diff options
Diffstat (limited to 'hypervideo_dl/extractor/googledrive.py')
| -rw-r--r-- | hypervideo_dl/extractor/googledrive.py | 68 |
1 files changed, 60 insertions, 8 deletions
diff --git a/hypervideo_dl/extractor/googledrive.py b/hypervideo_dl/extractor/googledrive.py index 7b5bf28..e027ea7 100644 --- a/hypervideo_dl/extractor/googledrive.py +++ b/hypervideo_dl/extractor/googledrive.py @@ -1,5 +1,3 @@ -from __future__ import unicode_literals - import re from .common import InfoExtractor @@ -79,13 +77,13 @@ class GoogleDriveIE(InfoExtractor): _caption_formats_ext = [] _captions_xml = None - @staticmethod - def _extract_url(webpage): + @classmethod + def _extract_embed_urls(cls, url, webpage): mobj = re.search( r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})', webpage) if mobj: - return 'https://drive.google.com/file/d/%s' % mobj.group('id') + yield 'https://drive.google.com/file/d/%s' % mobj.group('id') def _download_subtitles_xml(self, video_id, subtitles_id, hl): if self._captions_xml: @@ -255,8 +253,6 @@ class GoogleDriveIE(InfoExtractor): if not formats and reason: self.raise_no_formats(reason, expected=True) - self._sort_formats(formats) - hl = get_value('hl') subtitles_id = None ttsurl = get_value('ttsurl') @@ -266,7 +262,7 @@ class GoogleDriveIE(InfoExtractor): subtitles_id = ttsurl.encode('utf-8').decode( 'unicode_escape').split('=')[-1] - self._downloader.cookiejar.clear(domain='.google.com', path='/', name='NID') + self.cookiejar.clear(domain='.google.com', path='/', name='NID') return { 'id': video_id, @@ -278,3 +274,59 @@ class GoogleDriveIE(InfoExtractor): 'automatic_captions': self.extract_automatic_captions( video_id, subtitles_id, hl), } + + +class GoogleDriveFolderIE(InfoExtractor): + IE_NAME = 'GoogleDrive:Folder' + _VALID_URL = r'https?://(?:docs|drive)\.google\.com/drive/folders/(?P<id>[\w-]{28,})' + _TESTS = [{ + 'url': 'https://drive.google.com/drive/folders/1dQ4sx0-__Nvg65rxTSgQrl7VyW_FZ9QI', + 'info_dict': { + 'id': '1dQ4sx0-__Nvg65rxTSgQrl7VyW_FZ9QI', + 'title': 'Forrest' + }, + 'playlist_count': 3, + }] + _BOUNDARY = '=====vc17a3rwnndj=====' + _REQUEST = "/drive/v2beta/files?openDrive=true&reason=102&syncType=0&errorRecovery=false&q=trashed%20%3D%20false%20and%20'{folder_id}'%20in%20parents&fields=kind%2CnextPageToken%2Citems(kind%2CmodifiedDate%2CmodifiedByMeDate%2ClastViewedByMeDate%2CfileSize%2Cowners(kind%2CpermissionId%2Cid)%2ClastModifyingUser(kind%2CpermissionId%2Cid)%2ChasThumbnail%2CthumbnailVersion%2Ctitle%2Cid%2CresourceKey%2Cshared%2CsharedWithMeDate%2CuserPermission(role)%2CexplicitlyTrashed%2CmimeType%2CquotaBytesUsed%2Ccopyable%2CfileExtension%2CsharingUser(kind%2CpermissionId%2Cid)%2Cspaces%2Cversion%2CteamDriveId%2ChasAugmentedPermissions%2CcreatedDate%2CtrashingUser(kind%2CpermissionId%2Cid)%2CtrashedDate%2Cparents(id)%2CshortcutDetails(targetId%2CtargetMimeType%2CtargetLookupStatus)%2Ccapabilities(canCopy%2CcanDownload%2CcanEdit%2CcanAddChildren%2CcanDelete%2CcanRemoveChildren%2CcanShare%2CcanTrash%2CcanRename%2CcanReadTeamDrive%2CcanMoveTeamDriveItem)%2Clabels(starred%2Ctrashed%2Crestricted%2Cviewed))%2CincompleteSearch&appDataFilter=NO_APP_DATA&spaces=drive&pageToken={page_token}&maxResults=50&supportsTeamDrives=true&includeItemsFromAllDrives=true&corpora=default&orderBy=folder%2Ctitle_natural%20asc&retryCount=0&key={key} HTTP/1.1" + _DATA = f'''--{_BOUNDARY} +content-type: application/http +content-transfer-encoding: binary + +GET %s + +--{_BOUNDARY} +''' + + def _call_api(self, folder_id, key, data, **kwargs): + response = self._download_webpage( + 'https://clients6.google.com/batch/drive/v2beta', + folder_id, data=data.encode('utf-8'), + headers={ + 'Content-Type': 'text/plain;charset=UTF-8;', + 'Origin': 'https://drive.google.com', + }, query={ + '$ct': f'multipart/mixed; boundary="{self._BOUNDARY}"', + 'key': key + }, **kwargs) + return self._search_json('', response, 'api response', folder_id, **kwargs) or {} + + def _get_folder_items(self, folder_id, key): + page_token = '' + while page_token is not None: + request = self._REQUEST.format(folder_id=folder_id, page_token=page_token, key=key) + page = self._call_api(folder_id, key, self._DATA % request) + yield from page['items'] + page_token = page.get('nextPageToken') + + def _real_extract(self, url): + folder_id = self._match_id(url) + + webpage = self._download_webpage(url, folder_id) + key = self._search_regex(r'"(\w{39})"', webpage, 'key') + + folder_info = self._call_api(folder_id, key, self._DATA % f'/drive/v2beta/files/{folder_id} HTTP/1.1', fatal=False) + + return self.playlist_from_matches( + self._get_folder_items(folder_id, key), folder_id, folder_info.get('title'), + ie=GoogleDriveIE, getter=lambda item: f'https://drive.google.com/file/d/{item["id"]}') |