[googledrive] Add support for source format (closes #14046)

This commit is contained in:
Sergey M․ 2017-08-28 00:39:22 +07:00
parent 3902cdd0e3
commit fea82c1780
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -4,6 +4,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
lowercase_escape, lowercase_escape,
@ -15,17 +16,26 @@ class GoogleDriveIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})' _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})'
_TESTS = [{ _TESTS = [{
'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1', 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
'md5': 'd109872761f7e7ecf353fa108c0dbe1e', 'md5': '5c602afbbf2c1db91831f5d82f678554',
'info_dict': { 'info_dict': {
'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ', 'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Big Buck Bunny.mp4', 'title': 'Big Buck Bunny.mp4',
'duration': 45, 'duration': 45,
} }
}, {
# video can't be watched anonymously due to view count limit reached,
# but can be downloaded (see https://github.com/rg3/youtube-dl/issues/14046)
'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
'md5': 'bfbd670d03a470bb1e6d4a257adec12e',
'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',
'md5': 'c230c67252874fddd8170e3fd1a45886',
'info_dict': { 'info_dict': {
'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ', 'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ',
'ext': 'mp4', 'ext': 'mp4',
@ -147,47 +157,84 @@ class GoogleDriveIE(InfoExtractor):
webpage = self._download_webpage( webpage = self._download_webpage(
'http://docs.google.com/file/d/%s' % video_id, video_id) 'http://docs.google.com/file/d/%s' % video_id, video_id)
reason = self._search_regex( title = self._search_regex(
r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None) r'"title"\s*,\s*"([^"]+)', webpage, 'title',
if reason: default=None) or self._og_search_title(webpage)
raise ExtractorError(reason)
title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
duration = int_or_none(self._search_regex( duration = int_or_none(self._search_regex(
r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds',
default=None)) default=None))
fmt_stream_map = self._search_regex(
r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
'fmt stream map').split(',')
fmt_list = self._search_regex(
r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
resolutions = {}
for fmt in fmt_list:
mobj = re.search(
r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
if mobj:
resolutions[mobj.group('format_id')] = (
int(mobj.group('width')), int(mobj.group('height')))
formats = [] formats = []
for fmt_stream in fmt_stream_map: fmt_stream_map = self._search_regex(
fmt_stream_split = fmt_stream.split('|') r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
if len(fmt_stream_split) < 2: 'fmt stream map', default='').split(',')
continue fmt_list = self._search_regex(
format_id, format_url = fmt_stream_split[:2] r'"fmt_list"\s*,\s*"([^"]+)', webpage,
f = { 'fmt_list', default='').split(',')
'url': lowercase_escape(format_url), if fmt_stream_map and fmt_list:
'format_id': format_id, resolutions = {}
'ext': self._FORMATS_EXT[format_id], for fmt in fmt_list:
} mobj = re.search(
resolution = resolutions.get(format_id) r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
if resolution: if mobj:
f.update({ resolutions[mobj.group('format_id')] = (
'width': resolution[0], int(mobj.group('width')), int(mobj.group('height')))
'height': resolution[1],
for fmt_stream in fmt_stream_map:
fmt_stream_split = fmt_stream.split('|')
if len(fmt_stream_split) < 2:
continue
format_id, format_url = fmt_stream_split[:2]
f = {
'url': lowercase_escape(format_url),
'format_id': format_id,
'ext': self._FORMATS_EXT[format_id],
}
resolution = resolutions.get(format_id)
if resolution:
f.update({
'width': resolution[0],
'height': resolution[1],
})
formats.append(f)
source_url = update_url_query(
'https://drive.google.com/uc', {
'id': video_id,
'export': 'download',
})
urlh = self._request_webpage(
source_url, video_id, note='Requesting source file',
errnote='Unable to request source file', fatal=False)
if urlh:
def add_source_format(src_url):
formats.append({
'url': src_url,
'ext': determine_ext(title, 'mp4').lower(),
'format_id': 'source',
'quality': 1,
}) })
formats.append(f) if urlh.headers.get('Content-Disposition'):
add_source_format(source_url)
else:
confirmation_webpage = self._webpage_read_content(
urlh, url, video_id, note='Downloading confirmation page',
errnote='Unable to confirm download', fatal=False)
if confirmation_webpage:
confirm = self._search_regex(
r'confirm=([^&"\']+)', confirmation_webpage,
'confirmation code', fatal=False)
if confirm:
add_source_format(update_url_query(source_url, {
'confirm': confirm,
}))
if not formats:
reason = self._search_regex(
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 = self._search_regex(