[youtube] Quick extraction tempfix (closes #22367, closes #22163)

This commit is contained in:
Sergey M․ 2019-09-11 22:44:47 +07:00
parent bff90fc518
commit bf1317d257
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 106 additions and 78 deletions

View File

@ -1915,6 +1915,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return int_or_none(self._search_regex( return int_or_none(self._search_regex(
r'\bclen[=/](\d+)', media_url, 'filesize', default=None)) r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) or []
streaming_formats.extend(try_get(player_response, lambda x: x['streamingData']['adaptiveFormats'], list) or [])
if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
self.report_rtmp_download() self.report_rtmp_download()
formats = [{ formats = [{
@ -1923,10 +1926,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': video_info['conn'][0], 'url': video_info['conn'][0],
'player_url': player_url, 'player_url': player_url,
}] }]
elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1): elif not is_live and (streaming_formats or len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1):
encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
if 'rtmpe%3Dyes' in encoded_url_map: if 'rtmpe%3Dyes' in encoded_url_map:
raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True) raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
formats = []
formats_spec = {} formats_spec = {}
fmt_list = video_info.get('fmt_list', [''])[0] fmt_list = video_info.get('fmt_list', [''])[0]
if fmt_list: if fmt_list:
@ -1941,8 +1945,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'height': int_or_none(width_height[1]), 'height': int_or_none(width_height[1]),
} }
q = qualities(['small', 'medium', 'hd720']) q = qualities(['small', 'medium', 'hd720'])
streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list)
if streaming_formats:
for fmt in streaming_formats: for fmt in streaming_formats:
itag = str_or_none(fmt.get('itag')) itag = str_or_none(fmt.get('itag'))
if not itag: if not itag:
@ -1960,18 +1962,35 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
'width': int_or_none(fmt.get('width')), 'width': int_or_none(fmt.get('width')),
} }
formats = []
for url_data_str in encoded_url_map.split(','): for fmt in streaming_formats:
url_data = compat_parse_qs(url_data_str) if fmt.get('drm_families'):
if 'itag' not in url_data or 'url' not in url_data or url_data.get('drm_families'):
continue continue
url = url_or_none(fmt.get('url'))
if not url:
cipher = fmt.get('cipher')
if not cipher:
continue
url_data = compat_parse_qs(cipher)
url = url_or_none(try_get(url_data, lambda x: x['url'][0], compat_str))
if not url:
continue
else:
cipher = None
url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0])) stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
# Unsupported FORMAT_STREAM_TYPE_OTF # Unsupported FORMAT_STREAM_TYPE_OTF
if stream_type == 3: if stream_type == 3:
continue continue
format_id = url_data['itag'][0]
url = url_data['url'][0]
format_id = fmt.get('itag') or url_data['itag'][0]
if not format_id:
continue
format_id = compat_str(format_id)
if cipher:
if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
jsplayer_url_json = self._search_regex( jsplayer_url_json = self._search_regex(
@ -2044,24 +2063,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0]) mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
if width is None:
width = int_or_none(fmt.get('width'))
if height is None:
height = int_or_none(fmt.get('height'))
filesize = int_or_none(url_data.get( filesize = int_or_none(url_data.get(
'clen', [None])[0]) or _extract_filesize(url) 'clen', [None])[0]) or _extract_filesize(url)
quality = url_data.get('quality', [None])[0] quality = url_data.get('quality', [None])[0] or fmt.get('quality')
quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel')
tbr = float_or_none(url_data.get('bitrate', [None])[0], 1000) or float_or_none(fmt.get('bitrate'), 1000)
fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps'))
more_fields = { more_fields = {
'filesize': filesize, 'filesize': filesize,
'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000), 'tbr': tbr,
'width': width, 'width': width,
'height': height, 'height': height,
'fps': int_or_none(url_data.get('fps', [None])[0]), 'fps': fps,
'format_note': url_data.get('quality_label', [None])[0] or quality, 'format_note': quality_label or quality,
'quality': q(quality), 'quality': q(quality),
} }
for key, value in more_fields.items(): for key, value in more_fields.items():
if value: if value:
dct[key] = value dct[key] = value
type_ = url_data.get('type', [None])[0] type_ = url_data.get('type', [None])[0] or fmt.get('mimeType')
if type_: if type_:
type_split = type_.split(';') type_split = type_.split(';')
kind_ext = type_split[0].split('/') kind_ext = type_split[0].split('/')