Register new version in the changelog.

[youtubedl] / youtube_dl / extractor / mit.py

diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py
index 76b717fe5dbac08b8b103a1e44192a6fbf6d2a55..29ca45778a17654c4d2125ceda177b71cffca8a8 100644 (file)
--- a/youtube_dl/extractor/mit.py
+++ b/youtube_dl/extractor/mit.py
@@ -1,38 +1,42 @@
+from __future__ import unicode_literals
+

 import re
 import json
 
 from .common import InfoExtractor
 import re
 import json
 
 from .common import InfoExtractor

+from .youtube import YoutubeIE

 from ..utils import (
     clean_html,
 from ..utils import (
     clean_html,

+    ExtractorError,

     get_element_by_id,
 )
 
 
 class TechTVMITIE(InfoExtractor):
     get_element_by_id,
 )
 
 
 class TechTVMITIE(InfoExtractor):

-    IE_NAME = u'techtv.mit.edu'
-    _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
+    IE_NAME = 'techtv.mit.edu'
+    _VALID_URL = r'https?://techtv\.mit\.edu/(?:videos|embeds)/(?P<id>\d+)'

 
     _TEST = {
 
     _TEST = {

-        u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
-        u'file': u'25418.mp4',
-        u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
-        u'info_dict': {
-            u'title': u'MIT DNA Learning Center Set',
-            u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
+        'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
+        'md5': '00a3a27ee20d44bcaa0933ccec4a2cf7',
+        'info_dict': {
+            'id': '25418',
+            'ext': 'mp4',
+            'title': 'MIT DNA and Protein Sets',
+            'description': 'md5:46f5c69ce434f0a97e7c628cc142802d',

         },
     }
 
     def _real_extract(self, url):
         },
     }
 
     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)
         raw_page = self._download_webpage(
             'http://techtv.mit.edu/videos/%s' % video_id, video_id)

-        clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
+        clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)

 
 

-        base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
-            raw_page, u'base url')
-        formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
-            u'video formats')
+        base_url = self._proto_relative_url(self._search_regex(
+            r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url'), 'http:')
+        formats_json = self._search_regex(
+            r'bitrates: (\[.+?\])', raw_page, 'video formats')

         formats_mit = json.loads(formats_json)
         formats = [
             {
         formats_mit = json.loads(formats_json)
         formats = [
             {


@@ -48,28 +52,31 @@ class TechTVMITIE(InfoExtractor):
 
         title = get_element_by_id('edit-title', clean_page)
         description = clean_html(get_element_by_id('edit-description', clean_page))
 
         title = get_element_by_id('edit-title', clean_page)
         description = clean_html(get_element_by_id('edit-description', clean_page))

-        thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
-            raw_page, u'thumbnail', flags=re.DOTALL)
+        thumbnail = self._search_regex(
+            r'playlist:.*?url: \'(.+?)\'',
+            raw_page, 'thumbnail', flags=re.DOTALL)

 
 

-        return {'id': video_id,
-                'title': title,
-                'formats': formats,
-                'description': description,
-                'thumbnail': thumbnail,
-                }
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'thumbnail': thumbnail,
+        }

 
 
 class MITIE(TechTVMITIE):
 
 
 class MITIE(TechTVMITIE):

-    IE_NAME = u'video.mit.edu'
+    IE_NAME = 'video.mit.edu'

     _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
 
     _TEST = {
     _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
 
     _TEST = {

-        u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
-        u'file': u'21783.mp4',
-        u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
-        u'info_dict': {
-            u'title': u'The Government is Profiling You',
-            u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
+        'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
+        'md5': '7db01d5ccc1895fc5010e9c9e13648da',
+        'info_dict': {
+            'id': '21783',
+            'ext': 'mp4',
+            'title': 'The Government is Profiling You',
+            'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',

         },
     }
 
         },
     }
 


@@ -77,7 +84,73 @@ class MITIE(TechTVMITIE):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)

-        self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
-        embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
-            u'embed url')
-        return self.url_result(embed_url, ie='TechTVMIT')
+        embed_url = self._search_regex(
+            r'<iframe .*?src="(.+?)"', webpage, 'embed url')
+        return self.url_result(embed_url)
+
+
+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',
+        }