X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/fe979149c83b5a935f7d28baf75848a9137316fd..1f17a37b9b95db09a420a1f52cf18723ce4eb8b5:/youtube_dl/extractor/toypics.py?ds=inline diff --git a/youtube_dl/extractor/toypics.py b/youtube_dl/extractor/toypics.py index 2579ba8..f705a06 100644 --- a/youtube_dl/extractor/toypics.py +++ b/youtube_dl/extractor/toypics.py @@ -1,4 +1,4 @@ -# -*- coding:utf-8 -*- +# coding: utf-8 from __future__ import unicode_literals from .common import InfoExtractor @@ -6,42 +6,48 @@ import re class ToypicsIE(InfoExtractor): - IE_DESC = 'Toypics user profile' - _VALID_URL = r'https?://videos\.toypics\.net/view/(?P[0-9]+)/.*' + 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', + 'title': "Chance-Bulge'd, 2", 'age_limit': 18, 'uploader': 'kidsune', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - page = self._download_webpage(url, video_id) - video_url = self._html_search_regex( - r'src:\s+"(http://static[0-9]+\.toypics\.net/flvideo/[^"]+)"', page, 'video URL') - title = self._html_search_regex( - r'Toypics - ([^<]+)', page, 'title') - username = self._html_search_regex( - r'toypics.net/([^/"]+)" class="user-name">', page, 'username') + 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, - 'url': video_url, + 'formats': formats, 'title': title, - 'uploader': username, + 'uploader': uploader, 'age_limit': 18, } class ToypicsUserIE(InfoExtractor): IE_DESC = 'Toypics user profile' - _VALID_URL = r'https?://videos\.toypics\.net/(?P[^/?]+)(?:$|[?#])' + _VALID_URL = r'https?://videos\.toypics\.net/(?!view)(?P[^/?#&]+)' _TEST = { 'url': 'http://videos.toypics.net/Mikey', 'info_dict': { @@ -51,8 +57,7 @@ class ToypicsUserIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - username = mobj.group('username') + username = self._match_id(url) profile_page = self._download_webpage( url, username, note='Retrieving profile page') @@ -71,7 +76,7 @@ class ToypicsUserIE(InfoExtractor): note='Downloading page %d/%d' % (n, page_count)) urls.extend( re.findall( - r'

\s+', + r']+class=["\']preview[^>]+>\s*]+href="(https?://videos\.toypics\.net/view/[^"]+)"', lpage)) return {