summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/afreecatv.py
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-17 07:54:09 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-17 07:54:09 +0000
commitb12aca2eea3676bb3cf2666b63542c019fac699d (patch)
tree026eec6b22f4422a90479fea630e8e173781aa79 /yt_dlp/extractor/afreecatv.py
parentAdding debian version 2024.03.10-1. (diff)
downloadyt-dlp-b12aca2eea3676bb3cf2666b63542c019fac699d.tar.xz
yt-dlp-b12aca2eea3676bb3cf2666b63542c019fac699d.zip
Merging upstream version 2024.04.09.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'yt_dlp/extractor/afreecatv.py')
-rw-r--r--yt_dlp/extractor/afreecatv.py404
1 files changed, 153 insertions, 251 deletions
diff --git a/yt_dlp/extractor/afreecatv.py b/yt_dlp/extractor/afreecatv.py
index 3d26d9c..2c33c90 100644
--- a/yt_dlp/extractor/afreecatv.py
+++ b/yt_dlp/extractor/afreecatv.py
@@ -1,25 +1,63 @@
import functools
-import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
- date_from_str,
+ UserNotLive,
determine_ext,
+ filter_dict,
int_or_none,
- qualities,
- traverse_obj,
- unified_strdate,
unified_timestamp,
- update_url_query,
url_or_none,
urlencode_postdata,
- xpath_text,
)
+from ..utils.traversal import traverse_obj
-class AfreecaTVIE(InfoExtractor):
+class AfreecaTVBaseIE(InfoExtractor):
+ _NETRC_MACHINE = 'afreecatv'
+
+ def _perform_login(self, username, password):
+ login_form = {
+ 'szWork': 'login',
+ 'szType': 'json',
+ 'szUid': username,
+ 'szPassword': password,
+ 'isSaveId': 'false',
+ 'szScriptVar': 'oLoginRet',
+ 'szAction': '',
+ }
+
+ response = self._download_json(
+ 'https://login.afreecatv.com/app/LoginAction.php', None,
+ 'Logging in', data=urlencode_postdata(login_form))
+
+ _ERRORS = {
+ -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',
+ -6: 'https://login.afreecatv.com/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.",
+ -9: 'https://member.afreecatv.com/app/pop_login_block.php',
+ -11: 'https://login.afreecatv.com/afreeca/second_login.php',
+ -12: 'https://member.afreecatv.com/app/user_security.php',
+ 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.',
+ -3: 'You have entered your username/password incorrectly.',
+ -7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
+ -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.',
+ }
+
+ result = int_or_none(response.get('RESULT'))
+ if result != 1:
+ error = _ERRORS.get(result, 'You have failed to log in.')
+ raise ExtractorError(
+ 'Unable to login: %s said: %s' % (self.IE_NAME, error),
+ expected=True)
+
+
+class AfreecaTVIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv'
IE_DESC = 'afreecatv.com'
_VALID_URL = r'''(?x)
@@ -34,7 +72,6 @@ class AfreecaTVIE(InfoExtractor):
)
(?P<id>\d+)
'''
- _NETRC_MACHINE = 'afreecatv'
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
@@ -87,6 +124,7 @@ class AfreecaTVIE(InfoExtractor):
'uploader': '♥이슬이',
'uploader_id': 'dasl8121',
'upload_date': '20170411',
+ 'timestamp': 1491929865,
'duration': 213,
},
'params': {
@@ -120,219 +158,102 @@ class AfreecaTVIE(InfoExtractor):
'uploader_id': 'rlantnghks',
'uploader': '페이즈으',
'duration': 10840,
- 'thumbnail': 'http://videoimg.afreecatv.com/php/SnapshotLoad.php?rowKey=20230108_9FF5BEE1_244432674_1_r',
+ 'thumbnail': r're:https?://videoimg\.afreecatv\.com/.+',
'upload_date': '20230108',
+ 'timestamp': 1673218805,
'title': '젠지 페이즈',
},
'params': {
'skip_download': True,
},
+ }, {
+ # adult content
+ 'url': 'https://vod.afreecatv.com/player/70395877',
+ 'only_matching': True,
+ }, {
+ # subscribers only
+ 'url': 'https://vod.afreecatv.com/player/104647403',
+ 'only_matching': True,
+ }, {
+ # private
+ 'url': 'https://vod.afreecatv.com/player/81669846',
+ 'only_matching': True,
}]
- @staticmethod
- def parse_video_key(key):
- video_key = {}
- m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
- if m:
- video_key['upload_date'] = m.group('upload_date')
- video_key['part'] = int(m.group('part'))
- return video_key
-
- def _perform_login(self, username, password):
- login_form = {
- 'szWork': 'login',
- 'szType': 'json',
- 'szUid': username,
- 'szPassword': password,
- 'isSaveId': 'false',
- 'szScriptVar': 'oLoginRet',
- 'szAction': '',
- }
-
- response = self._download_json(
- 'https://login.afreecatv.com/app/LoginAction.php', None,
- 'Logging in', data=urlencode_postdata(login_form))
-
- _ERRORS = {
- -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',
- -6: 'https://login.afreecatv.com/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.",
- -9: 'https://member.afreecatv.com/app/pop_login_block.php',
- -11: 'https://login.afreecatv.com/afreeca/second_login.php',
- -12: 'https://member.afreecatv.com/app/user_security.php',
- 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.',
- -3: 'You have entered your username/password incorrectly.',
- -7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
- -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.',
- }
-
- result = int_or_none(response.get('RESULT'))
- if result != 1:
- error = _ERRORS.get(result, 'You have failed to log in.')
- raise ExtractorError(
- 'Unable to login: %s said: %s' % (self.IE_NAME, error),
- expected=True)
-
def _real_extract(self, url):
video_id = self._match_id(url)
-
- partial_view = False
- adult_view = False
- for _ in range(2):
- data = self._download_json(
- 'https://api.m.afreecatv.com/station/video/a/view',
- video_id, headers={'Referer': url}, data=urlencode_postdata({
- 'nTitleNo': video_id,
- 'nApiLevel': 10,
- }))['data']
- if traverse_obj(data, ('code', {int})) == -6221:
- raise ExtractorError('The VOD does not exist', expected=True)
- query = {
+ data = self._download_json(
+ 'https://api.m.afreecatv.com/station/video/a/view', video_id,
+ headers={'Referer': url}, data=urlencode_postdata({
'nTitleNo': video_id,
- 'nStationNo': data['station_no'],
- 'nBbsNo': data['bbs_no'],
- }
- if partial_view:
- query['partialView'] = 'SKIP_ADULT'
- if adult_view:
- query['adultView'] = 'ADULT_VIEW'
- video_xml = self._download_xml(
- 'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
- video_id, 'Downloading video info XML%s'
- % (' (skipping adult)' if partial_view else ''),
- video_id, headers={
- 'Referer': url,
- }, query=query)
-
- flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
- if flag and flag == 'SUCCEED':
- break
- if flag == 'PARTIAL_ADULT':
- self.report_warning(
- 'In accordance with local laws and regulations, underage users are restricted from watching adult content. '
- 'Only content suitable for all ages will be downloaded. '
- 'Provide account credentials if you wish to download restricted content.')
- partial_view = True
- continue
- elif flag == 'ADULT':
- if not adult_view:
- adult_view = True
- continue
- error = 'Only users older than 19 are able to watch this video. Provide account credentials to download this content.'
- else:
- error = flag
- raise ExtractorError(
- '%s said: %s' % (self.IE_NAME, error), expected=True)
- else:
- raise ExtractorError('Unable to download video info')
-
- video_element = video_xml.findall('./track/video')[-1]
- if video_element is None or video_element.text is None:
- raise ExtractorError(
- 'Video %s does not exist' % video_id, expected=True)
-
- video_url = video_element.text.strip()
-
- title = xpath_text(video_xml, './track/title', 'title', fatal=True)
-
- uploader = xpath_text(video_xml, './track/nickname', 'uploader')
- uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
- duration = int_or_none(xpath_text(
- video_xml, './track/duration', 'duration'))
- thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
-
- common_entry = {
- 'uploader': uploader,
- 'uploader_id': uploader_id,
- 'thumbnail': thumbnail,
- }
-
- info = common_entry.copy()
- info.update({
- 'id': video_id,
- 'title': title,
- 'duration': duration,
+ 'nApiLevel': 10,
+ }))['data']
+
+ error_code = traverse_obj(data, ('code', {int}))
+ if error_code == -6221:
+ raise ExtractorError('The VOD does not exist', expected=True)
+ elif error_code == -6205:
+ raise ExtractorError('This VOD is private', expected=True)
+
+ common_info = traverse_obj(data, {
+ 'title': ('title', {str}),
+ 'uploader': ('writer_nick', {str}),
+ 'uploader_id': ('bj_id', {str}),
+ 'duration': ('total_file_duration', {functools.partial(int_or_none, scale=1000)}),
+ 'thumbnail': ('thumb', {url_or_none}),
})
- if not video_url:
- entries = []
- file_elements = video_element.findall('./file')
- one = len(file_elements) == 1
- for file_num, file_element in enumerate(file_elements, start=1):
- file_url = url_or_none(file_element.text)
- if not file_url:
- continue
- key = file_element.get('key', '')
- upload_date = unified_strdate(self._search_regex(
- r'^(\d{8})_', key, 'upload date', default=None))
- if upload_date is not None:
- # sometimes the upload date isn't included in the file name
- # instead, another random ID is, which may parse as a valid
- # date but be wildly out of a reasonable range
- parsed_date = date_from_str(upload_date)
- if parsed_date.year < 2000 or parsed_date.year >= 2100:
- upload_date = None
- file_duration = int_or_none(file_element.get('duration'))
- format_id = key if key else '%s_%s' % (video_id, file_num)
- if determine_ext(file_url) == 'm3u8':
- formats = self._extract_m3u8_formats(
- file_url, video_id, 'mp4', entry_protocol='m3u8_native',
- m3u8_id='hls',
- note='Downloading part %d m3u8 information' % file_num)
- else:
- formats = [{
- 'url': file_url,
- 'format_id': 'http',
- }]
- if not formats and not self.get_param('ignore_no_formats'):
- continue
- file_info = common_entry.copy()
- file_info.update({
- 'id': format_id,
- 'title': title if one else '%s (part %d)' % (title, file_num),
- 'upload_date': upload_date,
- 'duration': file_duration,
- 'formats': formats,
+ entries = []
+ for file_num, file_element in enumerate(
+ traverse_obj(data, ('files', lambda _, v: url_or_none(v['file']))), start=1):
+ file_url = file_element['file']
+ if determine_ext(file_url) == 'm3u8':
+ formats = self._extract_m3u8_formats(
+ file_url, video_id, 'mp4', m3u8_id='hls',
+ note=f'Downloading part {file_num} m3u8 information')
+ else:
+ formats = [{
+ 'url': file_url,
+ 'format_id': 'http',
+ }]
+
+ entries.append({
+ **common_info,
+ 'id': file_element.get('file_info_key') or f'{video_id}_{file_num}',
+ 'title': f'{common_info.get("title") or "Untitled"} (part {file_num})',
+ 'formats': formats,
+ **traverse_obj(file_element, {
+ 'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
+ 'timestamp': ('file_start', {unified_timestamp}),
})
- entries.append(file_info)
- entries_info = info.copy()
- entries_info.update({
- '_type': 'multi_video',
- 'entries': entries,
})
- return entries_info
-
- info = {
- 'id': video_id,
- 'title': title,
- 'uploader': uploader,
- 'uploader_id': uploader_id,
- 'duration': duration,
- 'thumbnail': thumbnail,
- }
- if determine_ext(video_url) == 'm3u8':
- info['formats'] = self._extract_m3u8_formats(
- video_url, video_id, 'mp4', entry_protocol='m3u8_native',
- m3u8_id='hls')
- else:
- app, playpath = video_url.split('mp4:')
- info.update({
- 'url': app,
- 'ext': 'flv',
- 'play_path': 'mp4:' + playpath,
- 'rtmp_live': True, # downloading won't end without this
- })
+ if traverse_obj(data, ('adult_status', {str})) == 'notLogin':
+ if not entries:
+ self.raise_login_required(
+ 'Only users older than 19 are able to watch this video', method='password')
+ self.report_warning(
+ 'In accordance with local laws and regulations, underage users are '
+ 'restricted from watching adult content. Only content suitable for all '
+ f'ages will be downloaded. {self._login_hint("password")}')
+
+ if not entries and traverse_obj(data, ('sub_upload_type', {str})):
+ self.raise_login_required('This VOD is for subscribers only', method='password')
+
+ if len(entries) == 1:
+ return {
+ **entries[0],
+ 'title': common_info.get('title'),
+ }
- return info
+ common_info['timestamp'] = traverse_obj(entries, (..., 'timestamp'), get_all=False)
+ return self.playlist_result(entries, video_id, multi_video=True, **common_info)
-class AfreecaTVLiveIE(AfreecaTVIE): # XXX: Do not subclass from concrete IE
+class AfreecaTVLiveIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:live'
+ IE_DESC = 'afreecatv.com livestreams'
_VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
_TESTS = [{
'url': 'https://play.afreecatv.com/pyh3646/237852185',
@@ -347,77 +268,57 @@ class AfreecaTVLiveIE(AfreecaTVIE): # XXX: Do not subclass from concrete IE
},
'skip': 'Livestream has ended',
}, {
- 'url': 'http://play.afreeca.com/pyh3646/237852185',
+ 'url': 'https://play.afreecatv.com/pyh3646/237852185',
'only_matching': True,
}, {
- 'url': 'http://play.afreeca.com/pyh3646',
+ 'url': 'https://play.afreecatv.com/pyh3646',
'only_matching': True,
}]
_LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
- _QUALITIES = ('sd', 'hd', 'hd2k', 'original')
-
def _real_extract(self, url):
broadcaster_id, broadcast_no = self._match_valid_url(url).group('id', 'bno')
- password = self.get_param('videopassword')
+ channel_info = traverse_obj(self._download_json(
+ self._LIVE_API_URL, broadcaster_id, data=urlencode_postdata({'bid': broadcaster_id})),
+ ('CHANNEL', {dict})) or {}
- info = self._download_json(self._LIVE_API_URL, broadcaster_id, fatal=False,
- data=urlencode_postdata({'bid': broadcaster_id})) or {}
- channel_info = info.get('CHANNEL') or {}
broadcaster_id = channel_info.get('BJID') or broadcaster_id
broadcast_no = channel_info.get('BNO') or broadcast_no
- password_protected = channel_info.get('BPWD')
if not broadcast_no:
- raise ExtractorError(f'Unable to extract broadcast number ({broadcaster_id} may not be live)', expected=True)
- if password_protected == 'Y' and password is None:
+ raise UserNotLive(video_id=broadcaster_id)
+
+ password = self.get_param('videopassword')
+ if channel_info.get('BPWD') == 'Y' and password is None:
raise ExtractorError(
'This livestream is protected by a password, use the --video-password option',
expected=True)
- formats = []
- quality_key = qualities(self._QUALITIES)
- for quality_str in self._QUALITIES:
- params = {
+ aid = self._download_json(
+ self._LIVE_API_URL, broadcast_no, 'Downloading access token for stream',
+ 'Unable to download access token for stream', data=urlencode_postdata(filter_dict({
'bno': broadcast_no,
'stream_type': 'common',
'type': 'aid',
- 'quality': quality_str,
- }
- if password is not None:
- params['pwd'] = password
- aid_response = self._download_json(
- self._LIVE_API_URL, broadcast_no, fatal=False,
- data=urlencode_postdata(params),
- note=f'Downloading access token for {quality_str} stream',
- errnote=f'Unable to download access token for {quality_str} stream')
- aid = traverse_obj(aid_response, ('CHANNEL', 'AID'))
- if not aid:
- continue
-
- stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
- stream_info = self._download_json(
- f'{stream_base_url}/broad_stream_assign.html', broadcast_no, fatal=False,
- query={
- 'return_type': channel_info.get('CDN', 'gcp_cdn'),
- 'broad_key': f'{broadcast_no}-common-{quality_str}-hls',
- },
- note=f'Downloading metadata for {quality_str} stream',
- errnote=f'Unable to download metadata for {quality_str} stream') or {}
-
- if stream_info.get('view_url'):
- formats.append({
- 'format_id': quality_str,
- 'url': update_url_query(stream_info['view_url'], {'aid': aid}),
- 'ext': 'mp4',
- 'protocol': 'm3u8',
- 'quality': quality_key(quality_str),
- })
-
- station_info = self._download_json(
+ 'quality': 'master',
+ 'pwd': password,
+ })))['CHANNEL']['AID']
+
+ stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
+ stream_info = self._download_json(f'{stream_base_url}/broad_stream_assign.html', broadcast_no, query={
+ # works: gs_cdn_pc_app, gs_cdn_mobile_web, gs_cdn_pc_web
+ 'return_type': 'gs_cdn_pc_app',
+ 'broad_key': f'{broadcast_no}-common-master-hls',
+ }, note='Downloading metadata for stream', errnote='Unable to download metadata for stream')
+
+ formats = self._extract_m3u8_formats(
+ stream_info['view_url'], broadcast_no, 'mp4', m3u8_id='hls',
+ query={'aid': aid}, headers={'Referer': url})
+
+ station_info = traverse_obj(self._download_json(
'https://st.afreecatv.com/api/get_station_status.php', broadcast_no,
- query={'szBjId': broadcaster_id}, fatal=False,
- note='Downloading channel metadata', errnote='Unable to download channel metadata') or {}
+ 'Downloading channel metadata', 'Unable to download channel metadata',
+ query={'szBjId': broadcaster_id}, fatal=False), {dict}) or {}
return {
'id': broadcast_no,
@@ -427,6 +328,7 @@ class AfreecaTVLiveIE(AfreecaTVIE): # XXX: Do not subclass from concrete IE
'timestamp': unified_timestamp(station_info.get('broad_start')),
'formats': formats,
'is_live': True,
+ 'http_headers': {'Referer': url},
}