From 33afd662d96f82f7a5af4ac89513666f2a078a84 Mon Sep 17 00:00:00 2001 From: geauxlo <66712139+geauxlo@users.noreply.github.com> Date: Wed, 10 Jun 2020 06:42:44 +0000 Subject: [PATCH] UNDO --- youtube_dl/extractor/screencast.py | 64 ++++++------------------------ 1 file changed, 13 insertions(+), 51 deletions(-) diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py index d23a53706..69a0d01f3 100644 --- a/youtube_dl/extractor/screencast.py +++ b/youtube_dl/extractor/screencast.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..compat import ( compat_parse_qs, @@ -14,9 +12,7 @@ class ScreencastIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?screencast\.com/(?:t|users/[^/]+/folders/[^/]+/media)/(?P[a-zA-Z0-9\-]+)' - _API_URL = 'https://www.screencast.com/api/external/oembed?url=%s&format=json' - + _VALID_URL = r'https?://(?:www\.)?screencast\.com/t/(?P[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'http://www.screencast.com/t/3ZEjQXlT', 'md5': '917df1c13798a3e96211dd1561fded83', @@ -60,46 +56,17 @@ class ScreencastIE(InfoExtractor): }, { 'url': 'http://screencast.com/t/aAB3iowa', 'only_matching': True, - }, { - 'url': 'https://www.screencast.com/users/cindyhailes/folders/Jing/media/c9be177c-5808-4c4f-af56-eadceb3a7c82', - 'md5': '589d37a28d2add53c8bf16b9126d9dc2', - 'info_dict': { - 'id': 'c9be177c-5808-4c4f-af56-eadceb3a7c82', - 'ext': 'swf', - 'title': '2020-05-31_1737', - 'description': 'Shared from Screencast.com', - 'thumbnail': r're:^https?://.*\.(?:gif|jpg)$', - } }] def _real_extract(self, url): video_id = self._match_id(url) - - # The JSON given by the API has a thumbnail URL, - # but it's inferior to the webpage's thumbnail. - # It also has no video description, so we - # definitely still need to get the webpage. - - info = self._download_json( - self._API_URL % url, video_id, - 'Downloading video info JSON') - - video_url = info.get('url') - if video_url != None: - video_url_raw = compat_urllib_request.quote(video_url) - video_url = re.sub(r'^(?Phttps|http)%3A', - lambda match: '%s:' % match.group('proto'), - video_url_raw) - - title = info.get('title') webpage = self._download_webpage(url, video_id) - if video_url == None: - video_url = self._html_search_regex( - r'http|https)%3A', - lambda match: '%s:' % match.group('proto'), - video_url_raw) + video_url = video_url_raw.replace('http%3A', 'http:') - if video_url == None: + if video_url is None: video_meta = self._html_search_meta( 'og:video', webpage, default=None) if video_meta: @@ -125,31 +90,28 @@ def _real_extract(self, url): r'src=(.*?)(?:$|&)', video_meta, 'meta tag video URL', default=None) - if video_url == None: + if video_url is None: video_url = self._html_search_regex( r'MediaContentUrl["\']\s*:(["\'])(?P(?:(?!\1).)+)\1', webpage, 'video url', default=None, group='url') - if video_url == None: + if video_url is None: video_url = self._html_search_meta( 'og:video', webpage, default=None) - if video_url == None: + if video_url is None: raise ExtractorError('Cannot find video') - if title == None: - title = self._og_search_title(webpage, default=None) - - if title == None: + title = self._og_search_title(webpage, default=None) + if title is None: title = self._html_search_regex( [r'Title: ([^<]+)', r'class="tabSeperator">>(.+?)<', r'([^<]+)'], webpage, 'title') - thumbnail = self._og_search_thumbnail(webpage) description = self._og_search_description(webpage, default=None) - if description == None: + if description is None: description = self._html_search_meta('description', webpage) return {