[ie/mlbtv] Fix extraction (#10296)

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

diff --git a/yt_dlp/extractor/viidea.py b/yt_dlp/extractor/viidea.py
index 157ce4d8f944972bfd1cbd0612bf9ed25b89ca49..2f04e880f4c90f31dc08d083d1efa64aa701b2b7 100644 (file)
--- a/yt_dlp/extractor/viidea.py
+++ b/yt_dlp/extractor/viidea.py
@@ -1,11 +1,8 @@
 import re
+import urllib.parse
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_HTTPError,
-    compat_str,
-    compat_urlparse,
-)
+from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     js_to_json,
@@ -124,18 +121,18 @@ def _real_extract(self, url):
              r'cfg\s*:\s*({[^}]+})'],
             webpage, 'cfg'), lecture_slug, js_to_json)
 
-        lecture_id = compat_str(cfg['obj_id'])
+        lecture_id = str(cfg['obj_id'])
 
         base_url = self._proto_relative_url(cfg['livepipe'], 'http:')
 
         try:
             lecture_data = self._download_json(
-                '%s/site/api/lecture/%s?format=json' % (base_url, lecture_id),
+                f'{base_url}/site/api/lecture/{lecture_id}?format=json',
                 lecture_id)['lecture'][0]
         except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 403:
                 msg = self._parse_json(
-                    e.cause.read().decode('utf-8'), lecture_id)
+                    e.cause.response.read().decode('utf-8'), lecture_id)
                 raise ExtractorError(msg['detail'], expected=True)
             raise
 
@@ -150,19 +147,18 @@ def _real_extract(self, url):
 
         playlist_entries = []
         lecture_type = lecture_data.get('type')
-        parts = [compat_str(video) for video in cfg.get('videos', [])]
+        parts = [str(video) for video in cfg.get('videos', [])]
         if parts:
             multipart = len(parts) > 1
 
             def extract_part(part_id):
-                smil_url = '%s/%s/video/%s/smil.xml' % (base_url, lecture_slug, part_id)
+                smil_url = f'{base_url}/{lecture_slug}/video/{part_id}/smil.xml'
                 smil = self._download_smil(smil_url, lecture_id)
                 info = self._parse_smil(smil, smil_url, lecture_id)
-                self._sort_formats(info['formats'])
-                info['id'] = lecture_id if not multipart else '%s_part%s' % (lecture_id, part_id)
-                info['display_id'] = lecture_slug if not multipart else '%s_part%s' % (lecture_slug, part_id)
+                info['id'] = lecture_id if not multipart else f'{lecture_id}_part{part_id}'
+                info['display_id'] = lecture_slug if not multipart else f'{lecture_slug}_part{part_id}'
                 if multipart:
-                    info['title'] += ' (Part %s)' % part_id
+                    info['title'] += f' (Part {part_id})'
                 switch = smil.find('.//switch')
                 if switch is not None:
                     info['duration'] = parse_duration(switch.attrib.get('dur'))
@@ -188,9 +184,9 @@ def extract_part(part_id):
         # It's probably a playlist
         if not parts or lecture_type == 'evt':
             playlist_webpage = self._download_webpage(
-                '%s/site/ajax/drilldown/?id=%s' % (base_url, lecture_id), lecture_id)
+                f'{base_url}/site/ajax/drilldown/?id={lecture_id}', lecture_id)
             entries = [
-                self.url_result(compat_urlparse.urljoin(url, video_url), 'Viidea')
+                self.url_result(urllib.parse.urljoin(url, video_url), 'Viidea')
                 for _, video_url in re.findall(
                     r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', playlist_webpage)]
             playlist_entries.extend(entries)