debian/README.source: Update with instructions relative to GitHub.

[youtubedl] / youtube_dl / extractor / stanfordoc.py

diff --git a/youtube_dl/extractor/stanfordoc.py b/youtube_dl/extractor/stanfordoc.py
index 8d3e32ab9755f7d365a0c346126d450d65ccac51..ae3dd13807d0f9f46939f6dfab066a75eddd1ed1 100644 (file)
--- a/youtube_dl/extractor/stanfordoc.py
+++ b/youtube_dl/extractor/stanfordoc.py
@@ -1,14 +1,9 @@
+from __future__ import unicode_literals
+

 import re
 import re

-import socket
-import xml.etree.ElementTree

 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

-    compat_http_client,
-    compat_str,
-    compat_urllib_error,
-    compat_urllib_request,
-

     ExtractorError,
     orderedSet,
     unescapeHTML,
     ExtractorError,
     orderedSet,
     unescapeHTML,


@@ -16,17 +11,23 @@ from ..utils import (
 
 
 class StanfordOpenClassroomIE(InfoExtractor):
 
 
 class StanfordOpenClassroomIE(InfoExtractor):

-    """Information extractor for Stanford's Open ClassRoom"""
-
-    _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
-    IE_NAME = u'stanfordoc'
+    IE_NAME = 'stanfordoc'
+    IE_DESC = 'Stanford Open ClassRoom'
+    _VALID_URL = r'https?://openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
+    _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)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)

 
 

-        if mobj.group('course') and mobj.group('video'): # A specific video
+        if mobj.group('course') and mobj.group('video'):  # A specific video

             course = mobj.group('course')
             video = mobj.group('video')
             info = {
             course = mobj.group('course')
             video = mobj.group('video')
             info = {


@@ -35,78 +36,56 @@ class StanfordOpenClassroomIE(InfoExtractor):
                 'upload_date': None,
             }
 
                 'upload_date': None,
             }
 

-            self.report_extraction(info['id'])

             baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
             xmlUrl = baseUrl + video + '.xml'
             baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
             xmlUrl = baseUrl + video + '.xml'

-            try:
-                metaXml = compat_urllib_request.urlopen(xmlUrl).read()
-            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
-            mdoc = xml.etree.ElementTree.fromstring(metaXml)
+            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:
             try:
                 info['title'] = mdoc.findall('./title')[0].text
                 info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
             except IndexError:

-                raise ExtractorError(u'Invalid metadata XML file')
-            info['ext'] = info['url'].rpartition('.')[2]
-            return [info]
-        elif mobj.group('course'): # A course page
+                raise ExtractorError('Invalid metadata XML file')
+            return info
+        elif mobj.group('course'):  # A course page

             course = mobj.group('course')
             info = {
                 'id': course,
             course = mobj.group('course')
             info = {
                 'id': course,

-                'type': 'playlist',
+                '_type': 'playlist',

                 'uploader': None,
                 'upload_date': None,
             }
 
                 'uploader': None,
                 'upload_date': None,
             }
 

-            coursepage = self._download_webpage(url, info['id'],
-                                        note='Downloading course info page',
-                                        errnote='Unable to download course info page')
+            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('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
+            info['title'] = self._html_search_regex(
+                r'<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])

 
 

-            info['description'] = self._html_search_regex('<description>([^<]+)</description>',
-                coursepage, u'description', fatal=False)
+            info['description'] = self._html_search_regex(
+                r'(?s)<description>([^<]+)</description>',
+                coursepage, 'description', fatal=False)

 
 

-            links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
-            info['list'] = [
-                {
-                    'type': 'reference',
-                    'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
-                }
-                    for vpage in links]
-            results = []
-            for entry in info['list']:
-                assert entry['type'] == 'reference'
-                results += self.extract(entry['url'])
-            return results
-        else: # Root page
+            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',
             info = {
                 'id': 'Stanford OpenClassroom',

-                'type': 'playlist',
+                '_type': 'playlist',

                 'uploader': None,
                 'upload_date': None,
             }
                 'uploader': None,
                 'upload_date': None,
             }

-
-            self.report_download_webpage(info['id'])
-            rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
-            try:
-                rootpage = compat_urllib_request.urlopen(rootURL).read()
-            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
-

             info['title'] = info['id']
 
             info['title'] = info['id']
 

-            links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
-            info['list'] = [
-                {
-                    'type': 'reference',
-                    'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
-                }
-                    for cpage in links]
-
-            results = []
-            for entry in info['list']:
-                assert entry['type'] == 'reference'
-                results += self.extract(entry['url'])
-            return results
+            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