[ie/orf:on] Improve extraction (#9677)

[yt-dlp.git] / yt_dlp / extractor / piksel.py

diff --git a/yt_dlp/extractor/piksel.py b/yt_dlp/extractor/piksel.py
index 5cc99a44e6a6a30de5604f05b5721b27c8a36a9f..97a9bf5745b969f28ff265f85f433e0285169ffe 100644 (file)
--- a/yt_dlp/extractor/piksel.py
+++ b/yt_dlp/extractor/piksel.py
@@ -1,17 +1,16 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     dict_get,
     ExtractorError,
     int_or_none,
+    join_nonempty,
     parse_iso8601,
+    traverse_obj,
     try_get,
     unescapeHTML,
+    urljoin,
 )
 
 
@@ -33,6 +32,7 @@ class PikselIE(InfoExtractor):
             )\.jp|
             vidego\.baltimorecity\.gov
         )/v/(?:refid/(?P<refid>[^/]+)/prefid/)?(?P<id>[\w-]+)'''
+    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//player\.piksel\.com/v/[a-z0-9]+)']
     _TESTS = [
         {
             'url': 'http://player.piksel.com/v/ums2867l',
@@ -65,19 +65,11 @@ class PikselIE(InfoExtractor):
         }
     ]
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//player\.piksel\.com/v/[a-z0-9]+)',
-            webpage)
-        if mobj:
-            return mobj.group('url')
-
-    def _call_api(self, app_token, resource, display_id, query, fatal=True):
-        response = (self._download_json(
-            'http://player.piksel.com/ws/ws_%s/api/%s/mode/json/apiv/5' % (resource, app_token),
-            display_id, query=query, fatal=fatal) or {}).get('response')
-        failure = try_get(response, lambda x: x['failure']['reason'])
+    def _call_api(self, app_token, resource, display_id, query, host='https://player.piksel.com', fatal=True):
+        url = urljoin(host, f'/ws/ws_{resource}/api/{app_token}/mode/json/apiv/5')
+        response = traverse_obj(
+            self._download_json(url, display_id, query=query, fatal=fatal), ('response', {dict})) or {}
+        failure = traverse_obj(response, ('failure', 'reason')) if response else 'Empty response from API'
         if failure:
             if fatal:
                 raise ExtractorError(failure, expected=True)
@@ -93,7 +85,7 @@ def _real_extract(self, url):
         ], webpage, 'app token')
         query = {'refid': ref_id, 'prefid': display_id} if ref_id else {'v': display_id}
         program = self._call_api(
-            app_token, 'program', display_id, query)['WsProgramResponse']['program']
+            app_token, 'program', display_id, query, url)['WsProgramResponse']['program']
         video_id = program['uuid']
         video_data = program['asset']
         title = video_data['title']
@@ -116,12 +108,8 @@ def process_asset_file(asset_file):
             elif asset_type == 'audio':
                 tbr = abr
 
-            format_id = ['http']
-            if tbr:
-                format_id.append(compat_str(tbr))
-
             formats.append({
-                'format_id': '-'.join(format_id),
+                'format_id': join_nonempty('http', tbr),
                 'url': unescapeHTML(http_url),
                 'vbr': vbr,
                 'abr': abr,
@@ -143,7 +131,7 @@ def process_asset_files(asset_files):
                 process_asset_files(try_get(self._call_api(
                     app_token, 'asset_file', display_id, {
                         'assetid': asset_id,
-                    }, False), lambda x: x['WsAssetFileResponse']['AssetFiles']))
+                    }, url, False), lambda x: x['WsAssetFileResponse']['AssetFiles']))
 
         m3u8_url = dict_get(video_data, [
             'm3u8iPadURL',
@@ -167,8 +155,6 @@ def process_asset_files(asset_files):
                 re.sub(r'/od/[^/]+/', '/od/http/', smil_url), video_id,
                 transform_source=transform_source, fatal=False))
 
-        self._sort_formats(formats, ('tbr', ))  # Incomplete resolution information
-
         subtitles = {}
         for caption in video_data.get('captions', []):
             caption_url = caption.get('url')
@@ -184,4 +170,5 @@ def process_asset_files(asset_files):
             'timestamp': parse_iso8601(video_data.get('dateadd')),
             'formats': formats,
             'subtitles': subtitles,
+            '_format_sort_fields': ('tbr', ),  # Incomplete resolution information
         }