various
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

fix: New Piapro design

This commit is contained in:
Finn Gärtner 2024-02-27 21:05:15 +01:00
parent e28e135d6f
commit df81810879
1 changed files with 9 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
yt_dlp/extractor/piapro.py
View File

@ -88,25 +88,19 @@ class PiaproIE(InfoExtractor):
if category_id not in ('1', '2', '21', '22', '23', '24', '25'):
raise ExtractorError('The URL does not contain audio.', expected=True)
str_duration, str_filesize = self._search_regex(
r'サイズ：</span>(.+?)/\(([0-9,]+?[KMG]?B)）', webpage, 'duration and size',
group=(1, 2), default=(None, None))
str_viewcount = self._search_regex(r'閲覧数：</span>([0-9,]+)\s+', webpage, 'view count', fatal=False)
str_duration = self._search_regex(r'長さ：\s*(.+?)</p>', webpage, 'duration')
str_filesize = self._search_regex(r'サイズ：\s*([0-9.]+?[KMG]?B)', webpage, 'size')
str_viewcount = self._search_regex(r'閲覧数：\s*([0-9,]+)\s*</p>', webpage, 'view count', fatal=False)
uploader_id, uploader = self._search_regex(
r'<a\s+class="cd_user-name"\s+href="/(.*)">([^<]+)さん<', webpage, 'uploader',
group=(1, 2), default=(None, None))
content_id = self._search_regex(r'contentId\:\'(.+)\'', webpage, 'content ID')
create_date = self._search_regex(r'createDate\:\'(.+)\'', webpage, 'timestamp')
uploader_id = self._search_regex(r'<div\s+class="contents_creator">\s*<a\s+href="/(.*)"', webpage, 'uploader_id')
uploader = self._search_regex(r'class="contents_creator_txt">(.*)</p', webpage, 'uploader')
player_webpage = self._download_webpage(
f'https://piapro.jp/html5_player_popup/?id={content_id}&cdate={create_date}',
video_id, note='Downloading player webpage')
create_date = self._search_regex(r'投稿日：\s*(.+)</p>', webpage, 'timestamp')
return {
'id': video_id,
'title': self._html_search_regex(r'<h1\s+class="cd_works-title">(.+?)</h1>', webpage, 'title', fatal=False),
'description': self._html_search_regex(r'(?s)<p\s+class="cd_dtl_cap">(.+?)</p>\s*<div', webpage, 'description', fatal=False),
'title': self._html_search_regex(r'<h1\s+class="contents_title">(.+?)</h1>', webpage, 'title', fatal=False),
'description': self._html_search_regex(r'(?s)<div\s+class="contents_description">(.+?)</div>\s*<div', webpage, 'description', fatal=False),
'uploader': uploader,
'uploader_id': uploader_id,
'timestamp': unified_timestamp(create_date, False),
@ -115,7 +109,7 @@ class PiaproIE(InfoExtractor):
'thumbnail': self._html_search_meta('twitter:image', webpage),
'filesize_approx': parse_filesize(str_filesize.replace(',', '')),
'url': self._search_regex(r'mp3:\s*\'(.*?)\'\}', player_webpage, 'url'),
'url': self._search_regex(r'\"url\":\s*\"(.*?)\"', webpage, 'url'),
'ext': 'mp3',
'vcodec': 'none',
}