debian/copyright: Update my copyright years.

[youtubedl] / youtube_dl / extractor / gdcvault.py

diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py
index 89d5994eef02623222b73fa04e0287a264b01333..f7b467b0aff8f46aa028d1898f5909277e973318 100644 (file)
--- a/youtube_dl/extractor/gdcvault.py
+++ b/youtube_dl/extractor/gdcvault.py
@@ -3,10 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_urllib_parse,
     compat_urllib_request,
 )
     compat_urllib_parse,
     compat_urllib_request,
 )

+from ..utils import remove_end
+

 
 class GDCVaultIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)'
 
 class GDCVaultIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)'


@@ -31,6 +33,16 @@ class GDCVaultIE(InfoExtractor):
                 'skip_download': True,  # Requires rtmpdump
             }
         },
                 'skip_download': True,  # Requires rtmpdump
             }
         },

+        {
+            'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or',
+            'md5': 'a5eb77996ef82118afbbe8e48731b98e',
+            'info_dict': {
+                'id': '1015301',
+                'ext': 'flv',
+                'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
+            },
+            'skip': 'Requires login',
+        }

     ]
 
     def _parse_mp4(self, xml_description):
     ]
 
     def _parse_mp4(self, xml_description):


@@ -54,10 +66,12 @@ class GDCVaultIE(InfoExtractor):
 
     def _parse_flv(self, xml_description):
         video_formats = []
 
     def _parse_flv(self, xml_description):
         video_formats = []

-        akami_url = xml_description.find('./metadata/akamaiHost').text
+        akamai_url = xml_description.find('./metadata/akamaiHost').text

         slide_video_path = xml_description.find('./metadata/slideVideo').text
         video_formats.append({
         slide_video_path = xml_description.find('./metadata/slideVideo').text
         video_formats.append({

-            'url': 'rtmp://' + akami_url + '/' + slide_video_path,
+            'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
+            'play_path': remove_end(slide_video_path, '.flv'),
+            'ext': 'flv',

             'format_note': 'slide deck video',
             'quality': -2,
             'preference': -2,
             'format_note': 'slide deck video',
             'quality': -2,
             'preference': -2,


@@ -65,7 +79,9 @@ class GDCVaultIE(InfoExtractor):
         })
         speaker_video_path = xml_description.find('./metadata/speakerVideo').text
         video_formats.append({
         })
         speaker_video_path = xml_description.find('./metadata/speakerVideo').text
         video_formats.append({

-            'url': 'rtmp://' + akami_url + '/' + speaker_video_path,
+            'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
+            'play_path': remove_end(speaker_video_path, '.flv'),
+            'ext': 'flv',

             'format_note': 'speaker video',
             'quality': -1,
             'preference': -1,
             'format_note': 'speaker video',
             'quality': -1,
             'preference': -1,


@@ -103,18 +119,40 @@ class GDCVaultIE(InfoExtractor):
         webpage_url = 'http://www.gdcvault.com/play/' + video_id
         start_page = self._download_webpage(webpage_url, video_id)
 
         webpage_url = 'http://www.gdcvault.com/play/' + video_id
         start_page = self._download_webpage(webpage_url, video_id)
 

-        xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root', None, False)
+        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')
+
+            return {
+                'id': video_id,
+                'url': video_url,
+                'ext': 'flv',
+                'title': title,
+            }

 
 

+        xml_root = self._html_search_regex(
+            r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>',
+            start_page, 'xml root', default=None)

         if xml_root is None:
             # Probably need to authenticate
         if xml_root is None:
             # Probably need to authenticate

-            start_page = self._login(webpage_url, video_id)
-            if start_page is None:
+            login_res = self._login(webpage_url, video_id)
+            if login_res is None:

                 self.report_warning('Could not login.')
             else:
                 self.report_warning('Could not login.')
             else:

+                start_page = login_res

                 # Grab the url from the authenticated page
                 # Grab the url from the authenticated page

-                xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root')
+                xml_root = self._html_search_regex(
+                    r'<iframe src="(.*?)player.html.*?".*?</iframe>',
+                    start_page, 'xml root')

 
 

-        xml_name = self._html_search_regex(r'<iframe src=".*?\?xml=(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename', None, False)
+        xml_name = self._html_search_regex(
+            r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>',
+            start_page, 'xml filename', default=None)

         if xml_name is None:
             # 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')
         if xml_name is None:
             # 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')