Merge pull request #183 from ytdl-org/master

[pull] master from ytdl-org:master

youtube_dl/extractor/nintendo.py

@@ -5,13 +5,12 @@ import re
 
 from .common import InfoExtractor
 from .ooyala import OoyalaIE
-from ..utils import unescapeHTML
 
 
 class NintendoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nintendo\.com/games/detail/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?nintendo\.com/(?:games/detail|nintendo-direct)/(?P<id>[^/?#&]+)'
     _TESTS = [{
-        'url': 'http://www.nintendo.com/games/detail/yEiAzhU2eQI1KZ7wOHhngFoAHc1FpHwj',
+        'url': 'https://www.nintendo.com/games/detail/duck-hunt-wii-u/',
         'info_dict': {
             'id': 'MzMmticjp0VPzO3CCj4rmFOuohEuEWoW',
             'ext': 'flv',
@@ -28,7 +27,19 @@ class NintendoIE(InfoExtractor):
             'id': 'tokyo-mirage-sessions-fe-wii-u',
             'title': 'Tokyo Mirage Sessions ♯FE',
         },
-        'playlist_count': 3,
+        'playlist_count': 4,
+    }, {
+        'url': 'https://www.nintendo.com/nintendo-direct/09-04-2019/',
+        'info_dict': {
+            'id': 'J2bXdmaTE6fe3dWJTPcc7m23FNbc_A1V',
+            'ext': 'mp4',
+            'title': 'Switch_ROS_ND0904-H264.mov',
+            'duration': 2324.758,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Ooyala'],
     }]
 
     def _real_extract(self, url):
@@ -39,8 +50,11 @@ class NintendoIE(InfoExtractor):
         entries = [
             OoyalaIE._build_url_result(m.group('code'))
             for m in re.finditer(
-                r'class=(["\'])embed-video\1[^>]+data-video-code=(["\'])(?P<code>(?:(?!\2).)+)\2',
+                r'data-(?:video-id|directVideoId)=(["\'])(?P<code>(?:(?!\1).)+)\1', webpage)]
-                webpage)]
+
+        title = self._html_search_regex(
+            r'(?s)<(?:span|div)[^>]+class="(?:title|wrapper)"[^>]*>.*?<h1>(.+?)</h1>',
+            webpage, 'title', fatal=False)
 
         return self.playlist_result(
-            entries, page_id, unescapeHTML(self._og_search_title(webpage, fatal=False)))
+            entries, page_id, title)

youtube_dl/extractor/nrl.py

@@ -23,8 +23,8 @@ class NRLTVIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        q_data = self._parse_json(self._search_regex(
+        q_data = self._parse_json(self._html_search_regex(
-            r"(?s)q-data='({.+?})'", webpage, 'player data'), display_id)
+            r'(?s)q-data="({.+?})"', webpage, 'player data'), display_id)
         ooyala_id = q_data['videoId']
         return self.url_result(
             'ooyala:' + ooyala_id, 'Ooyala', ooyala_id, q_data.get('title'))

youtube_dl/extractor/ooyala.py

@@ -1,12 +1,12 @@
 from __future__ import unicode_literals
 
+import base64
 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_b64decode,
     compat_str,
-    compat_urllib_parse_urlencode,
 )
 from ..utils import (
     determine_ext,
@@ -21,9 +21,9 @@ from ..utils import (
 class OoyalaBaseIE(InfoExtractor):
     _PLAYER_BASE = 'http://player.ooyala.com/'
     _CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/'
-    _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?'
+    _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s'
 
-    def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None, embed_token=None):
+    def _extract(self, content_tree_url, video_id, domain=None, supportedformats=None, embed_token=None):
         content_tree = self._download_json(content_tree_url, video_id)['content_tree']
         metadata = content_tree[list(content_tree)[0]]
         embed_code = metadata['embed_code']
@@ -31,19 +31,22 @@ class OoyalaBaseIE(InfoExtractor):
         title = metadata['title']
 
         auth_data = self._download_json(
-            self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code)
+            self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code),
-            + compat_urllib_parse_urlencode({
+            video_id, headers=self.geo_verification_headers(), query={
-                'domain': domain,
+                'domain': domain or 'player.ooyala.com',
                 'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth',
                 'embedToken': embed_token,
-            }), video_id, headers=self.geo_verification_headers())
+            })['authorization_data'][embed_code]
-
-        cur_auth_data = auth_data['authorization_data'][embed_code]
 
         urls = []
         formats = []
-        if cur_auth_data['authorized']:
+        streams = auth_data.get('streams') or [{
-            for stream in cur_auth_data['streams']:
+            'delivery_type': 'hls',
+            'url': {
+                'data': base64.b64encode(('http://player.ooyala.com/hls/player/all/%s.m3u8' % embed_code).encode()).decode(),
+            }
+        }]
+        for stream in streams:
             url_data = try_get(stream, lambda x: x['url']['data'], compat_str)
             if not url_data:
                 continue
@@ -81,9 +84,9 @@ class OoyalaBaseIE(InfoExtractor):
                     'vbr': int_or_none(stream.get('video_bitrate')),
                     'fps': float_or_none(stream.get('framerate')),
                 })
-        else:
+        if not formats and not auth_data.get('authorized'):
             raise ExtractorError('%s said: %s' % (
-                self.IE_NAME, cur_auth_data['message']), expected=True)
+                self.IE_NAME, auth_data['message']), expected=True)
         self._sort_formats(formats)
 
         subtitles = {}

youtube_dl/extractor/teachingchannel.py

@@ -1,35 +1,33 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from .ooyala import OoyalaIE
 
 
 class TeachingChannelIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos/(?P<title>.+)'
+    _VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos?/(?P<id>[^/?&#]+)'
 
     _TEST = {
         'url': 'https://www.teachingchannel.org/videos/teacher-teaming-evolution',
-        'md5': '3d6361864d7cac20b57c8784da17166f',
         'info_dict': {
-            'id': 'F3bnlzbToeI6pLEfRyrlfooIILUjz4nM',
+            'id': '3swwlzkT',
             'ext': 'mp4',
             'title': 'A History of Teaming',
             'description': 'md5:2a9033db8da81f2edffa4c99888140b3',
-            'duration': 422.255,
+            'duration': 422,
+            'upload_date': '20170316',
+            'timestamp': 1489691297,
         },
         'params': {
             'skip_download': True,
         },
-        'add_ie': ['Ooyala'],
+        'add_ie': ['JWPlatform'],
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        display_id = self._match_id(url)
-        title = mobj.group('title')
+        webpage = self._download_webpage(url, display_id)
-        webpage = self._download_webpage(url, title)
+        mid = self._search_regex(
-        ooyala_code = self._search_regex(
+            r'(?:data-mid=["\']|id=["\']jw-video-player-)([a-zA-Z0-9]{8})',
-            r'data-embed-code=\'(.+?)\'', webpage, 'ooyala code')
+            webpage, 'media id')
 
-        return OoyalaIE._build_url_result(ooyala_code)
+        return self.url_result('jwplatform:' + mid, 'JWPlatform', mid)