[recurbate.com] Add recurbate extractor

yt_dlp/extractor/_extractors.py

@@ -1539,6 +1539,7 @@
     RCTIPlusTVIE,
 )
 from .rds import RDSIE
+from .recurbate import RecurbateIE
 from .redbee import ParliamentLiveUKIE, RTBFIE
 from .redbulltv import (
     RedBullTVIE,

yt_dlp/extractor/recurbate.py

@@ -0,0 +1,42 @@
+import urllib.error
+
+from .common import InfoExtractor
+from ..utils import ExtractorError, merge_dicts
+
+
+class RecurbateIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?recurbate\.com/play\.php\?video=(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://recurbate.com/play.php?video=39161415',
+        'md5': 'dd2b4ec57aa3e3572cb5cf0997fca99f',
+        'info_dict': {
+            'id': '39161415',
+            'ext': 'mp4',
+            'description': 'md5:db48d09e4d93fc715f47fd3d6b7edd51',
+            'title': 'Performer zsnicole33 show on 2022-10-25 20:23, Chaturbate Archive – Recurbate',
+            'age_limit': 18,
+        },
+        'skip': 'Website require membership.',
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        try:
+            webpage = self._download_webpage(url, video_id)
+        except ExtractorError as e:
+            if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403:
+                self.raise_login_required(msg='This video is only available for registered users; Set your authenticated browser user agent via the --user-agent parameter.', method='cookies')
+            raise
+        title = self._html_extract_title(webpage, 'title')
+        token = self._html_search_regex(r'data-token="([^"]+)"', webpage, 'token')
+
+        video_url = f'https://recurbate.com/api/get.php?video={video_id}&token={token}'
+        video_webpage = self._download_webpage(video_url, video_id)
+
+        entries = self._parse_html5_media_entries(video_url, video_webpage, video_id)
+        return merge_dicts({
+            'id': video_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'age_limit': self._rta_search(webpage),
+        }, entries[0])