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

56
plugins/youtube_download/yt_dlp/extractor/piapro.py
View File

@@ -1,7 +1,10 @@
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
clean_html,
get_element_by_class,
parse_duration,
parse_filesize,
str_to_int,
@@ -12,7 +15,7 @@ from ..utils import (
class PiaproIE(InfoExtractor):
_NETRC_MACHINE = 'piapro'
_VALID_URL = r'https?://piapro\.jp/(?:t|content)/(?P<id>\w+)/?'
_VALID_URL = r'https?://piapro\.jp/(?:t|content)/(?P<id>[\w-]+)/?'
_TESTS = [{
'url': 'https://piapro.jp/t/NXYR',
'md5': 'f7c0f760913fb1d44a1c45a4af793909',
@@ -28,7 +31,7 @@ class PiaproIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.(?:png|jpg)$',
'upload_date': '20090901',
'view_count': int,
}
},
}, {
'note': 'There are break lines in description, mandating (?s) flag',
'url': 'https://piapro.jp/t/9cSd',
@@ -45,10 +48,13 @@ class PiaproIE(InfoExtractor):
'view_count': int,
'thumbnail': r're:^https?://.*\.(?:png|jpg)$',
'uploader_id': 'cyankino',
}
},
}, {
'url': 'https://piapro.jp/content/hcw0z3a169wtemz6',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://piapro.jp/t/-SO-',
'only_matching': True,
}]
_login_status = False
@@ -59,7 +65,7 @@ class PiaproIE(InfoExtractor):
'_username': username,
'_password': password,
'_remember_me': 'on',
'login': 'ログイン'
'login': 'ログイン',
}
self._request_webpage('https://piapro.jp/login/', None)
urlh = self._request_webpage(
@@ -69,7 +75,7 @@ class PiaproIE(InfoExtractor):
if urlh is False:
login_ok = False
else:
parts = compat_urlparse.urlparse(urlh.url)
parts = urllib.parse.urlparse(urlh.url)
if parts.path != '/':
login_ok = False
if not login_ok:
@@ -85,34 +91,22 @@ 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)
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')
player_webpage = self._download_webpage(
f'https://piapro.jp/html5_player_popup/?id={content_id}&cdate={create_date}',
video_id, note='Downloading player webpage')
def extract_info(name, description):
return self._search_regex(rf'{name}[：:]\s*([\d\s,:/]+)\s*</p>', webpage, description, default=None)
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),
'uploader': uploader,
'uploader_id': uploader_id,
'timestamp': unified_timestamp(create_date, False),
'duration': parse_duration(str_duration),
'view_count': str_to_int(str_viewcount),
'title': clean_html(get_element_by_class('contents_title', webpage)),
'description': clean_html(get_element_by_class('contents_description', webpage)),
'uploader': clean_html(get_element_by_class('contents_creator_txt', webpage)),
'uploader_id': self._search_regex(
r'<a\s+href="/([^"]+)"', get_element_by_class('contents_creator', webpage), 'uploader id', default=None),
'timestamp': unified_timestamp(extract_info('投稿日', 'timestamp'), False),
'duration': parse_duration(extract_info('長さ', 'duration')),
'view_count': str_to_int(extract_info('閲覧数', 'view count')),
'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'),
'filesize_approx': parse_filesize((extract_info('サイズ', 'size') or '').replace(',', '')),
'url': self._search_regex(r'\"url\":\s*\"(.*?)\"', webpage, 'url'),
'ext': 'mp3',
'vcodec': 'none',
}