fenix
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[ie/afreecatv] Adapt extractors to new sooplive.co.kr domain (#11266) 

Closes #11253
Authored by: 63427083, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
This commit is contained in:
63427083dev 2024-10-22 01:42:45 +02:00 committed by GitHub
parent 0b7ec08816
commit 46fe60ff19
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 68 additions and 117 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

185
yt_dlp/extractor/afreecatv.py
View File

@ -33,21 +33,21 @@ class AfreecaTVBaseIE(InfoExtractor):
} }
response = self._download_json( response = self._download_json(
'https://login.afreecatv.com/app/LoginAction.php', None, 'https://login.sooplive.co.kr/app/LoginAction.php', None,
'Logging in', data=urlencode_postdata(login_form)) 'Logging in', data=urlencode_postdata(login_form))
_ERRORS = { _ERRORS = {
-4: 'Your account has been suspended due to a violation of our terms and policies.', -4: 'Your account has been suspended due to a violation of our terms and policies.',
-5: 'https://member.afreecatv.com/app/user_delete_progress.php', -5: 'https://member.sooplive.co.kr/app/user_delete_progress.php',
-6: 'https://login.afreecatv.com/membership/changeMember.php', -6: 'https://login.sooplive.co.kr/membership/changeMember.php',
-8: "Hello! AfreecaTV here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.", -8: "Hello! Soop here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
-9: 'https://member.afreecatv.com/app/pop_login_block.php', -9: 'https://member.sooplive.co.kr/app/pop_login_block.php',
-11: 'https://login.afreecatv.com/afreeca/second_login.php', -11: 'https://login.sooplive.co.kr/afreeca/second_login.php',
-12: 'https://member.afreecatv.com/app/user_security.php', -12: 'https://member.sooplive.co.kr/app/user_security.php',
0: 'The username does not exist or you have entered the wrong password.', 0: 'The username does not exist or you have entered the wrong password.',
-1: 'The username does not exist or you have entered the wrong password.', -1: 'The username does not exist or you have entered the wrong password.',
-3: 'You have entered your username/password incorrectly.', -3: 'You have entered your username/password incorrectly.',
-7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.', -7: 'You cannot use your Global Soop account to access Korean Soop.',
-10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.', -10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
-32008: 'You have failed to log in. Please contact our Help Center.', -32008: 'You have failed to log in. Please contact our Help Center.',
} }
@ -61,76 +61,40 @@ class AfreecaTVBaseIE(InfoExtractor):
def _call_api(self, endpoint, display_id, data=None, headers=None, query=None): def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
return self._download_json(Request( return self._download_json(Request(
f'https://api.m.afreecatv.com/{endpoint}', f'https://api.m.sooplive.co.kr/{endpoint}',
data=data, headers=headers, query=query, data=data, headers=headers, query=query,
extensions={'legacy_ssl': True}), display_id, extensions={'legacy_ssl': True}), display_id,
'Downloading API JSON', 'Unable to download API JSON') 'Downloading API JSON', 'Unable to download API JSON')
class AfreecaTVIE(AfreecaTVBaseIE): class AfreecaTVIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv' IE_NAME = 'soop'
IE_DESC = 'afreecatv.com' IE_DESC = 'sooplive.co.kr'
_VALID_URL = r'''(?x) _VALID_URL = r'https?://vod\.(?:sooplive\.co\.kr|afreecatv\.com)/(?:PLAYER/STATION|player)/(?P<id>\d+)/?(?:$|[?#&])'
https?://
(?:
(?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
(?:
/app/(?:index|read_ucc_bbs)\.cgi|
/player/[Pp]layer\.(?:swf|html)
)\?.*?\bnTitleNo=|
vod\.afreecatv\.com/(PLAYER/STATION|player)/
)
(?P<id>\d+)/?(?:$|[?#&])
'''
_TESTS = [{ _TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=', 'url': 'https://vod.sooplive.co.kr/player/96753363',
'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
'info_dict': { 'info_dict': {
'id': '36164052', 'id': '20230108_9FF5BEE1_244432674_1',
'ext': 'mp4', 'ext': 'mp4',
'title': '데일리 에이프릴 요정들의 시상식!', 'uploader_id': 'rlantnghks',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$', 'uploader': '페이즈으',
'uploader': 'dailyapril', 'duration': 10840,
'uploader_id': 'dailyapril', 'thumbnail': r're:https?://videoimg\.sooplive\.co/.kr/.+',
'upload_date': '20160503', 'upload_date': '20230108',
'timestamp': 1673218805,
'title': '젠지 페이즈',
}, },
'skip': 'Video is gone', 'params': {
}, { 'skip_download': True,
'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
'info_dict': {
'id': '36153164',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
}, },
'playlist_count': 2,
'playlist': [{
'md5': 'd8b7c174568da61d774ef0203159bf97',
'info_dict': {
'id': '36153164_1',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}, {
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
'info_dict': {
'id': '36153164_2',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}],
'skip': 'Video is gone',
}, { }, {
# non standard key # non standard key
'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605', 'url': 'http://vod.sooplive.co.kr/PLAYER/STATION/20515605',
'info_dict': { 'info_dict': {
'id': '20170411_BE689A0E_190960999_1_2_h', 'id': '20170411_BE689A0E_190960999_1_2_h',
'ext': 'mp4', 'ext': 'mp4',
'title': '혼자사는여자집', 'title': '혼자사는여자집',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$', 'thumbnail': r're:https?://(?:video|st)img\.sooplive\.co\.kr/.+',
'uploader': '♥이슬이', 'uploader': '♥이슬이',
'uploader_id': 'dasl8121', 'uploader_id': 'dasl8121',
'upload_date': '20170411', 'upload_date': '20170411',
@ -142,12 +106,12 @@ class AfreecaTVIE(AfreecaTVBaseIE):
}, },
}, { }, {
# adult content # adult content
'url': 'https://vod.afreecatv.com/player/97267690', 'url': 'https://vod.sooplive.co.kr/player/97267690',
'info_dict': { 'info_dict': {
'id': '20180327_27901457_202289533_1', 'id': '20180327_27901457_202289533_1',
'ext': 'mp4', 'ext': 'mp4',
'title': '[생]빨개요♥ (part 1)', 'title': '[생]빨개요♥ (part 1)',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$', 'thumbnail': r're:https?://(?:video|st)img\.sooplive\.co\.kr/.+',
'uploader': '[SA]서아', 'uploader': '[SA]서아',
'uploader_id': 'bjdyrksu', 'uploader_id': 'bjdyrksu',
'upload_date': '20180327', 'upload_date': '20180327',
@ -157,36 +121,17 @@ class AfreecaTVIE(AfreecaTVBaseIE):
'skip_download': True, 'skip_download': True,
}, },
'skip': 'The VOD does not exist', 'skip': 'The VOD does not exist',
}, {
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
'only_matching': True,
}, {
'url': 'https://vod.afreecatv.com/player/96753363',
'info_dict': {
'id': '20230108_9FF5BEE1_244432674_1',
'ext': 'mp4',
'uploader_id': 'rlantnghks',
'uploader': '페이즈으',
'duration': 10840,
'thumbnail': r're:https?://videoimg\.afreecatv\.com/.+',
'upload_date': '20230108',
'timestamp': 1673218805,
'title': '젠지 페이즈',
},
'params': {
'skip_download': True,
},
}, { }, {
# adult content # adult content
'url': 'https://vod.afreecatv.com/player/70395877', 'url': 'https://vod.sooplive.co.kr/player/70395877',
'only_matching': True, 'only_matching': True,
}, { }, {
# subscribers only # subscribers only
'url': 'https://vod.afreecatv.com/player/104647403', 'url': 'https://vod.sooplive.co.kr/player/104647403',
'only_matching': True, 'only_matching': True,
}, { }, {
# private # private
'url': 'https://vod.afreecatv.com/player/81669846', 'url': 'https://vod.sooplive.co.kr/player/81669846',
'only_matching': True, 'only_matching': True,
}] }]
@ -262,11 +207,11 @@ class AfreecaTVIE(AfreecaTVBaseIE):
class AfreecaTVCatchStoryIE(AfreecaTVBaseIE): class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:catchstory' IE_NAME = 'soop:catchstory'
IE_DESC = 'afreecatv.com catch story' IE_DESC = 'sooplive.co.kr catch story'
_VALID_URL = r'https?://vod\.afreecatv\.com/player/(?P<id>\d+)/catchstory' _VALID_URL = r'https?://vod\.(?:sooplive\.co\.kr|afreecatv\.com)/player/(?P<id>\d+)/catchstory'
_TESTS = [{ _TESTS = [{
'url': 'https://vod.afreecatv.com/player/103247/catchstory', 'url': 'https://vod.sooplive.co.kr/player/103247/catchstory',
'info_dict': { 'info_dict': {
'id': '103247', 'id': '103247',
}, },
@ -299,11 +244,11 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
class AfreecaTVLiveIE(AfreecaTVBaseIE): class AfreecaTVLiveIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:live' IE_NAME = 'soop:live'
IE_DESC = 'afreecatv.com livestreams' IE_DESC = 'sooplive.co.kr livestreams'
_VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?' _VALID_URL = r'https?://play\.(?:sooplive\.co\.kr|afreecatv\.com)/(?P<id>[^/?#]+)(?:/(?P<bno>\d+))?'
_TESTS = [{ _TESTS = [{
'url': 'https://play.afreecatv.com/pyh3646/237852185', 'url': 'https://play.sooplive.co.kr/pyh3646/237852185',
'info_dict': { 'info_dict': {
'id': '237852185', 'id': '237852185',
'ext': 'mp4', 'ext': 'mp4',
@ -315,30 +260,30 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
}, },
'skip': 'Livestream has ended', 'skip': 'Livestream has ended',
}, { }, {
'url': 'https://play.afreecatv.com/pyh3646/237852185', 'url': 'https://play.sooplive.co.kr/pyh3646/237852185',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://play.afreecatv.com/pyh3646', 'url': 'https://play.sooplive.co.kr/pyh3646',
'only_matching': True, 'only_matching': True,
}] }]
_LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php' _LIVE_API_URL = 'https://live.sooplive.co.kr/afreeca/player_live_api.php'
_WORKING_CDNS = [ _WORKING_CDNS = [
'gcp_cdn', # live-global-cdn-v02.afreecatv.com 'gcp_cdn', # live-global-cdn-v02.sooplive.co.kr
'gs_cdn_pc_app', # pc-app.stream.afreecatv.com 'gs_cdn_pc_app', # pc-app.stream.sooplive.co.kr
'gs_cdn_mobile_web', # mobile-web.stream.afreecatv.com 'gs_cdn_mobile_web', # mobile-web.stream.sooplive.co.kr
'gs_cdn_pc_web', # pc-web.stream.afreecatv.com 'gs_cdn_pc_web', # pc-web.stream.sooplive.co.kr
] ]
_BAD_CDNS = [ _BAD_CDNS = [
'gs_cdn', # chromecast.afreeca.gscdn.com (cannot resolve) 'gs_cdn', # chromecast.afreeca.gscdn.com (cannot resolve)
'gs_cdn_chromecast', # chromecast.stream.afreecatv.com (HTTP Error 400) 'gs_cdn_chromecast', # chromecast.stream.sooplive.co.kr (HTTP Error 400)
'azure_cdn', # live-global-cdn-v01.afreecatv.com (cannot resolve) 'azure_cdn', # live-global-cdn-v01.sooplive.co.kr (cannot resolve)
'aws_cf', # live-global-cdn-v03.afreecatv.com (cannot resolve) 'aws_cf', # live-global-cdn-v03.sooplive.co.kr (cannot resolve)
'kt_cdn', # kt.stream.afreecatv.com (HTTP Error 400) 'kt_cdn', # kt.stream.sooplive.co.kr (HTTP Error 400)
] ]
def _extract_formats(self, channel_info, broadcast_no, aid): def _extract_formats(self, channel_info, broadcast_no, aid):
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com' stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.sooplive.co.kr'
# If user has not passed CDN IDs, try API-provided CDN ID followed by other working CDN IDs # If user has not passed CDN IDs, try API-provided CDN ID followed by other working CDN IDs
default_cdn_ids = orderedSet([ default_cdn_ids = orderedSet([
@ -358,7 +303,7 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
try: try:
return self._extract_m3u8_formats( return self._extract_m3u8_formats(
m3u8_url, broadcast_no, 'mp4', m3u8_id='hls', query={'aid': aid}, m3u8_url, broadcast_no, 'mp4', m3u8_id='hls', query={'aid': aid},
headers={'Referer': 'https://play.afreecatv.com/'}) headers={'Referer': 'https://play.sooplive.co.kr/'})
except ExtractorError as e: except ExtractorError as e:
if attempt == len(cdn_ids): if attempt == len(cdn_ids):
raise raise
@ -374,7 +319,13 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
broadcaster_id = channel_info.get('BJID') or broadcaster_id broadcaster_id = channel_info.get('BJID') or broadcaster_id
broadcast_no = channel_info.get('BNO') or broadcast_no broadcast_no = channel_info.get('BNO') or broadcast_no
if not broadcast_no: if not broadcast_no:
raise UserNotLive(video_id=broadcaster_id) result = channel_info.get('RESULT')
if result == 0:
raise UserNotLive(video_id=broadcaster_id)
elif result == -6:
self.raise_login_required(
'This channel is streaming for subscribers only', method='password')
raise ExtractorError('Unable to extract broadcast number')
password = self.get_param('videopassword') password = self.get_param('videopassword')
if channel_info.get('BPWD') == 'Y' and password is None: if channel_info.get('BPWD') == 'Y' and password is None:
@ -403,7 +354,7 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
formats = self._extract_formats(channel_info, broadcast_no, aid) formats = self._extract_formats(channel_info, broadcast_no, aid)
station_info = traverse_obj(self._download_json( station_info = traverse_obj(self._download_json(
'https://st.afreecatv.com/api/get_station_status.php', broadcast_no, 'https://st.sooplive.co.kr/api/get_station_status.php', broadcast_no,
'Downloading channel metadata', 'Unable to download channel metadata', 'Downloading channel metadata', 'Unable to download channel metadata',
query={'szBjId': broadcaster_id}, fatal=False), {dict}) or {} query={'szBjId': broadcaster_id}, fatal=False), {dict}) or {}
@ -419,11 +370,11 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
} }
class AfreecaTVUserIE(InfoExtractor): class AfreecaTVUserIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:user' IE_NAME = 'soop:user'
_VALID_URL = r'https?://bj\.afreeca(?:tv)?\.com/(?P<id>[^/]+)/vods/?(?P<slug_type>[^/]+)?' _VALID_URL = r'https?://ch\.(?:sooplive\.co\.kr|afreecatv\.com)/(?P<id>[^/?#]+)/vods/?(?P<slug_type>[^/?#]+)?'
_TESTS = [{ _TESTS = [{
'url': 'https://bj.afreecatv.com/ryuryu24/vods/review', 'url': 'https://ch.sooplive.co.kr/ryuryu24/vods/review',
'info_dict': { 'info_dict': {
'_type': 'playlist', '_type': 'playlist',
'id': 'ryuryu24', 'id': 'ryuryu24',
@ -431,7 +382,7 @@ class AfreecaTVUserIE(InfoExtractor):
}, },
'playlist_count': 218, 'playlist_count': 218,
}, { }, {
'url': 'https://bj.afreecatv.com/parang1995/vods/highlight', 'url': 'https://ch.sooplive.co.kr/parang1995/vods/highlight',
'info_dict': { 'info_dict': {
'_type': 'playlist', '_type': 'playlist',
'id': 'parang1995', 'id': 'parang1995',
@ -439,7 +390,7 @@ class AfreecaTVUserIE(InfoExtractor):
}, },
'playlist_count': 997, 'playlist_count': 997,
}, { }, {
'url': 'https://bj.afreecatv.com/ryuryu24/vods', 'url': 'https://ch.sooplive.co.kr/ryuryu24/vods',
'info_dict': { 'info_dict': {
'_type': 'playlist', '_type': 'playlist',
'id': 'ryuryu24', 'id': 'ryuryu24',
@ -447,7 +398,7 @@ class AfreecaTVUserIE(InfoExtractor):
}, },
'playlist_count': 221, 'playlist_count': 221,
}, { }, {
'url': 'https://bj.afreecatv.com/ryuryu24/vods/balloonclip', 'url': 'https://ch.sooplive.co.kr/ryuryu24/vods/balloonclip',
'info_dict': { 'info_dict': {
'_type': 'playlist', '_type': 'playlist',
'id': 'ryuryu24', 'id': 'ryuryu24',
@ -459,12 +410,12 @@ class AfreecaTVUserIE(InfoExtractor):
def _fetch_page(self, user_id, user_type, page): def _fetch_page(self, user_id, user_type, page):
page += 1 page += 1
info = self._download_json(f'https://bjapi.afreecatv.com/api/{user_id}/vods/{user_type}', user_id, info = self._download_json(f'https://chapi.sooplive.co.kr/api/{user_id}/vods/{user_type}', user_id,
query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'}, query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'},
note=f'Downloading {user_type} video page {page}') note=f'Downloading {user_type} video page {page}')
for item in info['data']: for item in info['data']:
yield self.url_result( yield self.url_result(
f'https://vod.afreecatv.com/player/{item["title_no"]}/', AfreecaTVIE, item['title_no']) f'https://vod.sooplive.co.kr/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
def _real_extract(self, url): def _real_extract(self, url):
user_id, user_type = self._match_valid_url(url).group('id', 'slug_type') user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')