X-Git-Url: https://jfr.im/git/yt-dlp.git/blobdiff_plain/2f985f4bb4938ee13356bda0436fde18f8c0e434..c1708b89c09d7288213110fba859f4c5e0339c31:/youtube_dl/extractor/youtube.py
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index d1bbf0b01..bc5fa0b39 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -264,9 +264,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'},
# Dash mp4 audio
- '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 48, 'preference': -50},
- '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 128, 'preference': -50},
- '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 256, 'preference': -50},
+ '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
+ '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
+ '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
# Dash webm
'167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
@@ -287,7 +287,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
'303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
+ '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
'313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'},
+ '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
# Dash webm audio
'171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
@@ -392,6 +394,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'format': '141',
},
},
+ # JS player signature function name containing $
+ {
+ 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
+ 'info_dict': {
+ 'id': 'nfWlot6h_JM',
+ 'ext': 'm4a',
+ 'title': 'Taylor Swift - Shake It Off',
+ 'description': 'md5:2acfda1b285bdd478ccec22f9918199d',
+ 'uploader': 'TaylorSwiftVEVO',
+ 'uploader_id': 'TaylorSwiftVEVO',
+ 'upload_date': '20140818',
+ },
+ 'params': {
+ 'youtube_include_dash_manifest': True,
+ 'format': '141',
+ },
+ },
# Controversy video
{
'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
@@ -412,7 +431,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'id': 'HtVdAasjOgU',
'ext': 'mp4',
'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
- 'description': 'md5:eca57043abae25130f58f655ad9a7771',
+ 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
'uploader': 'The Witcher',
'uploader_id': 'WitcherGame',
'upload_date': '20140605',
@@ -463,6 +482,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'skip_download': 'requires avconv',
}
},
+ # Non-square pixels
+ {
+ 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
+ 'info_dict': {
+ 'id': '_b-2C3KPAM0',
+ 'ext': 'mp4',
+ 'stretched_ratio': 16 / 9.,
+ 'upload_date': '20110310',
+ 'uploader_id': 'AllenMeow',
+ 'description': 'made by Wacom from Korea | åå¹&å 油添é by TY\'s Allen | æè¬heylisa00cavey1001åå¸ç±æ
æä¾æ¢åç¿»è¯',
+ 'uploader': 'å«è¾å«',
+ 'title': '[A-made] è®æ
å¦åå¹ç å¤ªå¦ æå°±æ¯é樣ç人',
+ },
+ }
]
def __init__(self, *args, **kwargs):
@@ -572,7 +605,7 @@ def _genslice(start, end, step):
def _parse_sig_js(self, jscode):
funcname = self._search_regex(
- r'\.sig\|\|([a-zA-Z0-9]+)\(', jscode,
+ r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode,
'Initial JS player signature function name')
jsi = JSInterpreter(jscode)
@@ -1046,9 +1079,19 @@ def _map_to_format_list(urlmap):
for f in formats:
if f['format_id'] in dash_keys:
f['format_id'] = 'nondash-%s' % f['format_id']
- f['preference'] -= 10000
+ f['preference'] = f.get('preference', 0) - 10000
formats.extend(dash_formats)
+ # Check for malformed aspect ratio
+ stretched_m = re.search(
+ r'[0-9]+):(?P[0-9]+)">',
+ video_webpage)
+ if stretched_m:
+ ratio = float(stretched_m.group('w')) / float(stretched_m.group('h'))
+ for f in formats:
+ if f.get('vcodec') != 'none':
+ f['stretched_ratio'] = ratio
+
self._sort_formats(formats)
return {
@@ -1639,11 +1682,18 @@ class YoutubeTruncatedURLIE(InfoExtractor):
IE_NAME = 'youtube:truncated_url'
IE_DESC = False # Do not list
_VALID_URL = r'''(?x)
- (?:https?://)?[^/]+/watch\?(?:
+ (?:https?://)?
+ (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
+ (?:watch\?(?:
feature=[a-z_]+|
- annotation_id=annotation_[^&]+
- )?$|
- (?:https?://)?(?:www\.)?youtube\.com/attribution_link\?a=[^&]+$
+ annotation_id=annotation_[^&]+|
+ x-yt-cl=[0-9]+|
+ hl=[^&]*|
+ )?
+ |
+ attribution_link\?a=[^&]+
+ )
+ $
'''
_TESTS = [{
@@ -1652,6 +1702,15 @@ class YoutubeTruncatedURLIE(InfoExtractor):
}, {
'url': 'http://www.youtube.com/watch?',
'only_matching': True,
+ }, {
+ 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.youtube.com/watch?feature=foo',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.youtube.com/watch?hl=en-GB',
+ 'only_matching': True,
}]
def _real_extract(self, url):
@@ -1667,7 +1726,7 @@ def _real_extract(self, url):
class YoutubeTruncatedIDIE(InfoExtractor):
IE_NAME = 'youtube:truncated_id'
IE_DESC = False # Do not list
- _VALID_URL = r'https?://(?:www\.)youtube\.com/watch\?v=(?P[0-9A-Za-z_-]{1,10})$'
+ _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P[0-9A-Za-z_-]{1,10})$'
_TESTS = [{
'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',