[ie/PiaLive] Add extractor (#10811)

Authored by: ChocoLZS
This commit is contained in:
ChocoLZS 2024-11-18 02:41:57 +08:00 committed by GitHub
parent 10fc719bc7
commit d867f99622
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 240 additions and 71 deletions

View file

@ -1520,8 +1520,8 @@ from .pgatour import PGATourIE
from .philharmoniedeparis import PhilharmonieDeParisIE from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE from .photobucket import PhotobucketIE
from .pialive import PiaLiveIE
from .piapro import PiaproIE from .piapro import PiaproIE
from .piaulizaportal import PIAULIZAPortalIE
from .picarto import ( from .picarto import (
PicartoIE, PicartoIE,
PicartoVodIE, PicartoVodIE,
@ -2250,6 +2250,10 @@ from .ufctv import (
) )
from .ukcolumn import UkColumnIE from .ukcolumn import UkColumnIE
from .uktvplay import UKTVPlayIE from .uktvplay import UKTVPlayIE
from .uliza import (
UlizaPlayerIE,
UlizaPortalIE,
)
from .umg import UMGDeIE from .umg import UMGDeIE
from .unistra import UnistraIE from .unistra import UnistraIE
from .unity import UnityIE from .unity import UnityIE

122
yt_dlp/extractor/pialive.py Normal file
View file

@ -0,0 +1,122 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_class,
multipart_encode,
str_or_none,
unified_timestamp,
url_or_none,
)
from ..utils.traversal import traverse_obj
class PiaLiveIE(InfoExtractor):
_VALID_URL = r'https?://player\.pia-live\.jp/stream/(?P<id>[\w-]+)'
_PLAYER_ROOT_URL = 'https://player.pia-live.jp/'
_PIA_LIVE_API_URL = 'https://api.pia-live.jp'
_API_KEY = 'kfds)FKFps-dms9e'
_TESTS = [{
'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krUDqGOwN4d61dCWQYOd6CTxl4hjya9dsfEZGsM4uGOUdax60lEI4twsXGXf7crmz8Gk__GhupTrWxA7RFRVt76',
'info_dict': {
'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
'display_id': '2431867_001',
'title': 'こながめでたい日2024の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)',
'live_status': 'was_live',
'comment_count': int,
},
'params': {
'getcomments': True,
'skip_download': True,
'ignore_no_formats_error': True,
},
'skip': 'The video is no longer available',
}, {
'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krJdu0GVBVbVy01IwpJ6J3qBEm3d9TCTt1d0eWpsZGj7DrOjVOmS7GAWGwyscMgiThopJvzgWC4H5b-7XQjAfRZ',
'info_dict': {
'id': '9ce8b8ba-f6d1-4d1f-83a0-18c3148ded93',
'display_id': '2431867_002',
'title': 'こながめでたい日2024の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)',
'live_status': 'was_live',
'comment_count': int,
},
'params': {
'getcomments': True,
'skip_download': True,
'ignore_no_formats_error': True,
},
'skip': 'The video is no longer available',
}]
def _extract_var(self, variable, html):
return self._search_regex(
rf'(?:var|const|let)\s+{variable}\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
html, f'variable {variable}', group='value')
def _real_extract(self, url):
video_key = self._match_id(url)
webpage = self._download_webpage(url, video_key)
program_code = self._extract_var('programCode', webpage)
article_code = self._extract_var('articleCode', webpage)
title = self._html_extract_title(webpage)
if get_element_html_by_class('play-end', webpage):
raise ExtractorError('The video is no longer available', expected=True, video_id=program_code)
if start_info := clean_html(get_element_by_class('play-waiting__date', webpage)):
date, time = self._search_regex(
r'(?P<date>\d{4}/\d{1,2}/\d{1,2})\([月火水木金土日]\)(?P<time>\d{2}:\d{2})',
start_info, 'start_info', fatal=False, group=('date', 'time'))
if date and time:
release_timestamp_str = f'{date} {time} +09:00'
release_timestamp = unified_timestamp(release_timestamp_str)
self.raise_no_formats(f'The video will be available after {release_timestamp_str}', expected=True)
return {
'id': program_code,
'title': title,
'live_status': 'is_upcoming',
'release_timestamp': release_timestamp,
}
payload, content_type = multipart_encode({
'play_url': video_key,
'api_key': self._API_KEY,
})
api_data_and_headers = {
'data': payload,
'headers': {'Content-Type': content_type, 'Referer': self._PLAYER_ROOT_URL},
}
player_tag_list = self._download_json(
f'{self._PIA_LIVE_API_URL}/perf/player-tag-list/{program_code}', program_code,
'Fetching player tag list', 'Unable to fetch player tag list', **api_data_and_headers)
return self.url_result(
extract_attributes(player_tag_list['data']['movie_one_tag'])['src'],
url_transparent=True, title=title, display_id=program_code,
__post_extractor=self.extract_comments(program_code, article_code, api_data_and_headers))
def _get_comments(self, program_code, article_code, api_data_and_headers):
chat_room_url = traverse_obj(self._download_json(
f'{self._PIA_LIVE_API_URL}/perf/chat-tag-list/{program_code}/{article_code}', program_code,
'Fetching chat info', 'Unable to fetch chat info', fatal=False, **api_data_and_headers),
('data', 'chat_one_tag', {extract_attributes}, 'src', {url_or_none}))
if not chat_room_url:
return
comment_page = self._download_webpage(
chat_room_url, program_code, 'Fetching comment page', 'Unable to fetch comment page',
fatal=False, headers={'Referer': self._PLAYER_ROOT_URL})
if not comment_page:
return
yield from traverse_obj(self._search_json(
r'var\s+_history\s*=', comment_page, 'comment list',
program_code, contains_pattern=r'\[(?s:.+)\]', fatal=False), (..., {
'timestamp': (0, {int}),
'author_is_uploader': (1, {lambda x: x == 2}),
'author': (2, {str}),
'text': (3, {str}),
'id': (4, {str_or_none}),
}))

View file

@ -1,70 +0,0 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
parse_qs,
time_seconds,
traverse_obj,
)
class PIAULIZAPortalIE(InfoExtractor):
IE_DESC = 'ulizaportal.jp - PIA LIVE STREAM'
_VALID_URL = r'https?://(?:www\.)?ulizaportal\.jp/pages/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_TESTS = [{
'url': 'https://ulizaportal.jp/pages/005f18b7-e810-5618-cb82-0987c5755d44',
'info_dict': {
'id': '005f18b7-e810-5618-cb82-0987c5755d44',
'title': 'プレゼンテーションプレイヤーのサンプル',
'live_status': 'not_live',
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}, {
'url': 'https://ulizaportal.jp/pages/005e1b23-fe93-5780-19a0-98e917cc4b7d?expires=4102412400&signature=f422a993b683e1068f946caf406d211c17d1ef17da8bef3df4a519502155aa91&version=1',
'info_dict': {
'id': '005e1b23-fe93-5780-19a0-98e917cc4b7d',
'title': '【確認用】視聴サンプルページULIZA',
'live_status': 'not_live',
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
expires = int_or_none(traverse_obj(parse_qs(url), ('expires', 0)))
if expires and expires <= time_seconds():
raise ExtractorError('The link is expired.', video_id=video_id, expected=True)
webpage = self._download_webpage(url, video_id)
player_data = self._download_webpage(
self._search_regex(
r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
webpage, 'player data url'),
video_id, headers={'Referer': 'https://ulizaportal.jp/'},
note='Fetching player data', errnote='Unable to fetch player data')
formats = self._extract_m3u8_formats(
self._search_regex(
r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data,
'm3u8 url', default=None),
video_id, fatal=False)
m3u8_type = self._search_regex(
r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
return {
'id': video_id,
'title': self._html_extract_title(webpage),
'formats': formats,
'live_status': {
'video': 'is_live',
'dvr': 'was_live', # short-term archives
}.get(m3u8_type, 'not_live'), # VOD or long-term archives
}

113
yt_dlp/extractor/uliza.py Normal file
View file

@ -0,0 +1,113 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
make_archive_id,
parse_qs,
time_seconds,
)
from ..utils.traversal import traverse_obj
class UlizaPlayerIE(InfoExtractor):
_VALID_URL = r'https://player-api\.p\.uliza\.jp/v1/players/[^?#]+\?(?:[^#]*&)?name=(?P<id>[^#&]+)'
_TESTS = [{
'url': 'https://player-api.p.uliza.jp/v1/players/timeshift-disabled/pia/admin?type=normal&playerobjectname=ulizaPlayer&name=livestream01_dvr&repeatable=true',
'info_dict': {
'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
'ext': 'mp4',
'title': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
'live_status': 'was_live',
'_old_archive_ids': ['piaulizaportal 88f3109a-f503-4d0f-a9f7-9f39ac745d84'],
},
}, {
'url': 'https://player-api.p.uliza.jp/v1/players/uliza_jp_gallery_normal/promotion/admin?type=presentation&name=cookings&targetid=player1',
'info_dict': {
'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
'ext': 'mp4',
'title': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
'live_status': 'not_live',
'_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
},
}, {
'url': 'https://player-api.p.uliza.jp/v1/players/default-player/pia/admin?type=normal&name=pia_movie_uliza_fix&targetid=ulizahtml5&repeatable=true',
'info_dict': {
'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
'ext': 'mp4',
'title': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
'live_status': 'not_live',
'_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
player_data = self._download_webpage(
url, display_id, headers={'Referer': 'https://player-api.p.uliza.jp/'},
note='Fetching player data', errnote='Unable to fetch player data')
m3u8_url = self._search_regex(
r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data, 'm3u8 url')
video_id = parse_qs(m3u8_url).get('ss', [display_id])[0]
formats = self._extract_m3u8_formats(m3u8_url, video_id)
m3u8_type = self._search_regex(
r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
return {
'id': video_id,
'title': video_id,
'formats': formats,
'live_status': {
'video': 'is_live',
'dvr': 'was_live', # short-term archives
}.get(m3u8_type, 'not_live'), # VOD or long-term archives
'_old_archive_ids': [make_archive_id('PIAULIZAPortal', video_id)],
}
class UlizaPortalIE(InfoExtractor):
IE_DESC = 'ulizaportal.jp'
_VALID_URL = r'https?://(?:www\.)?ulizaportal\.jp/pages/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_TESTS = [{
'url': 'https://ulizaportal.jp/pages/005f18b7-e810-5618-cb82-0987c5755d44',
'info_dict': {
'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
'display_id': '005f18b7-e810-5618-cb82-0987c5755d44',
'title': 'プレゼンテーションプレイヤーのサンプル',
'live_status': 'not_live',
'_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}, {
'url': 'https://ulizaportal.jp/pages/005e1b23-fe93-5780-19a0-98e917cc4b7d?expires=4102412400&signature=f422a993b683e1068f946caf406d211c17d1ef17da8bef3df4a519502155aa91&version=1',
'info_dict': {
'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
'display_id': '005e1b23-fe93-5780-19a0-98e917cc4b7d',
'title': '【確認用】視聴サンプルページULIZA',
'live_status': 'not_live',
'_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
expires = int_or_none(traverse_obj(parse_qs(url), ('expires', 0)))
if expires and expires <= time_seconds():
raise ExtractorError('The link is expired', video_id=video_id, expected=True)
webpage = self._download_webpage(url, video_id)
player_data_url = self._search_regex(
r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
webpage, 'player data url')
return self.url_result(
player_data_url, UlizaPlayerIE, url_transparent=True,
display_id=video_id, video_title=self._html_extract_title(webpage))