mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-10-31 06:35:12 +00:00
Code Issues Projects Releases Wiki Activity

Update to ytdl-commit-2dd6c6e

Browse Source 
[YouTube] Avoid crash if uploader_id extraction fails
2dd6c6edd8

Except:
    * 295736c9cba714fb5de7d1c3dd31d86e50091cf8 [jsinterp] Improve parsing
    * 384f632e8a9b61e864a26678d85b2b39933b9bae [ITV] Overhaul ITV extractor
    * 33db85c571304bbd6863e3407ad8d08764c9e53b [feat]: Add support to external downloader aria2p
This commit is contained in:
pukkandan
2023-02-17 16:51:34 +05:30
parent a538772969
commit 45b2ee6f4f
19 changed files with 911 additions and 210 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
yt_dlp/extractor/myvideoge.py
View File

@@ -1,5 +1,16 @@
import re
from .common import InfoExtractor
from ..utils import js_to_json
from ..utils import (
MONTH_NAMES,
clean_html,
get_element_by_class,
get_element_by_id,
int_or_none,
js_to_json,
qualities,
unified_strdate,
)
class MyVideoGeIE(InfoExtractor):
@@ -11,37 +22,50 @@ class MyVideoGeIE(InfoExtractor):
'id': '3941048',
'ext': 'mp4',
'title': 'The best prikol',
'upload_date': '20200611',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'md5:d72addd357b0dd914e704781f7f777d8',
'description': 'md5:5c0371f540f5888d603ebfedd46b6df3'
}
'uploader': 'chixa33',
'description': 'md5:5b067801318e33c2e6eea4ab90b1fdd3',
},
}
_MONTH_NAMES_KA = ['იანვარი', 'თებერვალი', 'მარტი', 'აპრილი', 'მაისი', 'ივნისი', 'ივლისი', 'აგვისტო', 'სექტემბერი', 'ოქტომბერი', 'ნოემბერი', 'დეკემბერი']
_quality = staticmethod(qualities(('SD', 'HD')))
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1[^>]*>([^<]+)</h1>', webpage, 'title')
description = self._og_search_description(webpage)
thumbnail = self._html_search_meta(['og:image'], webpage)
uploader = self._search_regex(r'<a[^>]+class="mv_user_name"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False)
title = (
self._og_search_title(webpage, default=None)
or clean_html(get_element_by_class('my_video_title', webpage))
or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title\b', webpage, 'title'))
jwplayer_sources = self._parse_json(
self._search_regex(
r"(?s)jwplayer\(\"mvplayer\"\).setup\(.*?sources: (.*?])", webpage, 'jwplayer sources'),
video_id, transform_source=js_to_json)
r'''(?s)jwplayer\s*\(\s*['"]mvplayer['"]\s*\)\s*\.\s*setup\s*\(.*?\bsources\s*:\s*(\[.*?])\s*[,});]''', webpage, 'jwplayer sources', fatal=False)
or '',
video_id, transform_source=js_to_json, fatal=False)
def _formats_key(f):
if f['label'] == 'SD':
return -1
elif f['label'] == 'HD':
return 1
else:
return 0
formats = self._parse_jwplayer_formats(jwplayer_sources or [], video_id)
for f in formats or []:
f['quality'] = self._quality(f['format_id'])
jwplayer_sources = sorted(jwplayer_sources, key=_formats_key)
description = (
self._og_search_description(webpage)
or get_element_by_id('long_desc_holder', webpage)
or self._html_search_meta('description', webpage))
formats = self._parse_jwplayer_formats(jwplayer_sources, video_id)
uploader = self._search_regex(r'<a[^>]+class="mv_user_name"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False)
upload_date = get_element_by_class('mv_vid_upl_date', webpage)
# as ka locale may not be present roll a local date conversion
upload_date = (unified_strdate(
# translate any ka month to an en one
re.sub('|'.join(self._MONTH_NAMES_KA),
lambda m: MONTH_NAMES['en'][self._MONTH_NAMES_KA.index(m.group(0))],
upload_date, re.I))
if upload_date else None)
return {
'id': video_id,
@@ -49,5 +73,9 @@ class MyVideoGeIE(InfoExtractor):
'description': description,
'uploader': uploader,
'formats': formats,
'thumbnail': thumbnail
'thumbnail': self._og_search_thumbnail(webpage),
'upload_date': upload_date,
'view_count': int_or_none(get_element_by_class('mv_vid_views', webpage)),
'like_count': int_or_none(get_element_by_id('likes_count', webpage)),
'dislike_count': int_or_none(get_element_by_id('dislikes_count', webpage)),
}