Merge branch 'viki-shows' of https://github.com/ping/youtube-dl into ping-viki-shows

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 21f7b7290670a7d5b562df4f3d557238ad1f745f..173e9a15515a2a8325d7e86bb053bb3f3beded5e 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -141,6 +141,7 @@ from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
+from .espn import ESPNIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .expotv import ExpoTVIE
@@ -376,7 +377,10 @@ from .nytimes import (
 from .nuvid import NuvidIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
-from .ooyala import OoyalaIE
+from .ooyala import (
+    OoyalaIE,
+    OoyalaExternalIE,
+)
 from .openfilm import OpenFilmIE
 from .orf import (
     ORFTVthekIE,

diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py
new file mode 100644 (file)
index 0000000..e6f8f03
--- /dev/null
+++ b/youtube_dl/extractor/espn.py
@@ -0,0 +1,55 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class ESPNIE(InfoExtractor):
+    _VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+    _WORKING = False
+    _TESTS = [{
+        'url': 'http://espn.go.com/video/clip?id=10365079',
+        'info_dict': {
+            'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
+            'ext': 'mp4',
+            'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
+            'description': '',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079',
+        'only_matching': True,
+    }, {
+        'url': 'http://espn.go.com/nba/recap?gameId=400793786',
+        'only_matching': True,
+    }, {
+        'url': 'http://espn.go.com/blog/golden-state-warriors/post/_/id/593/how-warriors-rapidly-regained-a-winning-edge',
+        'only_matching': True,
+    }, {
+        'url': 'http://espn.go.com/sports/endurance/story/_/id/12893522/dzhokhar-tsarnaev-sentenced-role-boston-marathon-bombings',
+        'only_matching': True,
+    }, {
+        'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._search_regex(
+            r'class="video-play-button"[^>]+data-id="(\d+)',
+            webpage, 'video id')
+
+        player = self._download_webpage(
+            'https://espn.go.com/video/iframe/twitter/?id=%s' % video_id, video_id)
+
+        pcode = self._search_regex(
+            r'["\']pcode=([^"\']+)["\']', player, 'pcode')
+
+        return self.url_result(
+            'ooyalaexternal:espn:%s:%s' % (video_id, pcode),
+            'OoyalaExternal')

diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py
index c0e6d643d51982a8f8e0694329f940345c5f1284..a262a9f6d4ec232e78ee34f3ce38b03ea27d01e9 100644 (file)
--- a/youtube_dl/extractor/ooyala.py
+++ b/youtube_dl/extractor/ooyala.py
@@ -12,50 +12,7 @@ from ..utils import (
 )
 
 
-class OoyalaIE(InfoExtractor):
-    _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)'
-
-    _TESTS = [
-        {
-            # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
-            'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
-            'info_dict': {
-                'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
-                'ext': 'mp4',
-                'title': 'Explaining Data Recovery from Hard Drives and SSDs',
-                'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
-            },
-        }, {
-            # Only available for ipad
-            'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
-            'info_dict': {
-                'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
-                'ext': 'mp4',
-                'title': 'Simulation Overview - Levels of Simulation',
-                'description': '',
-            },
-        },
-        {
-            # Information available only through SAS api
-            # From http://community.plm.automation.siemens.com/t5/News-NX-Manufacturing/Tool-Path-Divide/ba-p/4187
-            'url': 'http://player.ooyala.com/player.js?embedCode=FiOG81ZTrvckcchQxmalf4aQj590qTEx',
-            'md5': 'a84001441b35ea492bc03736e59e7935',
-            'info_dict': {
-                'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx',
-                'ext': 'mp4',
-                'title': 'Ooyala video',
-            }
-        }
-    ]
-
-    @staticmethod
-    def _url_for_embed_code(embed_code):
-        return 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
-
-    @classmethod
-    def _build_url_result(cls, embed_code):
-        return cls.url_result(cls._url_for_embed_code(embed_code),
-                              ie=cls.ie_key())
+class OoyalaBaseIE(InfoExtractor):
 
     def _extract_result(self, info, more_info):
         embedCode = info['embedCode']
@@ -77,11 +34,8 @@ class OoyalaIE(InfoExtractor):
             'thumbnail': more_info['promo'],
         }
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        embedCode = mobj.group('id')
-        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
-        player = self._download_webpage(player_url, embedCode)
+    def _extract(self, player_url, video_id):
+        player = self._download_webpage(player_url, video_id)
         mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
                                         player, 'mobile player url')
         # Looks like some videos are only available for particular devices
@@ -94,7 +48,7 @@ class OoyalaIE(InfoExtractor):
         devices.insert(0, 'unknown')
         for device in devices:
             mobile_player = self._download_webpage(
-                '%s&device=%s' % (mobile_url, device), embedCode,
+                '%s&device=%s' % (mobile_url, device), video_id,
                 'Downloading mobile player JS for %s device' % device)
             videos_info = self._search_regex(
                 r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
@@ -105,10 +59,10 @@ class OoyalaIE(InfoExtractor):
         if not videos_info:
             formats = []
             auth_data = self._download_json(
-                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (embedCode, embedCode),
-                embedCode)
+                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id),
+                video_id)
 
-            cur_auth_data = auth_data['authorization_data'][embedCode]
+            cur_auth_data = auth_data['authorization_data'][video_id]
 
             for stream in cur_auth_data['streams']:
                 formats.append({
@@ -123,7 +77,7 @@ class OoyalaIE(InfoExtractor):
                 })
             if formats:
                 return {
-                    'id': embedCode,
+                    'id': video_id,
                     'formats': formats,
                     'title': 'Ooyala video',
                 }
@@ -143,9 +97,100 @@ class OoyalaIE(InfoExtractor):
             videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
             return {
                 '_type': 'playlist',
-                'id': embedCode,
+                'id': video_id,
                 'title': unescapeHTML(videos_more_info['title']),
                 'entries': videos,
             }
         else:
             return self._extract_result(videos_info[0], videos_more_info)
+
+
+class OoyalaIE(OoyalaBaseIE):
+    _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)'
+
+    _TESTS = [
+        {
+            # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
+            'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
+            'info_dict': {
+                'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
+                'ext': 'mp4',
+                'title': 'Explaining Data Recovery from Hard Drives and SSDs',
+                'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
+            },
+        }, {
+            # Only available for ipad
+            'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
+            'info_dict': {
+                'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
+                'ext': 'mp4',
+                'title': 'Simulation Overview - Levels of Simulation',
+                'description': '',
+            },
+        },
+        {
+            # Information available only through SAS api
+            # From http://community.plm.automation.siemens.com/t5/News-NX-Manufacturing/Tool-Path-Divide/ba-p/4187
+            'url': 'http://player.ooyala.com/player.js?embedCode=FiOG81ZTrvckcchQxmalf4aQj590qTEx',
+            'md5': 'a84001441b35ea492bc03736e59e7935',
+            'info_dict': {
+                'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx',
+                'ext': 'mp4',
+                'title': 'Ooyala video',
+            }
+        }
+    ]
+
+    @staticmethod
+    def _url_for_embed_code(embed_code):
+        return 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
+
+    @classmethod
+    def _build_url_result(cls, embed_code):
+        return cls.url_result(cls._url_for_embed_code(embed_code),
+                              ie=cls.ie_key())
+
+    def _real_extract(self, url):
+        embed_code = self._match_id(url)
+        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
+        return self._extract(player_url, embed_code)
+
+
+class OoyalaExternalIE(OoyalaBaseIE):
+    _VALID_URL = r'''(?x)
+                    (?:
+                        ooyalaexternal:|
+                        https?://.+?\.ooyala\.com/.*?\bexternalId=
+                    )
+                    (?P<partner_id>[^:]+)
+                    :
+                    (?P<id>.+)
+                    (?:
+                        :|
+                        .*?&pcode=
+                    )
+                    (?P<pcode>.+?)
+                    (&|$)
+                    '''
+
+    _TEST = {
+        'url': 'https://player.ooyala.com/player.js?externalId=espn:10365079&pcode=1kNG061cgaoolOncv54OAO1ceO-I&adSetCode=91cDU6NuXTGKz3OdjOxFdAgJVtQcKJnI&callback=handleEvents&hasModuleParams=1&height=968&playerBrandingId=7af3bd04449c444c964f347f11873075&targetReplaceId=videoPlayer&width=1656&wmode=opaque&allowScriptAccess=always',
+        'info_dict': {
+            'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
+            'ext': 'mp4',
+            'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
+            'description': '',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        partner_id = mobj.group('partner_id')
+        video_id = mobj.group('id')
+        pcode = mobj.group('pcode')
+        player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode)
+        return self._extract(player_url, video_id)

diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py
index b8775c2f99f4a105ae35f1b04a919e64c987df0f..3073e5e866150048523dc4cbe65e66c57661e3a3 100644 (file)
--- a/youtube_dl/extractor/sbs.py
+++ b/youtube_dl/extractor/sbs.py
@@ -33,16 +33,18 @@ class SBSIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
 
-        release_urls_json = js_to_json(self._search_regex(
+        player = self._search_regex(
             r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n',
-            webpage, ''))
-        release_urls = json.loads(release_urls_json)
-        theplatform_url = (
-            release_urls.get('progressive') or release_urls.get('standard'))
+            webpage, 'player')
+        player = re.sub(r"'\s*\+\s*[\da-zA-Z_]+\s*\+\s*'", '', player)
+
+        release_urls = self._parse_json(js_to_json(player), video_id)
+
+        theplatform_url = release_urls.get('progressive') or release_urls['standard']
 
         title = remove_end(self._og_search_title(webpage), ' (The Feed)')
         description = self._html_search_meta('description', webpage)
@@ -52,7 +54,6 @@ class SBSIE(InfoExtractor):
             '_type': 'url_transparent',
             'id': video_id,
             'url': theplatform_url,
-
             'title': title,
             'description': description,
             'thumbnail': thumbnail,