itdominator/SolarFM
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Upgrade yt_dlp and download script

Browse Source
This commit is contained in:
itdominator
2025-05-02 16:11:08 -05:00
parent 3a2e8eeb08
commit d68d9ce4f9
1194 changed files with 60099 additions and 44436 deletions
Download Patch File Download Diff File Expand all files Collapse all files

153
plugins/youtube_download/yt_dlp/extractor/sohu.py
View File

@@ -1,14 +1,17 @@
import base64
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
)
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
traverse_obj,
try_get,
unified_timestamp,
url_or_none,
urljoin,
)
@@ -31,20 +34,33 @@ class SohuIE(InfoExtractor):
'id': '409385080',
'ext': 'mp4',
'title': '《2015湖南卫视羊年元宵晚会》唐嫣《花好月圆》',
}
},
'skip': 'no longer available',
}, {
'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
'info_dict': {
'id': '78693464',
'ext': 'mp4',
'title': '【爱范品】第31期：MWC见不到的奇葩手机',
}
'uploader': '爱范儿视频',
'duration': 213,
'timestamp': 1425519600,
'upload_date': '20150305',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M10/83/FA/MTAuMTAuODguODA=/6_14cbccdde5eg104SysCutcloud_78693464_7_0b.jpg',
'tags': ['爱范儿', '爱范品', 'MWC', '手机'],
},
}, {
'note': 'Multipart video',
'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml',
'info_dict': {
'id': '78910339',
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
'uploader': '小苍cany',
'duration': 744.0,
'timestamp': 1426269360,
'upload_date': '20150313',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M11/89/57/MTAuMTAuODguODA=/6_14cea022a1dg102SysCutcloud_78910339_8_0b.jpg',
'tags': ['小苍MM', '英雄联盟', '实战秘籍'],
},
'playlist': [{
'info_dict': {
@@ -52,22 +68,22 @@ class SohuIE(InfoExtractor):
'ext': 'mp4',
'duration': 294,
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
},
}, {
'info_dict': {
'id': '78910339_part2',
'ext': 'mp4',
'duration': 300,
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
},
}, {
'info_dict': {
'id': '78910339_part3',
'ext': 'mp4',
'duration': 150,
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}]
},
}],
}, {
'note': 'Video with title containing dash',
'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml',
@@ -75,10 +91,15 @@ class SohuIE(InfoExtractor):
'id': '78932792',
'ext': 'mp4',
'title': 'youtube-dl testing video',
'duration': 360,
'timestamp': 1426348620,
'upload_date': '20150314',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M02/8A/00/MTAuMTAuODguNzk=/6_14cee1be192g102SysCutcloud_78932792_7_7b.jpg',
'tags': [],
},
'params': {
'skip_download': True
}
'skip_download': True,
},
}]
def _real_extract(self, url):
@@ -91,7 +112,7 @@ class SohuIE(InfoExtractor):
return self._download_json(
base_data_url + vid_id, video_id,
'Downloading JSON data for %s' % vid_id,
f'Downloading JSON data for {vid_id}',
headers=self.geo_verification_headers())
mobj = self._match_valid_url(url)
@@ -100,7 +121,7 @@ class SohuIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
title = re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage))
title = re.sub(r'( - 高清正版在线观看)? - 搜狐视频$', '', self._og_search_title(webpage))
vid = self._html_search_regex(
r'var vid ?= ?["\'](\d+)["\']',
@@ -109,18 +130,18 @@ class SohuIE(InfoExtractor):
if vid_data['play'] != 1:
if vid_data.get('status') == 12:
raise ExtractorError(
'%s said: There\'s something wrong in the video.' % self.IE_NAME,
f'{self.IE_NAME} said: There\'s something wrong in the video.',
expected=True)
else:
self.raise_geo_restricted(
'%s said: The video is only licensed to users in Mainland China.' % self.IE_NAME)
f'{self.IE_NAME} said: The video is only licensed to users in Mainland China.')
formats_json = {}
for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'):
vid_id = vid_data['data'].get('%sVid' % format_id)
vid_id = vid_data['data'].get(f'{format_id}Vid')
if not vid_id:
continue
vid_id = compat_str(vid_id)
vid_id = str(vid_id)
formats_json[format_id] = vid_data if vid == vid_id else _fetch_data(vid_id, mytv)
part_count = vid_data['data']['totalBlocks']
@@ -132,36 +153,37 @@ class SohuIE(InfoExtractor):
allot = format_data['allot']
data = format_data['data']
clips_url = data['clipsURL']
clip_url = traverse_obj(data, (('clipsURL', 'mp4PlayUrl'), i, {url_or_none}), get_all=False)
if not clip_url:
raise ExtractorError(f'Unable to extract url for clip {i}')
su = data['su']
video_url = 'newflv.sohu.ccgslb.net'
cdnId = None
cdn_id = None
retries = 0
while 'newflv.sohu.ccgslb.net' in video_url:
params = {
'prot': 9,
'file': clips_url[i],
'file': clip_url,
'new': su[i],
'prod': 'flash',
'prod': 'h5n',
'rb': 1,
}
if cdnId is not None:
params['idc'] = cdnId
if cdn_id is not None:
params['idc'] = cdn_id
download_note = 'Downloading %s video URL part %d of %d' % (
format_id, i + 1, part_count)
download_note = f'Downloading {format_id} video URL part {i + 1} of {part_count}'
if retries > 0:
download_note += ' (retry #%d)' % retries
download_note += f' (retry #{retries})'
part_info = self._parse_json(self._download_webpage(
'http://%s/?%s' % (allot, compat_urllib_parse_urlencode(params)),
f'http://{allot}/?{urllib.parse.urlencode(params)}',
video_id, download_note), video_id)
video_url = part_info['url']
cdnId = part_info.get('nid')
cdn_id = part_info.get('nid')
retries += 1
if retries > 5:
@@ -178,7 +200,7 @@ class SohuIE(InfoExtractor):
})
playlist.append({
'id': '%s_part%d' % (video_id, i + 1),
'id': f'{video_id}_part{i + 1}',
'title': title,
'duration': vid_data['data']['clipsDuration'][i],
'formats': formats,
@@ -193,6 +215,75 @@ class SohuIE(InfoExtractor):
'entries': playlist,
'id': video_id,
'title': title,
'duration': traverse_obj(vid_data, ('data', 'totalDuration', {float_or_none})),
}
return info
if mytv:
publish_time = unified_timestamp(self._search_regex(
r'publishTime:\s*["\'](\d+-\d+-\d+ \d+:\d+)["\']', webpage, 'publish time', fatal=False))
else:
publish_time = traverse_obj(vid_data, ('tv_application_time', {unified_timestamp}))
return {
'timestamp': publish_time - 8 * 3600 if publish_time else None,
**traverse_obj(vid_data, {
'alt_title': ('data', 'subName', {str}),
'uploader': ('wm_data', 'wm_username', {str}),
'thumbnail': ('data', 'coverImg', {url_or_none}),
'tags': ('data', 'tag', {str.split}),
}),
**info,
}
class SohuVIE(InfoExtractor):
_VALID_URL = r'https?://tv\.sohu\.com/v/(?P<id>[\w=-]+)\.html(?:$|[#?])'
_TESTS = [{
'note': 'Multipart video',
'url': 'https://tv.sohu.com/v/MjAyMzA2MTQvbjYwMTMxNTE5Mi5zaHRtbA==.html',
'info_dict': {
'id': '601315192',
'title': '《淬火丹心》第1集',
'alt_title': '“点天灯”发生事故',
'duration': 2701.692,
'timestamp': 1686758040,
'upload_date': '20230614',
'thumbnail': 'http://photocdn.tv.sohu.com/img/20230614/vrsa_hor_1686738763256_454010551.jpg',
},
'playlist_mincount': 9,
'skip': 'Only available in China',
}, {
'url': 'https://tv.sohu.com/v/dXMvMjMyNzk5ODg5Lzc4NjkzNDY0LnNodG1s.html',
'info_dict': {
'id': '78693464',
'ext': 'mp4',
'title': '【爱范品】第31期：MWC见不到的奇葩手机',
'uploader': '爱范儿视频',
'duration': 213,
'timestamp': 1425519600,
'upload_date': '20150305',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M10/83/FA/MTAuMTAuODguODA=/6_14cbccdde5eg104SysCutcloud_78693464_7_0b.jpg',
'tags': ['爱范儿', '爱范品', 'MWC', '手机'],
},
}, {
'note': 'Multipart video',
'url': 'https://tv.sohu.com/v/dXMvMjQyNTYyMTYzLzc4OTEwMzM5LnNodG1s.html?src=pl',
'info_dict': {
'id': '78910339',
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
'uploader': '小苍cany',
'duration': 744.0,
'timestamp': 1426269360,
'upload_date': '20150313',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M11/89/57/MTAuMTAuODguODA=/6_14cea022a1dg102SysCutcloud_78910339_8_0b.jpg',
'tags': ['小苍MM', '英雄联盟', '实战秘籍'],
},
'playlist_mincount': 3,
}]
def _real_extract(self, url):
encoded_id = self._match_id(url)
path = base64.urlsafe_b64decode(encoded_id).decode()
subdomain = 'tv' if re.match(r'\d+/n\d+\.shtml', path) else 'my.tv'
return self.url_result(urljoin(f'http://{subdomain}.sohu.com/', path), SohuIE)