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

[iwara.tv] Extract more metadata (#829)

Browse source 
Authored-by: BunnyHelp
This commit is contained in:
BunnyHelp 2021-08-31 15:29:30 -04:00 committed by GitHub
parent b2eeee0ce0
commit 8eb7ba82ca
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 21 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
yt_dlp/extractor/iwara.py
View file

@ -1,5 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse from ..compat import compat_urllib_parse_urlparse
@ -8,6 +9,8 @@
mimetype2ext, mimetype2ext,
remove_end, remove_end,
url_or_none, url_or_none,
unified_strdate,
strip_or_none,
) )
@ -21,6 +24,10 @@ class IwaraIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': '【MMD R-18】ガールフレンド carry_me_off', 'title': '【MMD R-18】ガールフレンド carry_me_off',
'age_limit': 18, 'age_limit': 18,
'thumbnail': 'https://i.iwara.tv/sites/default/files/videos/thumbnails/7951/thumbnail-7951_0001.png',
'uploader': 'Reimu丨Action',
'upload_date': '20150828',
'description': 'md5:1d4905ce48c66c9299c617f08e106e0f',
}, },
}, { }, {
'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO', 'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO',
@ -73,8 +80,17 @@ def _real_extract(self, url):
r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara') r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'<video[^>]+id=[\'"]video-player[\'"][^>]+poster=[\'"]([^\'"]+)', r'poster=[\'"]([^\'"]+)', webpage, 'thumbnail', default=None)
webpage, 'thumbnail', default=None)
uploader = self._html_search_regex(
r'class="username">([^<]+)', webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
r'作成日:([^\s]+)', webpage, 'upload_date', fatal=False))
description = strip_or_none(self._search_regex(
r'<p>(.+?(?=</div))', webpage, 'description', fatal=False,
flags=re.DOTALL))
formats = [] formats = []
for a_format in video_data: for a_format in video_data:
@ -101,4 +117,7 @@ def _real_extract(self, url):
'age_limit': age_limit, 'age_limit': age_limit,
'formats': formats, 'formats': formats,
'thumbnail': self._proto_relative_url(thumbnail, 'https:'), 'thumbnail': self._proto_relative_url(thumbnail, 'https:'),
'uploader': uploader,
'upload_date': upload_date,
'description': description,
} }