Update upstream source from tag 'upstream/2020.05.08'

[youtubedl] / youtube_dl / extractor / tele5.py

diff --git a/youtube_dl/extractor/tele5.py b/youtube_dl/extractor/tele5.py
index 25573e49ff115f4a91262b9a42bb3436bb93197d..364556a1f89d3c1943950c1634bbfae0639a3e7d 100644 (file)
--- a/youtube_dl/extractor/tele5.py
+++ b/youtube_dl/extractor/tele5.py
@@ -1,13 +1,23 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

+import re
+

 from .common import InfoExtractor
 from .common import InfoExtractor

+from .jwplatform import JWPlatformIE

 from .nexx import NexxIE
 from .nexx import NexxIE

-from ..compat import compat_urlparse
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
+from ..utils import (
+    NO_DEFAULT,
+    try_get,
+)

 
 
 class Tele5IE(InfoExtractor):
 
 
 class Tele5IE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P<id>[^?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'

     _TESTS = [{
         'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
         'info_dict': {
     _TESTS = [{
         'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
         'info_dict': {


@@ -21,10 +31,22 @@ class Tele5IE(InfoExtractor):
             'skip_download': True,
         },
     }, {
             'skip_download': True,
         },
     }, {

-        'url': 'https://www.tele5.de/tv/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
+        'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/video-clip/?ve_id=1609440',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/filme/schlefaz-dragon-crusaders/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/filme/making-of/avengers-endgame/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/star-trek/raumschiff-voyager/ganze-folge/das-vinculum/',

         'only_matching': True,
     }, {
         'only_matching': True,
     }, {

-        'url': 'https://www.tele5.de/tv/dark-matter/videos',
+        'url': 'https://www.tele5.de/anders-ist-sevda/',

         'only_matching': True,
     }]
 
         'only_matching': True,
     }]
 


@@ -32,13 +54,49 @@ class Tele5IE(InfoExtractor):
         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
         video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
 
         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
         video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
 

-        if not video_id:
+        NEXX_ID_RE = r'\d{6,}'
+        JWPLATFORM_ID_RE = r'[a-zA-Z0-9]{8}'
+
+        def nexx_result(nexx_id):
+            return self.url_result(
+                'https://api.nexx.cloud/v3/759/videos/byid/%s' % nexx_id,
+                ie=NexxIE.ie_key(), video_id=nexx_id)
+
+        nexx_id = jwplatform_id = None
+
+        if video_id:
+            if re.match(NEXX_ID_RE, video_id):
+                return nexx_result(video_id)
+            elif re.match(JWPLATFORM_ID_RE, video_id):
+                jwplatform_id = video_id
+
+        if not nexx_id:

             display_id = self._match_id(url)
             webpage = self._download_webpage(url, display_id)
             display_id = self._match_id(url)
             webpage = self._download_webpage(url, display_id)

-            video_id = self._html_search_regex(
-                r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)',
-                webpage, 'video id')
+
+            def extract_id(pattern, name, default=NO_DEFAULT):
+                return self._html_search_regex(
+                    (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](%s)' % pattern,
+                     r'\s+id\s*=\s*["\']player_(%s)' % pattern,
+                     r'\bdata-id\s*=\s*["\'](%s)' % pattern), webpage, name,
+                    default=default)
+
+            nexx_id = extract_id(NEXX_ID_RE, 'nexx id', default=None)
+            if nexx_id:
+                return nexx_result(nexx_id)
+
+            if not jwplatform_id:
+                jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id')
+
+            media = self._download_json(
+                'https://cdn.jwplayer.com/v2/media/' + jwplatform_id,
+                display_id)
+            nexx_id = try_get(
+                media, lambda x: x['playlist'][0]['nexx_id'], compat_str)
+
+            if nexx_id:
+                return nexx_result(nexx_id)

 
         return self.url_result(
 
         return self.url_result(

-            'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,
-            ie=NexxIE.ie_key(), video_id=video_id)
+            'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
+            video_id=jwplatform_id)