From 762fe4e670a06dc42425445e97b85dba53ec8de8 Mon Sep 17 00:00:00 2001
From: geauxlo <66712139+geauxlo@users.noreply.github.com>
Date: Wed, 10 Jun 2020 06:57:55 +0000
Subject: [PATCH] Prefer API to scraping HTML when possible

---
 youtube_dl/extractor/screencast.py | 151 +++++++++++++++++++++++++++++
 1 file changed, 151 insertions(+)
 create mode 100644 youtube_dl/extractor/screencast.py

diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py
new file mode 100644
index 000000000..859c9dc0d
--- /dev/null
+++ b/youtube_dl/extractor/screencast.py
@@ -0,0 +1,151 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_request,
+)
+from ..utils import (
+    ExtractorError,
+)
+
+
+class ScreencastIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
+    _API_URL = 'https://www.screencast.com/api/external/oembed?url=%s&format=json'
+
+    _TESTS = [{
+        'url': 'http://www.screencast.com/t/3ZEjQXlT',
+        'md5': '917df1c13798a3e96211dd1561fded83',
+        'info_dict': {
+            'id': '3ZEjQXlT',
+            'ext': 'm4v',
+            'title': 'Color Measurement with Ocean Optics Spectrometers',
+            'description': 'md5:240369cde69d8bed61349a199c5fb153',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
+        }
+    }, {
+        'url': 'http://www.screencast.com/t/V2uXehPJa1ZI',
+        'md5': 'e8e4b375a7660a9e7e35c33973410d34',
+        'info_dict': {
+            'id': 'V2uXehPJa1ZI',
+            'ext': 'mov',
+            'title': 'The Amadeus Spectrometer',
+            'description': 're:^In this video, our friends at.*To learn more about Amadeus, visit',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
+        }
+    }, {
+        'url': 'http://www.screencast.com/t/aAB3iowa',
+        'md5': 'dedb2734ed00c9755761ccaee88527cd',
+        'info_dict': {
+            'id': 'aAB3iowa',
+            'ext': 'mp4',
+            'title': 'Google Earth Export',
+            'description': 'Provides a demo of a CommunityViz export to Google Earth, one of the 3D viewing options.',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
+        }
+    }, {
+        'url': 'http://www.screencast.com/t/X3ddTrYh',
+        'md5': '669ee55ff9c51988b4ebc0877cc8b159',
+        'info_dict': {
+            'id': 'X3ddTrYh',
+            'ext': 'wmv',
+            'title': 'Toolkit 6 User Group Webinar (2014-03-04) - Default Judgment and First Impression',
+            'description': 'md5:7b9f393bc92af02326a5c5889639eab0',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
+        }
+    }, {
+        'url': 'http://screencast.com/t/aAB3iowa',
+        'only_matching': True,
+    }]
+
+    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'^(?P<proto>https|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'<embed name="Video".*?src="([^"]+)"', webpage,
+                'QuickTime embed', default=None)
+
+        if video_url == None:
+            flash_vars_s = self._html_search_regex(
+                r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars',
+                default=None)
+            if not flash_vars_s:
+                flash_vars_s = self._html_search_regex(
+                    r'<param name="initParams" value="([^"]+)"', webpage, 'flash vars',
+                    default=None)
+                if flash_vars_s:
+                    flash_vars_s = flash_vars_s.replace(',', '&')
+            if flash_vars_s:
+                flash_vars = compat_parse_qs(flash_vars_s)
+                video_url_raw = compat_urllib_request.quote(
+                    flash_vars['content'][0])
+                video_url = re.sub(r'^(?P<proto>http|https)%3A',
+                                   lambda match: '%s:' % match.group('proto'),
+                                   video_url_raw)
+
+        if video_url == None:
+            video_meta = self._html_search_meta(
+                'og:video', webpage, default=None)
+            if video_meta:
+                video_url = self._search_regex(
+                    r'src=(.*?)(?:$|&)', video_meta,
+                    'meta tag video URL', default=None)
+
+        if video_url == None:
+            video_url = self._html_search_regex(
+                r'MediaContentUrl["\']\s*:(["\'])(?P<url>(?:(?!\1).)+)\1',
+                webpage, 'video url', default=None, group='url')
+
+        if video_url == None:
+            video_url = self._html_search_meta(
+                'og:video', webpage, default=None)
+
+        if video_url == None:
+            raise ExtractorError('Cannot find video')
+
+        if title == None:
+            title = self._og_search_title(webpage, default=None)
+        
+        if title == None:
+            title = self._html_search_regex(
+                [r'<b>Title:</b> ([^<]+)</div>',
+                 r'class="tabSeperator">></span><span class="tabText">(.+?)<',
+                 r'<title>([^<]+)</title>'],
+                webpage, 'title')
+
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(webpage, default=None)
+        if description == None:
+            description = self._html_search_meta('description', webpage)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+        }