Merge tag 'upstream/2015.05.15'

[youtubedl] / youtube_dl / extractor / gdcvault.py

diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py
index fed968f5179ebf6159212da5ab75b024b3bc0a03..43f916412d9b97f3ca93cea830e5390bdcc70db0 100644 (file)
--- a/youtube_dl/extractor/gdcvault.py
+++ b/youtube_dl/extractor/gdcvault.py
@@ -7,16 +7,19 @@ from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )
     compat_urllib_parse,
     compat_urllib_request,
 )

+from ..utils import remove_end

 
 
 class GDCVaultIE(InfoExtractor):
 
 
 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 = [
         {
             'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
             'md5': '7ce8388f544c88b7ac11c7ab1b593704',
             'info_dict': {
                 'id': '1019721',
     _TESTS = [
         {
             'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
             '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)'
             }
                 'ext': 'mp4',
                 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
             }


@@ -25,6 +28,7 @@ class GDCVaultIE(InfoExtractor):
             'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
             'info_dict': {
                 'id': '1015683',
             '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'
             },
                 'ext': 'flv',
                 'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
             },


@@ -37,10 +41,15 @@ class GDCVaultIE(InfoExtractor):
             'md5': 'a5eb77996ef82118afbbe8e48731b98e',
             'info_dict': {
                 'id': '1015301',
             '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',
                 '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,

         }
     ]
 
         }
     ]
 


@@ -65,10 +74,12 @@ 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,


@@ -76,7 +87,9 @@ 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,


@@ -84,7 +97,7 @@ class GDCVaultIE(InfoExtractor):
         })
         return video_formats
 
         })
         return video_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.')
         (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.')


@@ -101,9 +114,9 @@ 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')
 
         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
 
 
         return start_page
 


@@ -111,8 +124,10 @@ class GDCVaultIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
         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
         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\("(/[^"]+)"\)\);',
 
         direct_url = self._search_regex(
             r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',


@@ -125,6 +140,7 @@ class GDCVaultIE(InfoExtractor):
 
             return {
                 'id': video_id,
 
             return {
                 'id': video_id,

+                'display_id': display_id,

                 'url': video_url,
                 'ext': 'flv',
                 'title': title,
                 'url': video_url,
                 'ext': 'flv',
                 'title': title,


@@ -135,7 +151,7 @@ class GDCVaultIE(InfoExtractor):
             start_page, 'xml root', default=None)
         if xml_root is None:
             # Probably need to authenticate
             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:
             if login_res is None:
                 self.report_warning('Could not login.')
             else:


@@ -153,7 +169,7 @@ class GDCVaultIE(InfoExtractor):
             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_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 = self._download_xml(xml_decription_url, display_id)

 
         video_title = xml_description.find('./metadata/title').text
         video_formats = self._parse_mp4(xml_description)
 
         video_title = xml_description.find('./metadata/title').text
         video_formats = self._parse_mp4(xml_description)


@@ -162,6 +178,7 @@ class GDCVaultIE(InfoExtractor):
 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

+            'display_id': display_id,

             'title': video_title,
             'formats': video_formats,
         }
             'title': video_title,
             'formats': video_formats,
         }