TV' + _GEO_COUNTRIES = ['CN'] _TESTS = [{ 'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html', - 'md5': 'b1ffc0fc163152acf6beaa81832c9ee7', 'info_dict': { 'id': '3116640', 'ext': 'mp4', - 'title': '我是歌手第四季双年巅峰会:韩红李玟“双王”领军对抗', + 'title': '我是歌手 第四季', 'description': '我是歌手第四季双年巅峰会', 'duration': 7461, 'thumbnail': r're:^https?://.*\.jpg$', @@ -28,16 +38,30 @@ class MGTVIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - api_data = self._download_json( - 'http://pcweb.api.mgtv.com/player/video', video_id, - query={'video_id': video_id}, - headers=self.geo_verification_headers())['data'] + try: + api_data = self._download_json( + 'https://pcweb.api.mgtv.com/player/video', video_id, query={ + 'tk2': base64.urlsafe_b64encode(b'did=%s|pno=1030|ver=0.3.0301|clit=%d' % (compat_str(uuid.uuid4()).encode(), time.time()))[::-1], + 'video_id': video_id, + }, headers=self.geo_verification_headers())['data'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + error = self._parse_json(e.cause.read().decode(), None) + if error.get('code') == 40005: + self.raise_geo_restricted(countries=self._GEO_COUNTRIES) + raise ExtractorError(error['msg'], expected=True) + raise info = api_data['info'] title = info['title'].strip() - stream_domain = api_data['stream_domain'][0] + stream_data = self._download_json( + 'https://pcweb.api.mgtv.com/player/getSource', video_id, query={ + 'pm2': api_data['atc']['pm2'], + 'video_id': video_id, + }, headers=self.geo_verification_headers())['data'] + stream_domain = stream_data['stream_domain'][0] formats = [] - for idx, stream in enumerate(api_data['stream']): + for idx, stream in enumerate(stream_data['stream']): stream_path = stream.get('url') if not stream_path: continue @@ -47,7 +71,7 @@ class MGTVIE(InfoExtractor): format_url = format_data.get('info') if not format_url: continue - tbr = int_or_none(self._search_regex( + tbr = int_or_none(stream.get('filebitrate') or self._search_regex( r'_(\d+)_mp4/', format_url, 'tbr', default=None)) formats.append({ 'format_id': compat_str(tbr or idx), diff --git a/youtube_dl/extractor/stv.py b/youtube_dl/extractor/stv.py new file mode 100644 index 000000000..ccb074cd4 --- /dev/null +++ b/youtube_dl/extractor/stv.py @@ -0,0 +1,94 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse +) +from ..utils import ( + extract_attributes, + float_or_none, + int_or_none, + str_or_none, +) + + +class STVPlayerIE(InfoExtractor): + IE_NAME = 'stv:player' + _VALID_URL = r'https?://player\.stv\.tv/(?P<type>episode|video)/(?P<id>[a-z0-9]{4})' + _TEST = { + 'url': 'https://player.stv.tv/video/7srz/victoria/interview-with-the-cast-ahead-of-new-victoria/', + 'md5': '2ad867d4afd641fa14187596e0fbc91b', + 'info_dict': { + 'id': '6016487034001', + 'ext': 'mp4', + 'upload_date': '20190321', + 'title': 'Interview with the cast ahead of new Victoria', + 'description': 'Nell Hudson and Lily Travers tell us what to expect in the new season of Victoria.', + 'timestamp': 1553179628, + 'uploader_id': '1486976045', + }, + 'skip': 'this resource is unavailable outside of the UK', + } + _PUBLISHER_ID = '1486976045' + _PTYPE_MAP = { + 'episode': 'episodes', + 'video': 'shortform', + } + + def _real_extract(self, url): + ptype, video_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, video_id) + + qs = compat_parse_qs(compat_urllib_parse_urlparse(self._search_regex( + r'itemprop="embedURL"[^>]+href="([^"]+)', + webpage, 'embed URL', default=None)).query) + publisher_id = qs.get('publisherID', [None])[0] or self._PUBLISHER_ID + + player_attr = extract_attributes(self._search_regex( + r'(<[^>]+class="bcplayer"[^>]+>)', webpage, 'player', default=None)) or {} + + info = {} + duration = ref_id = series = video_id = None + api_ref_id = player_attr.get('data-player-api-refid') + if api_ref_id: + resp = self._download_json( + 'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], api_ref_id), + api_ref_id, fatal=False) + if resp: + result = resp.get('results') or {} + video = result.get('video') or {} + video_id = str_or_none(video.get('id')) + ref_id = video.get('guid') + duration = video.get('length') + programme = result.get('programme') or {} + series = programme.get('name') or programme.get('shortName') + subtitles = {} + _subtitles = result.get('_subtitles') or {} + for ext, sub_url in _subtitles.items(): + subtitles.setdefault('en', []).append({ + 'ext': 'vtt' if ext == 'webvtt' else ext, + 'url': sub_url, + }) + info.update({ + 'description': result.get('summary'), + 'subtitles': subtitles, + 'view_count': int_or_none(result.get('views')), + }) + if not video_id: + video_id = qs.get('videoId', [None])[0] or self._search_regex( + r'<link\s+itemprop="url"\s+href="(\d+)"', + webpage, 'video id', default=None) or 'ref:' + (ref_id or player_attr['data-refid']) + + info.update({ + '_type': 'url_transparent', + 'duration': float_or_none(duration or player_attr.get('data-duration'), 1000), + 'id': video_id, + 'ie_key': 'BrightcoveNew', + 'series': series or player_attr.get('data-programme-name'), + 'url': 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id), + }) + return info diff --git a/youtube_dl/extractor/tiktok.py b/youtube_dl/extractor/tiktok.py index 083e9f36d..66088b9ab 100644 --- a/youtube_dl/extractor/tiktok.py +++ b/youtube_dl/extractor/tiktok.py @@ -65,8 +65,15 @@ class TikTokBaseIE(InfoExtractor): class TikTokIE(TikTokBaseIE): - _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>\d+)' - _TEST = { + _VALID_URL = r'''(?x) + https?:// + (?: + (?:m\.)?tiktok\.com/v| + (?:www\.)?tiktok\.com/share/video + ) + /(?P<id>\d+) + ''' + _TESTS = [{ 'url': 'https://m.tiktok.com/v/6606727368545406213.html', 'md5': 'd584b572e92fcd48888051f238022420', 'info_dict': { @@ -81,25 +88,39 @@ class TikTokIE(TikTokBaseIE): 'comment_count': int, 'repost_count': int, } - } + }, { + 'url': 'https://www.tiktok.com/share/video/6606727368545406213', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + 'https://m.tiktok.com/v/%s.html' % video_id, video_id) data = self._parse_json(self._search_regex( r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id) return self._extract_aweme(data) class TikTokUserIE(TikTokBaseIE): - _VALID_URL = r'https?://(?:m\.)?tiktok\.com/h5/share/usr/(?P<id>\d+)' - _TEST = { + _VALID_URL = r'''(?x) + https?:// + (?: + (?:m\.)?tiktok\.com/h5/share/usr| + (?:www\.)?tiktok\.com/share/user + ) + /(?P<id>\d+) + ''' + _TESTS = [{ 'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html', 'info_dict': { 'id': '188294915489964032', }, 'playlist_mincount': 24, - } + }, { + 'url': 'https://www.tiktok.com/share/user/188294915489964032', + 'only_matching': True, + }] def _real_extract(self, url): user_id = self._match_id(url) diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 2c63f9752..b1d1eb6b6 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -8,8 +8,8 @@ from ..utils import ( class YourPornIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?yourporn\.sexy/post/(?P<id>[^/?#&.]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?(?:yourporn\.sexy|sxyprn\.com)/post/(?P<id>[^/?#&.]+)' + _TESTS = [{ 'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html', 'md5': '6f8682b6464033d87acaa7a8ff0c092e', 'info_dict': { @@ -23,7 +23,10 @@ class YourPornIE(InfoExtractor): 'params': { 'skip_download': True, }, - } + }, { + 'url': 'https://sxyprn.com/post/57ffcb2e1179b.html', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) |