youtube-dl/youtube_dl/extractor/tiktok.py

148 lines
4.9 KiB
Python
Raw Permalink Normal View History

2018-11-09 21:49:20 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
compat_str,
ExtractorError,
float_or_none,
2018-11-09 21:49:20 +00:00
int_or_none,
str_or_none,
try_get,
url_or_none,
)
class TikTokBaseIE(InfoExtractor):
def _extract_video(self, data, video_id=None):
video = data['video']
2018-11-09 21:49:20 +00:00
description = str_or_none(try_get(data, lambda x: x['desc']))
width = int_or_none(try_get(data, lambda x: video['width']))
height = int_or_none(try_get(data, lambda x: video['height']))
2018-11-09 21:49:20 +00:00
format_urls = set()
2018-11-09 21:49:20 +00:00
formats = []
for format_id in ('download', 'play'):
format_url = url_or_none(video.get('%sAddr' % format_id))
if not format_url:
continue
if format_url in format_urls:
continue
format_urls.add(format_url)
formats.append({
'url': format_url,
'ext': 'mp4',
'height': height,
'width': width,
'http_headers': {
'Referer': 'https://www.tiktok.com/',
}
})
2018-11-09 21:49:20 +00:00
self._sort_formats(formats)
thumbnail = url_or_none(video.get('cover'))
duration = float_or_none(video.get('duration'))
2018-11-09 21:49:20 +00:00
uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
uploader_id = try_get(data, lambda x: x['author']['id'], compat_str)
timestamp = int_or_none(data.get('createTime'))
2018-11-09 21:49:20 +00:00
def stats(key):
return int_or_none(try_get(
data, lambda x: x['stats']['%sCount' % key]))
view_count = stats('play')
like_count = stats('digg')
comment_count = stats('comment')
repost_count = stats('share')
aweme_id = data.get('id') or video_id
2018-11-09 21:49:20 +00:00
return {
'id': aweme_id,
'title': uploader or aweme_id,
2018-11-09 21:49:20 +00:00
'description': description,
'thumbnail': thumbnail,
'duration': duration,
2018-11-09 21:49:20 +00:00
'uploader': uploader,
'uploader_id': uploader_id,
'timestamp': timestamp,
'view_count': view_count,
'like_count': like_count,
'comment_count': comment_count,
'repost_count': repost_count,
2018-11-09 21:49:20 +00:00
'formats': formats,
}
class TikTokIE(TikTokBaseIE):
_VALID_URL = r'https?://(?:www\.)?tiktok\.com/@[^/]+/video/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.tiktok.com/@zureeal/video/6606727368545406213',
'md5': '163ceff303bb52de60e6887fe399e6cd',
'info_dict': {
'id': '6606727368545406213',
'ext': 'mp4',
'title': 'Zureeal',
'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay',
'thumbnail': r're:^https?://.*',
'duration': 15,
'uploader': 'Zureeal',
'uploader_id': '188294915489964032',
'timestamp': 1538248586,
'upload_date': '20180929',
'view_count': int,
'like_count': int,
'comment_count': int,
'repost_count': int,
}
}]
def _real_initialize(self):
# Setup session (will set necessary cookies)
self._request_webpage(
'https://www.tiktok.com/', None, note='Setting up session')
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
page_props = self._parse_json(self._search_regex(
r'<script[^>]+\bid=["\']__NEXT_DATA__[^>]+>\s*({.+?})\s*</script',
webpage, 'data'), video_id)['props']['pageProps']
data = try_get(page_props, lambda x: x['itemInfo']['itemStruct'], dict)
if not data and page_props.get('statusCode') == 10216:
raise ExtractorError('This video is private', expected=True)
return self._extract_video(data, video_id)
class TikTokUserIE(TikTokBaseIE):
_VALID_URL = r'https://(?:www\.)?tiktok\.com/@(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.tiktok.com/@zureeal',
'info_dict': {
'id': '188294915489964032',
},
'playlist_mincount': 24,
}]
_WORKING = False
@classmethod
def suitable(cls, url):
return False if TikTokIE.suitable(url) else super(TikTokUserIE, cls).suitable(url)
def _real_extract(self, url):
user_id = self._match_id(url)
data = self._download_json(
'https://m.tiktok.com/h5/share/usr/list/%s/' % user_id, user_id,
query={'_signature': '_'})
entries = []
for aweme in data['aweme_list']:
try:
entry = self._extract_video(aweme)
except ExtractorError:
continue
entry['extractor_key'] = TikTokIE.ie_key()
entries.append(entry)
return self.playlist_result(entries, user_id)