From 2415e66f889f38503b73e8ebc5f43ca342390e5c Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Mon, 15 Apr 2024 18:49:24 +0200 Subject: Adding upstream version 2024.03.10. Signed-off-by: Daniel Baumann --- yt_dlp/extractor/toypics.py | 89 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 yt_dlp/extractor/toypics.py (limited to 'yt_dlp/extractor/toypics.py') diff --git a/yt_dlp/extractor/toypics.py b/yt_dlp/extractor/toypics.py new file mode 100644 index 0000000..aa7ee6c --- /dev/null +++ b/yt_dlp/extractor/toypics.py @@ -0,0 +1,89 @@ +from .common import InfoExtractor +import re + + +class ToypicsIE(InfoExtractor): + _WORKING = False + IE_DESC = 'Toypics video' + _VALID_URL = r'https?://videos\.toypics\.net/view/(?P[0-9]+)' + _TEST = { + 'url': 'http://videos.toypics.net/view/514/chancebulged,-2-1/', + 'md5': '16e806ad6d6f58079d210fe30985e08b', + 'info_dict': { + 'id': '514', + 'ext': 'mp4', + 'title': "Chance-Bulge'd, 2", + 'age_limit': 18, + 'uploader': 'kidsune', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + formats = self._parse_html5_media_entries( + url, webpage, video_id)[0]['formats'] + title = self._html_search_regex([ + r']+class=["\']view-video-title[^>]+>([^<]+)([^<]+) - Toypics', + ], webpage, 'title') + + uploader = self._html_search_regex( + r'More videos from ([^<]+)', webpage, 'uploader', + fatal=False) + + return { + 'id': video_id, + 'formats': formats, + 'title': title, + 'uploader': uploader, + 'age_limit': 18, + } + + +class ToypicsUserIE(InfoExtractor): + _WORKING = False + IE_DESC = 'Toypics user profile' + _VALID_URL = r'https?://videos\.toypics\.net/(?!view)(?P[^/?#&]+)' + _TEST = { + 'url': 'http://videos.toypics.net/Mikey', + 'info_dict': { + 'id': 'Mikey', + }, + 'playlist_mincount': 19, + } + + def _real_extract(self, url): + username = self._match_id(url) + + profile_page = self._download_webpage( + url, username, note='Retrieving profile page') + + video_count = int(self._search_regex( + r'public/">Public Videos \(([0-9]+)\)', profile_page, + 'video count')) + + PAGE_SIZE = 8 + urls = [] + page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE + for n in range(1, page_count + 1): + lpage_url = url + '/public/%d' % n + lpage = self._download_webpage( + lpage_url, username, + note='Downloading page %d/%d' % (n, page_count)) + urls.extend( + re.findall( + r']+class=["\']preview[^>]+>\s*]+href="(https?://videos\.toypics\.net/view/[^"]+)"', + lpage)) + + return { + '_type': 'playlist', + 'id': username, + 'entries': [{ + '_type': 'url', + 'url': eurl, + 'ie_key': 'Toypics', + } for eurl in urls] + } -- cgit v1.2.3