X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgdcvault.py;h=a6834db433de249ed2d0f9ffa7c07c3ff5becc16;hb=11bed5827dace09b5483b159476ce9f8c29d6078;hp=51796f3a40310f484cf1a49fc6e11468264dbe3a;hpb=938c3f65b6c1c1f5b8f7eb731a3eef00a06b6128;p=youtube-dl

diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py
index 51796f3a4..a6834db43 100644
--- a/youtube_dl/extractor/gdcvault.py
+++ b/youtube_dl/extractor/gdcvault.py
@@ -7,11 +7,14 @@ from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )
-from ..utils import remove_end
+from ..utils import (
+    remove_end,
+    HEADRequest,
+)
 
 
 class GDCVaultIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)'
+    _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)?'
     _NETRC_MACHINE = 'gdcvault'
     _TESTS = [
         {
@@ -19,6 +22,7 @@ class GDCVaultIE(InfoExtractor):
             'md5': '7ce8388f544c88b7ac11c7ab1b593704',
             'info_dict': {
                 'id': '1019721',
+                'display_id': 'Doki-Doki-Universe-Sweet-Simple',
                 'ext': 'mp4',
                 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
             }
@@ -27,6 +31,7 @@ class GDCVaultIE(InfoExtractor):
             'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
             'info_dict': {
                 'id': '1015683',
+                'display_id': 'Embracing-the-Dark-Art-of',
                 'ext': 'flv',
                 'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
             },
@@ -39,10 +44,15 @@ class GDCVaultIE(InfoExtractor):
             'md5': 'a5eb77996ef82118afbbe8e48731b98e',
             'info_dict': {
                 'id': '1015301',
+                'display_id': 'Thexder-Meets-Windows-95-or',
                 'ext': 'flv',
                 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
             },
             'skip': 'Requires login',
+        },
+        {
+            'url': 'http://gdcvault.com/play/1020791/',
+            'only_matching': True,
         }
     ]
 
@@ -66,10 +76,20 @@ class GDCVaultIE(InfoExtractor):
         return video_formats
 
     def _parse_flv(self, xml_description):
-        video_formats = []
+        formats = []
         akamai_url = xml_description.find('./metadata/akamaiHost').text
+        audios = xml_description.find('./metadata/audios')
+        if audios is not None:
+            for audio in audios:
+                formats.append({
+                    'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
+                    'play_path': remove_end(audio.get('url'), '.flv'),
+                    'ext': 'flv',
+                    'vcodec': 'none',
+                    'format_id': audio.get('code'),
+                })
         slide_video_path = xml_description.find('./metadata/slideVideo').text
-        video_formats.append({
+        formats.append({
             'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
             'play_path': remove_end(slide_video_path, '.flv'),
             'ext': 'flv',
@@ -79,7 +99,7 @@ class GDCVaultIE(InfoExtractor):
             'format_id': 'slides',
         })
         speaker_video_path = xml_description.find('./metadata/speakerVideo').text
-        video_formats.append({
+        formats.append({
             'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
             'play_path': remove_end(speaker_video_path, '.flv'),
             'ext': 'flv',
@@ -88,9 +108,9 @@ class GDCVaultIE(InfoExtractor):
             'preference': -1,
             'format_id': 'speaker',
         })
-        return video_formats
+        return formats
 
-    def _login(self, webpage_url, video_id):
+    def _login(self, webpage_url, display_id):
         (username, password) = self._get_login_info()
         if username is None or password is None:
             self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
@@ -107,9 +127,9 @@ class GDCVaultIE(InfoExtractor):
 
         request = compat_urllib_request.Request(login_url, compat_urllib_parse.urlencode(login_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        self._download_webpage(request, video_id, 'Logging in')
-        start_page = self._download_webpage(webpage_url, video_id, 'Getting authenticated video page')
-        self._download_webpage(logout_url, video_id, 'Logging out')
+        self._download_webpage(request, display_id, 'Logging in')
+        start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')
+        self._download_webpage(logout_url, display_id, 'Logging out')
 
         return start_page
 
@@ -117,22 +137,27 @@ class GDCVaultIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
+        display_id = mobj.group('name') or video_id
+
         webpage_url = 'http://www.gdcvault.com/play/' + video_id
-        start_page = self._download_webpage(webpage_url, video_id)
+        start_page = self._download_webpage(webpage_url, display_id)
 
         direct_url = self._search_regex(
             r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
             start_page, 'url', default=None)
         if direct_url:
-            video_url = 'http://www.gdcvault.com/' + direct_url
             title = self._html_search_regex(
                 r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>',
                 start_page, 'title')
+            video_url = 'http://www.gdcvault.com' + direct_url
+            # resolve the url so that we can detect the correct extension
+            head = self._request_webpage(HEADRequest(video_url), video_id)
+            video_url = head.geturl()
 
             return {
                 'id': video_id,
+                'display_id': display_id,
                 'url': video_url,
-                'ext': 'flv',
                 'title': title,
             }
 
@@ -141,7 +166,7 @@ class GDCVaultIE(InfoExtractor):
             start_page, 'xml root', default=None)
         if xml_root is None:
             # Probably need to authenticate
-            login_res = self._login(webpage_url, video_id)
+            login_res = self._login(webpage_url, display_id)
             if login_res is None:
                 self.report_warning('Could not login.')
             else:
@@ -158,8 +183,8 @@ class GDCVaultIE(InfoExtractor):
             # Fallback to the older format
             xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename')
 
-        xml_decription_url = xml_root + 'xml/' + xml_name
-        xml_description = self._download_xml(xml_decription_url, video_id)
+        xml_description_url = xml_root + 'xml/' + xml_name
+        xml_description = self._download_xml(xml_description_url, display_id)
 
         video_title = xml_description.find('./metadata/title').text
         video_formats = self._parse_mp4(xml_description)
@@ -168,6 +193,7 @@ class GDCVaultIE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': video_title,
             'formats': video_formats,
         }