github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[Nexx] Extract more metadata (#2273)

Browse source 
Authored by: MinePlayersPE
This commit is contained in:
MinePlayersPE 2022-01-10 22:32:15 +07:00 committed by GitHub
parent b31874334d
commit 0931ba94ab
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 55 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

81
yt_dlp/extractor/nexx.py
View file

@ -12,6 +12,7 @@
ExtractorError, ExtractorError,
int_or_none, int_or_none,
parse_duration, parse_duration,
srt_subtitles_timecode,
traverse_obj, traverse_obj,
try_get, try_get,
urlencode_postdata, urlencode_postdata,
@ -21,7 +22,7 @@
class NexxIE(InfoExtractor): class NexxIE(InfoExtractor):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
(?: (?:
https?://api\.nexx(?:\.cloud|cdn\.com)/v3/(?P<domain_id>\d+)/videos/byid/| https?://api\.nexx(?:\.cloud|cdn\.com)/v3(?:\.\d)?/(?P<domain_id>\d+)/videos/byid/|
nexx:(?:(?P<domain_id_s>\d+):)?| nexx:(?:(?P<domain_id_s>\d+):)?|
https?://arc\.nexx\.cloud/api/video/ https?://arc\.nexx\.cloud/api/video/
) )
@ -43,35 +44,37 @@ class NexxIE(InfoExtractor):
'timestamp': 1384264416, 'timestamp': 1384264416,
'upload_date': '20131112', 'upload_date': '20131112',
}, },
'skip': 'Spiegel nexx CDNs are now disabled'
}, { }, {
# episode # episode with captions
'url': 'https://api.nexx.cloud/v3/741/videos/byid/247858', 'url': 'https://api.nexx.cloud/v3.1/741/videos/byid/1701834',
'info_dict': { 'info_dict': {
'id': '247858', 'id': '1701834',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Return of the Golden Child (OV)', 'title': 'Mein Leben mit \'nem TikTok E-Boy 😤',
'description': 'md5:5d969537509a92b733de21bae249dc63', 'alt_title': 'Mein Leben mit \'nem TikTok E-Boy 😤',
'release_year': 2017, 'description': 'md5:f84f395a881fd143f952c892deab528d',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1397, 'duration': 770,
'timestamp': 1495033267, 'timestamp': 1595600027,
'upload_date': '20170517', 'upload_date': '20200724',
'episode_number': 2, 'episode_number': 2,
'season_number': 2, 'season_number': 2,
'episode': 'Episode 2',
'season': 'Season 2',
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
'skip': 'HTTP Error 404: Not Found',
}, { }, {
# does not work via arc
'url': 'nexx:741:1269984', 'url': 'nexx:741:1269984',
'md5': 'c714b5b238b2958dc8d5642addba6886', 'md5': 'd5f14e14b592501e51addd5abef95a7f',
'info_dict': { 'info_dict': {
'id': '1269984', 'id': '1269984',
'ext': 'mp4', 'ext': 'mp4',
'title': '1 TAG ohne KLO... wortwörtlich! 😑', 'title': '1 TAG ohne KLO... wortwörtlich! ?',
'alt_title': '1 TAG ohne KLO... wortwörtlich! 😑', 'alt_title': '1 TAG ohne KLO... wortwörtlich! ?',
'description': 'md5:2016393a31991a900946432ccdd09a6f',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'duration': 607, 'duration': 607,
'timestamp': 1518614955, 'timestamp': 1518614955,
@ -92,6 +95,7 @@ class NexxIE(InfoExtractor):
'timestamp': 1527874460, 'timestamp': 1527874460,
'upload_date': '20180601', 'upload_date': '20180601',
}, },
'skip': 'Spiegel nexx CDNs are now disabled'
}, { }, {
'url': 'https://api.nexxcdn.com/v3/748/videos/byid/128907', 'url': 'https://api.nexxcdn.com/v3/748/videos/byid/128907',
'only_matching': True, 'only_matching': True,
@ -139,6 +143,8 @@ def _extract_url(webpage):
return NexxIE._extract_urls(webpage)[0] return NexxIE._extract_urls(webpage)[0]
def _handle_error(self, response): def _handle_error(self, response):
if traverse_obj(response, ('metadata', 'notice'), expected_type=str):
self.report_warning('%s said: %s' % (self.IE_NAME, response['metadata']['notice']))
status = int_or_none(try_get( status = int_or_none(try_get(
response, lambda x: x['metadata']['status']) or 200) response, lambda x: x['metadata']['status']) or 200)
if 200 <= status < 300: if 200 <= status < 300:
@ -405,10 +411,11 @@ def find_video(result):
# md5( operation + domain_id + domain_secret ) # md5( operation + domain_id + domain_secret )
# where domain_secret is a static value that will be given by nexx.tv # where domain_secret is a static value that will be given by nexx.tv
# as per [1]. Here is how this "secret" is generated (reversed # as per [1]. Here is how this "secret" is generated (reversed
# from _play.api.init function, search for clienttoken). So it's # from _play._factory.data.getDomainData function, search for
# actually not static and not that much of a secret. # domaintoken or enableAPIAccess). So it's actually not static
# and not that much of a secret.
# 1. https://nexxtvstorage.blob.core.windows.net/files/201610/27.pdf # 1. https://nexxtvstorage.blob.core.windows.net/files/201610/27.pdf
secret = result['device']['clienttoken'][int(device_id[0]):] secret = result['device']['domaintoken'][int(device_id[0]):]
secret = secret[0:len(secret) - int(device_id[-1])] secret = secret[0:len(secret) - int(device_id[-1])]
op = 'byid' op = 'byid'
@ -420,15 +427,18 @@ def find_video(result):
result = self._call_api( result = self._call_api(
domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={ domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={
'additionalfields': 'language,channel,actors,studio,licenseby,slug,subtitle,teaser,description', 'additionalfields': 'language,channel,format,licenseby,slug,fileversion,episode,season',
'addInteractionOptions': '1', 'addInteractionOptions': '1',
'addStatusDetails': '1', 'addStatusDetails': '1',
'addStreamDetails': '1', 'addStreamDetails': '1',
'addCaptions': '1', 'addFeatures': '1',
# Caption format selection doesn't seem to be enforced?
'addCaptions': 'vtt',
'addScenes': '1', 'addScenes': '1',
'addChapters': '1',
'addHotSpots': '1', 'addHotSpots': '1',
'addConnectedMedia': 'persons',
'addBumpers': '1', 'addBumpers': '1',
'captionFormat': 'data',
}, headers={ }, headers={
'X-Request-CID': cid, 'X-Request-CID': cid,
'X-Request-Token': request_token, 'X-Request-Token': request_token,
@ -451,22 +461,41 @@ def find_video(result):
self._sort_formats(formats) self._sort_formats(formats)
subtitles = {}
for sub in video.get('captiondata') or []:
if sub.get('data'):
subtitles.setdefault(sub.get('language', 'en'), []).append({
'ext': 'srt',
'data': '\n\n'.join(
f'{i + 1}\n{srt_subtitles_timecode(line["fromms"] / 1000)} --> {srt_subtitles_timecode(line["toms"] / 1000)}\n{line["caption"]}'
for i, line in enumerate(sub['data'])),
'name': sub.get('language_long') or sub.get('title')
})
elif sub.get('url'):
subtitles.setdefault(sub.get('language', 'en'), []).append({
'url': sub['url'],
'ext': sub.get('format'),
'name': sub.get('language_long') or sub.get('title')
})
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'alt_title': general.get('subtitle'), 'alt_title': general.get('subtitle'),
'description': general.get('description'), 'description': general.get('description'),
'release_year': int_or_none(general.get('year')), 'release_year': int_or_none(general.get('year')),
'creator': general.get('studio') or general.get('studio_adref'), 'creator': general.get('studio') or general.get('studio_adref') or None,
'thumbnail': try_get( 'thumbnail': try_get(
video, lambda x: x['imagedata']['thumb'], compat_str), video, lambda x: x['imagedata']['thumb'], compat_str),
'duration': parse_duration(general.get('runtime')), 'duration': parse_duration(general.get('runtime')),
'timestamp': int_or_none(general.get('uploaded')), 'timestamp': int_or_none(general.get('uploaded')),
'episode_number': int_or_none(try_get( 'episode_number': traverse_obj(
video, lambda x: x['episodedata']['episode'])), video, (('episodedata', 'general'), 'episode'), expected_type=int, get_all=False),
'season_number': int_or_none(try_get( 'season_number': traverse_obj(
video, lambda x: x['episodedata']['season'])), video, (('episodedata', 'general'), 'season'), expected_type=int, get_all=False),
'cast': traverse_obj(video, ('connectedmedia', ..., 'title'), expected_type=str),
'formats': formats, 'formats': formats,
'subtitles': subtitles,
} }