[misc] Add `hatch`, `ruff`, `pre-commit` and improve dev docs (#7409)

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

diff --git a/yt_dlp/extractor/redtube.py b/yt_dlp/extractor/redtube.py
index a1ca791caaa165b520f121c5969b7f0ab6173acc..14ed0edab2873cd45b79627b96af56208ab42a5e 100644 (file)
--- a/yt_dlp/extractor/redtube.py
+++ b/yt_dlp/extractor/redtube.py
@@ -1,51 +1,49 @@
-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': 'http://www.redtube.com/66418',
-        'md5': 'fc08071233725f26b8f014dba9590005',
+        'url': 'https://www.redtube.com/38864951',
+        'md5': '4fba70cbca3aefd25767ab4b523c9878',
         'info_dict': {
-            'id': '66418',
+            'id': '38864951',
             'ext': 'mp4',
-            'title': 'Sucked on a toilet',
-            'upload_date': '20110811',
-            'duration': 596,
+            'title': 'Public Sex on the Balcony in Freezing Paris! Amateur Couple LeoLulu',
+            'description': 'Watch video Public Sex on the Balcony in Freezing Paris! Amateur Couple LeoLulu on Redtube, home of free Blowjob porn videos and Blonde sex movies online. Video length: (10:46) - Uploaded by leolulu - Verified User - Starring Pornstar: Leolulu',
+            'upload_date': '20210111',
+            'timestamp': 1610343109,
+            'duration': 646,
             'view_count': int,
             'age_limit': 18,
-        }
+            'thumbnail': r're:https://\wi-ph\.rdtcdn\.com/videos/.+/.+\.jpg',
+        },
     }, {
         'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
         'only_matching': True,
     }, {
         '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'),
@@ -84,28 +82,38 @@ def _real_extract(self, url):
                 r'mediaDefinition["\']?\s*:\s*(\[.+?}\s*\])', webpage,
                 'media definitions', default='{}'),
             video_id, fatal=False)
-        if medias and isinstance(medias, list):
-            for media in medias:
+        for media in medias if isinstance(medias, list) else []:
+            format_url = urljoin('https://www.redtube.com', media.get('videoUrl'))
+            if not format_url:
+                continue
+            format_id = media.get('format')
+            quality = media.get('quality')
+            if format_id == 'hls' or (format_id == 'mp4' and not quality):
+                more_media = self._download_json(format_url, video_id, fatal=False)
+            else:
+                more_media = [media]
+            for media in more_media if isinstance(more_media, list) else []:
                 format_url = url_or_none(media.get('videoUrl'))
                 if not format_url:
                     continue
-                if media.get('format') == 'hls' or determine_ext(format_url) == 'm3u8':
+                format_id = media.get('format')
+                if format_id == 'hls' or determine_ext(format_url) == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
                         format_url, video_id, 'mp4',
-                        entry_protocol='m3u8_native', m3u8_id='hls',
+                        entry_protocol='m3u8_native', m3u8_id=format_id or 'hls',
                         fatal=False))
                     continue
                 format_id = media.get('quality')
                 formats.append({
                     'url': format_url,
+                    'ext': 'mp4',
                     'format_id': format_id,
                     'height': int_or_none(format_id),
                 })
         if not formats:
             video_url = self._html_search_regex(
                 r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
-            formats.append({'url': video_url})
-        self._sort_formats(formats)
+            formats.append({'url': video_url, 'ext': 'mp4'})
 
         thumbnail = self._og_search_thumbnail(webpage)
         upload_date = unified_strdate(self._search_regex(