[kakao] improve info extraction and detect geo restriction(closes #26577)

pull/22659/head^2
Remita Amine 2021-02-14 19:48:26 +01:00
parent 6d32c6c6d3
commit d8085580f6
1 changed files with 30 additions and 34 deletions

View File

@ -3,10 +3,13 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_HTTPError
from ..utils import ( from ..utils import (
ExtractorError,
int_or_none, int_or_none,
str_or_none,
strip_or_none, strip_or_none,
try_get,
unified_timestamp, unified_timestamp,
update_url_query, update_url_query,
) )
@ -23,7 +26,7 @@ class KakaoIE(InfoExtractor):
'id': '301965083', 'id': '301965083',
'ext': 'mp4', 'ext': 'mp4',
'title': '乃木坂46 バナナマン 「3期生紹介コーナーが始動顔高低差GPも」 『乃木坂工事中』', 'title': '乃木坂46 バナナマン 「3期生紹介コーナーが始動顔高低差GPも」 『乃木坂工事中』',
'uploader_id': 2671005, 'uploader_id': '2671005',
'uploader': '그랑그랑이', 'uploader': '그랑그랑이',
'timestamp': 1488160199, 'timestamp': 1488160199,
'upload_date': '20170227', 'upload_date': '20170227',
@ -36,11 +39,15 @@ class KakaoIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회', 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)', 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
'uploader_id': 2653210, 'uploader_id': '2653210',
'uploader': '쇼! 음악중심', 'uploader': '쇼! 음악중심',
'timestamp': 1485684628, 'timestamp': 1485684628,
'upload_date': '20170129', 'upload_date': '20170129',
} }
}, {
# geo restricted
'url': 'https://tv.kakao.com/channel/3643855/cliplink/412069491',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -68,8 +75,7 @@ class KakaoIE(InfoExtractor):
'fields': ','.join([ 'fields': ','.join([
'-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title', '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
'description', 'channelId', 'createTime', 'duration', 'playCount', 'description', 'channelId', 'createTime', 'duration', 'playCount',
'likeCount', 'commentCount', 'tagList', 'channel', 'name', 'likeCount', 'commentCount', 'tagList', 'channel', 'name', 'thumbnailUrl',
'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault',
'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label']) 'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
} }
@ -82,24 +88,28 @@ class KakaoIE(InfoExtractor):
title = clip.get('title') or clip_link.get('displayTitle') title = clip.get('title') or clip_link.get('displayTitle')
query['tid'] = impress.get('tid', '') query.update({
'fields': '-*,code,message,url',
'tid': impress.get('tid') or '',
})
formats = [] formats = []
for fmt in clip.get('videoOutputList', []): for fmt in (clip.get('videoOutputList') or []):
try: try:
profile_name = fmt['profile'] profile_name = fmt['profile']
if profile_name == 'AUDIO': if profile_name == 'AUDIO':
continue continue
query.update({ query['profile'] = profile_name
'profile': profile_name, try:
'fields': '-*,url', fmt_url_json = self._download_json(
}) api_base + 'raw/videolocation', display_id,
fmt_url_json = self._download_json( 'Downloading video URL for profile %s' % profile_name,
api_base + 'raw/videolocation', display_id, query=query, headers=player_header)
'Downloading video URL for profile %s' % profile_name, except ExtractorError as e:
query=query, headers=player_header, fatal=False) if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
resp = self._parse_json(e.cause.read().decode(), video_id)
if fmt_url_json is None: if resp.get('code') == 'GeoBlocked':
self.raise_geo_restricted()
continue continue
fmt_url = fmt_url_json['url'] fmt_url = fmt_url_json['url']
@ -116,27 +126,13 @@ class KakaoIE(InfoExtractor):
pass pass
self._sort_formats(formats) self._sort_formats(formats)
thumbs = []
for thumb in clip.get('clipChapterThumbnailList', []):
thumbs.append({
'url': thumb.get('thumbnailUrl'),
'id': compat_str(thumb.get('timeInSec')),
'preference': -1 if thumb.get('isDefault') else 0
})
top_thumbnail = clip.get('thumbnailUrl')
if top_thumbnail:
thumbs.append({
'url': top_thumbnail,
'preference': 10,
})
return { return {
'id': display_id, 'id': display_id,
'title': title, 'title': title,
'description': strip_or_none(clip.get('description')), 'description': strip_or_none(clip.get('description')),
'uploader': clip_link.get('channel', {}).get('name'), 'uploader': try_get(clip_link, lambda x: x['channel']['name']),
'uploader_id': clip_link.get('channelId'), 'uploader_id': str_or_none(clip_link.get('channelId')),
'thumbnails': thumbs, 'thumbnail': clip.get('thumbnailUrl'),
'timestamp': unified_timestamp(clip_link.get('createTime')), 'timestamp': unified_timestamp(clip_link.get('createTime')),
'duration': int_or_none(clip.get('duration')), 'duration': int_or_none(clip.get('duration')),
'view_count': int_or_none(clip.get('playCount')), 'view_count': int_or_none(clip.get('playCount')),