1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-27 10:25:49 +01:00
youtube-dl/youtube_dl/extractor/kakao.py

148 lines
5.4 KiB
Python
Raw Normal View History

2017-08-24 04:32:24 +02:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
2017-09-23 02:25:15 +02:00
from ..compat import compat_str
2017-08-24 04:32:24 +02:00
from ..utils import (
int_or_none,
strip_or_none,
2017-08-24 04:32:24 +02:00
unified_timestamp,
2017-09-23 02:25:15 +02:00
update_url_query,
2017-08-24 04:32:24 +02:00
)
class KakaoIE(InfoExtractor):
_VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P<id>\d+|[^?#&]+@my)'
_API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/cliplinks/%s/'
2017-08-24 04:32:24 +02:00
_TESTS = [{
'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083',
'md5': '702b2fbdeb51ad82f5c904e8c0766340',
'info_dict': {
'id': '301965083',
'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』',
'uploader_id': 2671005,
'uploader': '그랑그랑이',
'timestamp': 1488160199,
'upload_date': '20170227',
}
}, {
'url': 'http://tv.kakao.com/channel/2653210/cliplink/300103180',
'md5': 'a8917742069a4dd442516b86e7d66529',
'info_dict': {
'id': '300103180',
'ext': 'mp4',
'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
'uploader_id': 2653210,
'uploader': '쇼! 음악중심',
2017-08-24 04:32:24 +02:00
'timestamp': 1485684628,
'upload_date': '20170129',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
display_id = video_id.rstrip('@my')
api_base = self._API_BASE_TMPL % video_id
2017-08-24 04:32:24 +02:00
2017-09-23 02:25:15 +02:00
player_header = {
'Referer': update_url_query(
'http://tv.kakao.com/embed/player/cliplink/%s' % video_id, {
'service': 'kakao_tv',
'autoplay': '1',
'profile': 'HIGH',
'wmode': 'transparent',
})
}
query = {
2017-09-23 02:25:15 +02:00
'player': 'monet_html5',
'referer': url,
'uuid': '',
'service': 'kakao_tv',
'section': '',
'dteType': 'PC',
'fields': ','.join([
'-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
'description', 'channelId', 'createTime', 'duration', 'playCount',
'likeCount', 'commentCount', 'tagList', 'channel', 'name',
'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault',
'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
2017-09-23 02:25:15 +02:00
}
2017-08-24 04:32:24 +02:00
impress = self._download_json(
api_base + 'impress', display_id, 'Downloading video info',
2017-09-23 02:25:15 +02:00
query=query, headers=player_header)
clip_link = impress['clipLink']
clip = clip_link['clip']
title = clip.get('title') or clip_link.get('displayTitle')
2017-08-24 04:32:24 +02:00
query['tid'] = impress.get('tid', '')
2017-08-24 04:32:24 +02:00
formats = []
for fmt in clip.get('videoOutputList', []):
2017-08-24 04:32:24 +02:00
try:
profile_name = fmt['profile']
if profile_name == 'AUDIO':
continue
query.update({
'profile': profile_name,
'fields': '-*,url',
})
2017-08-24 04:32:24 +02:00
fmt_url_json = self._download_json(
api_base + 'raw/videolocation', display_id,
2017-09-23 02:25:15 +02:00
'Downloading video URL for profile %s' % profile_name,
query=query, headers=player_header, fatal=False)
2017-08-24 04:32:24 +02:00
if fmt_url_json is None:
continue
fmt_url = fmt_url_json['url']
formats.append({
'url': fmt_url,
'format_id': profile_name,
'width': int_or_none(fmt.get('width')),
'height': int_or_none(fmt.get('height')),
'format_note': fmt.get('label'),
'filesize': int_or_none(fmt.get('filesize')),
'tbr': int_or_none(fmt.get('kbps')),
2017-08-24 04:32:24 +02:00
})
except KeyError:
pass
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
})
2017-09-23 02:25:15 +02:00
top_thumbnail = clip.get('thumbnailUrl')
if top_thumbnail:
thumbs.append({
'url': top_thumbnail,
'preference': 10,
})
2017-08-24 04:32:24 +02:00
2017-09-23 02:25:15 +02:00
return {
'id': display_id,
2017-09-23 02:25:15 +02:00
'title': title,
'description': strip_or_none(clip.get('description')),
2017-09-23 02:25:15 +02:00
'uploader': clip_link.get('channel', {}).get('name'),
'uploader_id': clip_link.get('channelId'),
'thumbnails': thumbs,
'timestamp': unified_timestamp(clip_link.get('createTime')),
'duration': int_or_none(clip.get('duration')),
'view_count': int_or_none(clip.get('playCount')),
'like_count': int_or_none(clip.get('likeCount')),
'comment_count': int_or_none(clip.get('commentCount')),
'formats': formats,
'tags': clip.get('tagList'),
2017-09-23 02:25:15 +02:00
}