Annotate some highlights of the release.

[youtubedl] / youtube_dl / extractor / tele5.py

diff --git a/youtube_dl/extractor/tele5.py b/youtube_dl/extractor/tele5.py
index 33a72083bff96a74e04020257ba3305d1cfee2ca..3e1a7a9e609a9eb80732348b86e5976e12093a0b 100644 (file)
--- a/youtube_dl/extractor/tele5.py
+++ b/youtube_dl/extractor/tele5.py
@@ -1,13 +1,21 @@
 # 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 ..compat import compat_urlparse
 from .nexx import NexxIE
 from ..compat import compat_urlparse

+from ..utils import (
+    NO_DEFAULT,
+    smuggle_url,
+)

 
 
 class Tele5IE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
 
 
 class Tele5IE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'

+    _GEO_COUNTRIES = ['DE']

     _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': {


@@ -20,6 +28,21 @@ class Tele5IE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
         'params': {
             'skip_download': True,
         },

+    }, {
+        # jwplatform, nexx unavailable
+        'url': 'https://www.tele5.de/filme/ghoul-das-geheimnis-des-friedhofmonsters/',
+        'info_dict': {
+            'id': 'WJuiOlUp',
+            'ext': 'mp4',
+            'upload_date': '20200603',
+            'timestamp': 1591214400,
+            'title': 'Ghoul - Das Geheimnis des Friedhofmonsters',
+            'description': 'md5:42002af1d887ff3d5b2b3ca1f8137d97',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [JWPlatformIE.ie_key()],

     }, {
         'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
         'only_matching': True,
     }, {
         'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
         'only_matching': True,


@@ -44,14 +67,42 @@ 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+)',
-                 r'\s+id\s*=\s*["\']player_(\d{6,})',
-                 r'\bdata-id\s*=\s*["\'](\d{6,})'), 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')

 
         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)
+            smuggle_url(
+                'jwplatform:%s' % jwplatform_id,
+                {'geo_countries': self._GEO_COUNTRIES}),
+            ie=JWPlatformIE.ie_key(), video_id=jwplatform_id)