[cleanup] Add more ruff rules (#10149)

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

diff --git a/yt_dlp/extractor/redtube.py b/yt_dlp/extractor/redtube.py
index 7fee54fee418d931e0e7ba520c7d9428eae6e46c..94a90540d1483f00c11b6200acd2b52a9be350ff 100644 (file)
--- a/yt_dlp/extractor/redtube.py
+++ b/yt_dlp/extractor/redtube.py
@@ -1,21 +1,19 @@
-from __future__ import unicode_literals
-
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     ExtractorError,
+    determine_ext,
     int_or_none,
     merge_dicts,
     str_to_int,
     unified_strdate,
     url_or_none,
+    urljoin,
 )
 
 
 class RedTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com(?:\.br)?/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)']
     _TESTS = [{
         'url': 'https://www.redtube.com/38864951',
         'md5': '4fba70cbca3aefd25767ab4b523c9878',
@@ -37,18 +35,15 @@ class RedTubeIE(InfoExtractor):
     }, {
         'url': 'http://it.redtube.com/66418',
         'only_matching': True,
+    }, {
+        'url': 'https://www.redtube.com.br/103224331',
+        'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)',
-            webpage)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
-            'http://www.redtube.com/%s' % video_id, video_id)
+            f'https://www.redtube.com/{video_id}', video_id)
 
         ERRORS = (
             (('video-deleted-info', '>This video has been removed'), 'has been removed'),
@@ -58,14 +53,14 @@ def _real_extract(self, url):
         for patterns, message in ERRORS:
             if any(p in webpage for p in patterns):
                 raise ExtractorError(
-                    'Video %s %s' % (video_id, message), expected=True)
+                    f'Video {video_id} {message}', expected=True)
 
         info = self._search_json_ld(webpage, video_id, default={})
 
         if not info.get('title'):
             info['title'] = self._html_search_regex(
                 (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle|video_title)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
-                 r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
+                 r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
                 webpage, 'title', group='title',
                 default=None) or self._og_search_title(webpage)
 
@@ -88,7 +83,7 @@ def _real_extract(self, url):
                 'media definitions', default='{}'),
             video_id, fatal=False)
         for media in medias if isinstance(medias, list) else []:
-            format_url = url_or_none(media.get('videoUrl'))
+            format_url = urljoin('https://www.redtube.com', media.get('videoUrl'))
             if not format_url:
                 continue
             format_id = media.get('format')
@@ -119,7 +114,6 @@ def _real_extract(self, url):
             video_url = self._html_search_regex(
                 r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
             formats.append({'url': video_url, 'ext': 'mp4'})
-        self._sort_formats(formats)
 
         thumbnail = self._og_search_thumbnail(webpage)
         upload_date = unified_strdate(self._search_regex(