Merge remote-tracking branch 'duncankl/airmozilla'

[youtube-dl] / youtube_dl / extractor / mit.py

diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py
index f50e36cb4fcc82a45d3a5f379beadb2764e2faf9..d7ab6a9aef23235d099175c7aff76ddd0ac0f84d 100644 (file)
--- a/youtube_dl/extractor/mit.py
+++ b/youtube_dl/extractor/mit.py
@@ -4,16 +4,17 @@ import re
 import json
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 from ..utils import (
-    compat_urlparse,
     clean_html,
+    ExtractorError,
     get_element_by_id,
 )
 
 
 class TechTVMITIE(InfoExtractor):
     IE_NAME = 'techtv.mit.edu'
-    _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
+    _VALID_URL = r'https?://techtv\.mit\.edu/(?:videos|embeds)/(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
@@ -27,8 +28,7 @@ class TechTVMITIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         raw_page = self._download_webpage(
             'http://techtv.mit.edu/videos/%s' % video_id, video_id)
         clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
@@ -71,7 +71,6 @@ class MITIE(TechTVMITIE):
 
     _TEST = {
         'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
-        'file': '.mp4',
         'md5': '7db01d5ccc1895fc5010e9c9e13648da',
         'info_dict': {
             'id': '21783',
@@ -88,3 +87,70 @@ class MITIE(TechTVMITIE):
         embed_url = self._search_regex(
             r'<iframe .*?src="(.+?)"', webpage, 'embed url')
         return self.url_result(embed_url, ie='TechTVMIT')
+
+
+class OCWMITIE(InfoExtractor):
+    IE_NAME = 'ocw.mit.edu'
+    _VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
+    _BASE_URL = 'http://ocw.mit.edu/'
+
+    _TESTS = [
+        {
+            'url': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/',
+            'info_dict': {
+                'id': 'EObHWIEKGjA',
+                'ext': 'mp4',
+                'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
+                'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
+                'upload_date': '20121109',
+                'uploader_id': 'MIT',
+                'uploader': 'MIT OpenCourseWare',
+            }
+        },
+        {
+            'url': 'http://ocw.mit.edu/courses/mathematics/18-01sc-single-variable-calculus-fall-2010/1.-differentiation/part-a-definition-and-basic-rules/session-1-introduction-to-derivatives/',
+            'info_dict': {
+                'id': '7K1sB05pE0A',
+                'ext': 'mp4',
+                'title': 'Session 1: Introduction to Derivatives',
+                'upload_date': '20090818',
+                'uploader_id': 'MIT',
+                'uploader': 'MIT OpenCourseWare',
+                'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        topic = mobj.group('topic')
+
+        webpage = self._download_webpage(url, topic)
+        title = self._html_search_meta('WT.cg_s', webpage)
+        description = self._html_search_meta('Description', webpage)
+
+        # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, start, stop, captions_file)
+        embed_chapter_media = re.search(r'ocw_embed_chapter_media\((.+?)\)', webpage)
+        if embed_chapter_media:
+            metadata = re.sub(r'[\'"]', '', embed_chapter_media.group(1))
+            metadata = re.split(r', ?', metadata)
+            yt = metadata[1]
+        else:
+            # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file)
+            embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage)
+            if embed_media:
+                metadata = re.sub(r'[\'"]', '', embed_media.group(1))
+                metadata = re.split(r', ?', metadata)
+                yt = metadata[1]
+            else:
+                raise ExtractorError('Unable to find embedded YouTube video.')
+        video_id = YoutubeIE.extract_id(yt)
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'url': yt,
+            'ie_key': 'Youtube',
+        }