0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
yt-dlp/yt_dlp/extractor/dropbox.py

74 lines
3.3 KiB
Python
Raw Normal View History

2014-01-19 05:16:40 +00:00
import os.path
2014-01-18 15:15:53 +00:00
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import (
ExtractorError,
traverse_obj,
try_get,
url_basename,
)
2014-01-18 15:15:53 +00:00
2014-01-19 05:14:24 +00:00
2014-01-19 04:50:26 +00:00
class DropboxIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dropbox[.]com/sh?/(?P<id>[a-zA-Z0-9]{15})/.*'
2014-11-23 20:39:15 +00:00
_TESTS = [
{
'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
2014-11-23 20:39:15 +00:00
'info_dict': {
'id': 'nelirfsxnmcfbfh',
'ext': 'mp4',
'title': 'youtube-dl test video \'ä"BaW_jenozKc'
2014-11-23 20:39:15 +00:00
}
}, {
'url': 'https://www.dropbox.com/sh/662glsejgzoj9sr/AAByil3FGH9KFNZ13e08eSa1a/Pregame%20Ceremony%20Program%20PA%2020140518.m4v',
'only_matching': True,
},
]
2014-01-19 05:14:24 +00:00
def _real_extract(self, url):
mobj = self._match_valid_url(url)
2014-01-19 05:14:24 +00:00
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
fn = compat_urllib_parse_unquote(url_basename(url))
title = os.path.splitext(fn)[0]
password = self.get_param('videopassword')
if (self._og_search_title(webpage) == 'Dropbox - Password Required'
or 'Enter the password for this link' in webpage):
if password:
content_id = self._search_regex(r'content_id=(.*?)["\']', webpage, 'content_id')
payload = f'is_xhr=true&t={self._get_cookies("https://www.dropbox.com").get("t").value}&content_id={content_id}&password={password}&url={url}'
response = self._download_json(
'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password', data=payload.encode('UTF-8'),
headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'})
if response.get('status') != 'authed':
raise ExtractorError('Authentication failed!', expected=True)
webpage = self._download_webpage(url, video_id)
elif self._get_cookies('https://dropbox.com').get('sm_auth'):
webpage = self._download_webpage(url, video_id)
else:
raise ExtractorError('Password protected video, use --video-password <password>', expected=True)
info_json = self._search_json(r'InitReact\.mountComponent\(.*?,', webpage, 'mountComponent', video_id,
contains_pattern=r'.+?"preview".+?', end_pattern=r'\)')['props']
transcode_url = traverse_obj(info_json, ((None, 'preview'), 'file', 'preview', 'content', 'transcode_url'), get_all=False)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id)
# downloads enabled we can get the original file
if 'anonymous' in (try_get(info_json, lambda x: x['sharePermission']['canDownloadRoles']) or []):
video_url = re.sub(r'[?&]dl=0', '', url)
video_url += ('?' if '?' not in video_url else '&') + 'dl=1'
formats.append({'url': video_url, 'format_id': 'original', 'format_note': 'Original', 'quality': 1})
self._sort_formats(formats)
2014-01-19 05:14:24 +00:00
return {
'id': video_id,
'title': title,
'formats': formats,
'subtitles': subtitles
2014-01-19 05:14:24 +00:00
}