From 3ca3f77f9ce9dd504dc6af4ef605c245c31ff860 Mon Sep 17 00:00:00 2001
From: Unknown <blackjack4494@web.de>
Date: Wed, 2 Sep 2020 23:33:41 +0200
Subject: [skip travis] adding automerge support

basically copying content of youtube_dl folder to youtube_dlc and excluding the youtube_dl folder when compiling
---
 youtube_dl/extractor/stanfordoc.py | 91 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 91 insertions(+)
 create mode 100644 youtube_dl/extractor/stanfordoc.py

(limited to 'youtube_dl/extractor/stanfordoc.py')

diff --git a/youtube_dl/extractor/stanfordoc.py b/youtube_dl/extractor/stanfordoc.py
new file mode 100644
index 000000000..ae3dd1380
--- /dev/null
+++ b/youtube_dl/extractor/stanfordoc.py
@@ -0,0 +1,91 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    orderedSet,
+    unescapeHTML,
+)
+
+
+class StanfordOpenClassroomIE(InfoExtractor):
+    IE_NAME = 'stanfordoc'
+    IE_DESC = 'Stanford Open ClassRoom'
+    _VALID_URL = r'https?://openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
+    _TEST = {
+        'url': 'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
+        'md5': '544a9468546059d4e80d76265b0443b8',
+        'info_dict': {
+            'id': 'PracticalUnix_intro-environment',
+            'ext': 'mp4',
+            'title': 'Intro Environment',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        if mobj.group('course') and mobj.group('video'):  # A specific video
+            course = mobj.group('course')
+            video = mobj.group('video')
+            info = {
+                'id': course + '_' + video,
+                'uploader': None,
+                'upload_date': None,
+            }
+
+            baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
+            xmlUrl = baseUrl + video + '.xml'
+            mdoc = self._download_xml(xmlUrl, info['id'])
+            try:
+                info['title'] = mdoc.findall('./title')[0].text
+                info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
+            except IndexError:
+                raise ExtractorError('Invalid metadata XML file')
+            return info
+        elif mobj.group('course'):  # A course page
+            course = mobj.group('course')
+            info = {
+                'id': course,
+                '_type': 'playlist',
+                'uploader': None,
+                'upload_date': None,
+            }
+
+            coursepage = self._download_webpage(
+                url, info['id'],
+                note='Downloading course info page',
+                errnote='Unable to download course info page')
+
+            info['title'] = self._html_search_regex(
+                r'<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
+
+            info['description'] = self._html_search_regex(
+                r'(?s)<description>([^<]+)</description>',
+                coursepage, 'description', fatal=False)
+
+            links = orderedSet(re.findall(r'<a href="(VideoPage\.php\?[^"]+)">', coursepage))
+            info['entries'] = [self.url_result(
+                'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
+            ) for l in links]
+            return info
+        else:  # Root page
+            info = {
+                'id': 'Stanford OpenClassroom',
+                '_type': 'playlist',
+                'uploader': None,
+                'upload_date': None,
+            }
+            info['title'] = info['id']
+
+            rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
+            rootpage = self._download_webpage(rootURL, info['id'],
+                                              errnote='Unable to download course info page')
+
+            links = orderedSet(re.findall(r'<a href="(CoursePage\.php\?[^"]+)">', rootpage))
+            info['entries'] = [self.url_result(
+                'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
+            ) for l in links]
+            return info
-- 
cgit v1.2.3