[googledrive] fix format extraction(closes #26979)

This commit is contained in:
Remita Amine 2020-11-19 20:01:24 +01:00
parent 2cf8003638
commit 25a35cb38a

View File

@ -3,11 +3,13 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_parse_qs
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
lowercase_escape, lowercase_escape,
try_get,
update_url_query, update_url_query,
) )
@ -38,21 +40,10 @@ class GoogleDriveIE(InfoExtractor):
# video can't be watched anonymously due to view count limit reached, # video can't be watched anonymously due to view count limit reached,
# but can be downloaded (see https://github.com/ytdl-org/youtube-dl/issues/14046) # but can be downloaded (see https://github.com/ytdl-org/youtube-dl/issues/14046)
'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view', 'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
'md5': 'bfbd670d03a470bb1e6d4a257adec12e', 'only_matching': True,
'info_dict': {
'id': '0B-vUyvmDLdWDcEt4WjBqcmI2XzQ',
'ext': 'mp4',
'title': 'Annabelle Creation (2017)- Z.V1 [TH].MP4',
}
}, { }, {
# video id is longer than 28 characters # video id is longer than 28 characters
'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit', 'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
'info_dict': {
'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ',
'ext': 'mp4',
'title': 'Andreea Banica feat Smiley - Hooky Song (Official Video).mp4',
'duration': 189,
},
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://drive.google.com/open?id=0B2fjwgkl1A_CX083Tkowdmt6d28', 'url': 'https://drive.google.com/open?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
@ -171,23 +162,21 @@ class GoogleDriveIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage( video_info = compat_parse_qs(self._download_webpage(
'http://docs.google.com/file/d/%s' % video_id, video_id) 'https://drive.google.com/get_video_info',
video_id, query={'docid': video_id}))
title = self._search_regex( def get_value(key):
r'"title"\s*,\s*"([^"]+)', webpage, 'title', return try_get(video_info, lambda x: x[key][0])
default=None) or self._og_search_title(webpage)
duration = int_or_none(self._search_regex( reason = get_value('reason')
r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', title = get_value('title')
default=None)) if not title and reason:
raise ExtractorError(reason, expected=True)
formats = [] formats = []
fmt_stream_map = self._search_regex( fmt_stream_map = (get_value('fmt_stream_map') or '').split(',')
r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, fmt_list = (get_value('fmt_list') or '').split(',')
'fmt stream map', default='').split(',')
fmt_list = self._search_regex(
r'"fmt_list"\s*,\s*"([^"]+)', webpage,
'fmt_list', default='').split(',')
if fmt_stream_map and fmt_list: if fmt_stream_map and fmt_list:
resolutions = {} resolutions = {}
for fmt in fmt_list: for fmt in fmt_list:
@ -257,19 +246,14 @@ class GoogleDriveIE(InfoExtractor):
if urlh and urlh.headers.get('Content-Disposition'): if urlh and urlh.headers.get('Content-Disposition'):
add_source_format(urlh) add_source_format(urlh)
if not formats: if not formats and reason:
reason = self._search_regex( raise ExtractorError(reason, expected=True)
r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
if reason:
raise ExtractorError(reason, expected=True)
self._sort_formats(formats) self._sort_formats(formats)
hl = self._search_regex( hl = get_value('hl')
r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None)
subtitles_id = None subtitles_id = None
ttsurl = self._search_regex( ttsurl = get_value('ttsurl')
r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None)
if ttsurl: if ttsurl:
# the video Id for subtitles will be the last value in the ttsurl # the video Id for subtitles will be the last value in the ttsurl
# query string # query string
@ -279,8 +263,8 @@ class GoogleDriveIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'thumbnail': self._og_search_thumbnail(webpage, default=None), 'thumbnail': 'https://drive.google.com/thumbnail?id=' + video_id,
'duration': duration, 'duration': int_or_none(get_value('length_seconds')),
'formats': formats, 'formats': formats,
'subtitles': self.extract_subtitles(video_id, subtitles_id, hl), 'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
'automatic_captions': self.extract_automatic_captions( 'automatic_captions': self.extract_automatic_captions(