From 7141ced57dc05d9a8a3c56dd7990c61852894eed Mon Sep 17 00:00:00 2001 From: zenerdi0de <83358565+zenerdi0de@users.noreply.github.com> Date: Sun, 2 Jan 2022 16:14:10 +0530 Subject: [PATCH] [Dropbox] Support password protected files and more formats (#2201) Authored by: zenerdi0de --- yt_dlp/extractor/dropbox.py | 44 +++++++++++++++++++++++++++++++++---- 1 file changed, 40 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/dropbox.py b/yt_dlp/extractor/dropbox.py index 6a7d050aa..3ae3a8d3d 100644 --- a/yt_dlp/extractor/dropbox.py +++ b/yt_dlp/extractor/dropbox.py @@ -6,7 +6,12 @@ from .common import InfoExtractor from ..compat import compat_urllib_parse_unquote -from ..utils import url_basename +from ..utils import ( + ExtractorError, + traverse_obj, + try_get, + url_basename, +) class DropboxIE(InfoExtractor): @@ -28,13 +33,44 @@ class DropboxIE(InfoExtractor): def _real_extract(self, url): mobj = self._match_valid_url(url) 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] - video_url = re.sub(r'[?&]dl=0', '', url) - video_url += ('?' if '?' not in video_url else '&') + 'dl=1' + + 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 ', expected=True) + + json_string = self._html_search_regex(r'InitReact\.mountComponent.+ "props":(.+), "elem_id"', webpage, 'Info JSON') + info_json = self._parse_json(json_string, video_id) + 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) return { 'id': video_id, 'title': title, - 'url': video_url, + 'formats': formats, + 'subtitles': subtitles }