mirror of https://github.com/yt-dlp/yt-dlp
Merge branch 'yt-dlp:master' into onsen
doe1080
2 months ago
committed by
GitHub
commit
9b1d30cccf
@ -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}),
|
||||
}))
|
||||
@ -1,189 +0,0 @@
|
||||
import functools
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
OnDemandPagedList,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
qualities,
|
||||
remove_start,
|
||||
strip_or_none,
|
||||
)
|
||||
|
||||
|
||||
class VeohIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|videos|embed|iphone/#_Watch)/(?P<id>(?:v|e|yapi-)[\da-zA-Z]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
|
||||
'md5': '620e68e6a3cff80086df3348426c9ca3',
|
||||
'info_dict': {
|
||||
'id': 'v56314296nk7Zdmz3',
|
||||
'ext': 'mp4',
|
||||
'title': 'Straight Backs Are Stronger',
|
||||
'description': 'md5:203f976279939a6dc664d4001e13f5f4',
|
||||
'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th56314296\\.jpg(\\?.*)?',
|
||||
'uploader': 'LUMOback',
|
||||
'duration': 46,
|
||||
'view_count': int,
|
||||
'average_rating': int,
|
||||
'comment_count': int,
|
||||
'age_limit': 0,
|
||||
'categories': ['technology_and_gaming'],
|
||||
'tags': ['posture', 'posture', 'sensor', 'back', 'pain', 'wearable', 'tech', 'lumo'],
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.veoh.com/embed/v56314296nk7Zdmz3',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
|
||||
'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
|
||||
'info_dict': {
|
||||
'id': '27701988',
|
||||
'ext': 'mp4',
|
||||
'title': 'Chile workers cover up to avoid skin damage',
|
||||
'description': 'md5:2bd151625a60a32822873efc246ba20d',
|
||||
'uploader': 'afp-news',
|
||||
'duration': 123,
|
||||
},
|
||||
'skip': 'This video has been deleted.',
|
||||
}, {
|
||||
'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
|
||||
'md5': '4fde7b9e33577bab2f2f8f260e30e979',
|
||||
'note': 'Embedded ooyala video',
|
||||
'info_dict': {
|
||||
'id': '69525809',
|
||||
'ext': 'mp4',
|
||||
'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
|
||||
'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
|
||||
'uploader': 'newsy-videos',
|
||||
},
|
||||
'skip': 'This video has been deleted.',
|
||||
}, {
|
||||
'url': 'http://www.veoh.com/watch/e152215AJxZktGS',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.veoh.com/videos/v16374379WA437rMH',
|
||||
'md5': 'cceb73f3909063d64f4b93d4defca1b3',
|
||||
'info_dict': {
|
||||
'id': 'v16374379WA437rMH',
|
||||
'ext': 'mp4',
|
||||
'title': 'Phantasmagoria 2, pt. 1-3',
|
||||
'description': 'Phantasmagoria: a Puzzle of Flesh',
|
||||
'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th16374379\\.jpg(\\?.*)?',
|
||||
'uploader': 'davidspackage',
|
||||
'duration': 968,
|
||||
'view_count': int,
|
||||
'average_rating': int,
|
||||
'comment_count': int,
|
||||
'age_limit': 18,
|
||||
'categories': ['technology_and_gaming', 'gaming'],
|
||||
'tags': ['puzzle', 'of', 'flesh'],
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
metadata = self._download_json(
|
||||
'https://www.veoh.com/watch/getVideo/' + video_id,
|
||||
video_id)
|
||||
video = metadata['video']
|
||||
title = video['title']
|
||||
|
||||
thumbnail_url = None
|
||||
q = qualities(['Regular', 'HQ'])
|
||||
formats = []
|
||||
for f_id, f_url in video.get('src', {}).items():
|
||||
if not f_url:
|
||||
continue
|
||||
if f_id == 'poster':
|
||||
thumbnail_url = f_url
|
||||
else:
|
||||
formats.append({
|
||||
'format_id': f_id,
|
||||
'quality': q(f_id),
|
||||
'url': f_url,
|
||||
})
|
||||
|
||||
categories = metadata.get('categoryPath')
|
||||
if not categories:
|
||||
category = remove_start(strip_or_none(video.get('category')), 'category_')
|
||||
categories = [category] if category else None
|
||||
tags = video.get('tags')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': video.get('description'),
|
||||
'thumbnail': thumbnail_url,
|
||||
'uploader': video.get('author', {}).get('nickname'),
|
||||
'duration': int_or_none(video.get('lengthBySec')) or parse_duration(video.get('length')),
|
||||
'view_count': int_or_none(video.get('views')),
|
||||
'formats': formats,
|
||||
'average_rating': int_or_none(video.get('rating')),
|
||||
'comment_count': int_or_none(video.get('numOfComments')),
|
||||
'age_limit': 18 if video.get('contentRatingId') == 2 else 0,
|
||||
'categories': categories,
|
||||
'tags': tags.split(', ') if tags else None,
|
||||
}
|
||||
|
||||
|
||||
class VeohUserIE(VeohIE): # XXX: Do not subclass from concrete IE
|
||||
_VALID_URL = r'https?://(?:www\.)?veoh\.com/users/(?P<id>[\w-]+)'
|
||||
IE_NAME = 'veoh:user'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'https://www.veoh.com/users/valentinazoe',
|
||||
'info_dict': {
|
||||
'id': 'valentinazoe',
|
||||
'title': 'valentinazoe (Uploads)',
|
||||
},
|
||||
'playlist_mincount': 75,
|
||||
},
|
||||
{
|
||||
'url': 'https://www.veoh.com/users/PiensaLibre',
|
||||
'info_dict': {
|
||||
'id': 'PiensaLibre',
|
||||
'title': 'PiensaLibre (Uploads)',
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
}]
|
||||
|
||||
_PAGE_SIZE = 16
|
||||
|
||||
def _fetch_page(self, uploader, page):
|
||||
response = self._download_json(
|
||||
'https://www.veoh.com/users/published/videos', uploader,
|
||||
note=f'Downloading videos page {page + 1}',
|
||||
headers={
|
||||
'x-csrf-token': self._TOKEN,
|
||||
'content-type': 'application/json;charset=UTF-8',
|
||||
},
|
||||
data=json.dumps({
|
||||
'username': uploader,
|
||||
'maxResults': self._PAGE_SIZE,
|
||||
'page': page + 1,
|
||||
'requestName': 'userPage',
|
||||
}).encode())
|
||||
if not response.get('success'):
|
||||
raise ExtractorError(response['message'])
|
||||
|
||||
for video in response['videos']:
|
||||
yield self.url_result(f'https://www.veoh.com/watch/{video["permalinkId"]}', VeohIE,
|
||||
video['permalinkId'], video.get('title'))
|
||||
|
||||
def _real_initialize(self):
|
||||
webpage = self._download_webpage(
|
||||
'https://www.veoh.com', None, note='Downloading authorization token')
|
||||
self._TOKEN = self._search_regex(
|
||||
r'csrfToken:\s*(["\'])(?P<token>[0-9a-zA-Z]{40})\1', webpage,
|
||||
'request token', group='token')
|
||||
|
||||
def _real_extract(self, url):
|
||||
uploader = self._match_id(url)
|
||||
return self.playlist_result(OnDemandPagedList(
|
||||
functools.partial(self._fetch_page, uploader),
|
||||
self._PAGE_SIZE), uploader, f'{uploader} (Uploads)')
|
||||
Loading…
Reference in New Issue