From 055351fddbc0aae22c977e6e89dc4bb70b8fa231 Mon Sep 17 00:00:00 2001
From: DarkFighterLuke <luca-consoli@live.it>
Date: Sat, 26 Feb 2022 13:28:16 +0100
Subject: [PATCH] Scrape actors urls

---
 youtube_dl/extractor/sxyprn.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/youtube_dl/extractor/sxyprn.py b/youtube_dl/extractor/sxyprn.py
index d6a698061..9c30e6293 100644
--- a/youtube_dl/extractor/sxyprn.py
+++ b/youtube_dl/extractor/sxyprn.py
@@ -65,11 +65,12 @@ class SxyPrnIE(InfoExtractor):
         tags = self._search_regex(r'<meta name="keywords".+content="(?P<tags>.+)"', webpage, 'tags', group='tags').split(', ')
         uploader = self._search_regex(r'<div class=\'pes_author_div pes_edit_div transition\'.+?>.+?<span class=\'a_name\'>(?P<uploader>.+?)<', webpage, 'uploader', group='uploader')
         uploader_url = urljoin(url, self._search_regex(r'<div class=\'pes_author_div pes_edit_div transition\'.+?><a href=\'(?P<uploader_url>.+?)\'.+?<span class=\'a_name\'>(?P<uploader>.+?)<', webpage, 'uploader_url', group='uploader_url'))
-        actors_names = re.findall(r'<span>·</span><b>(?P<actor>.+?)</b>', webpage)
+        actors_data = re.findall(r'<a href=\'(?P<actor_url>.+?)\' class=\'tdn htag_rel_a\'><div class=\'htag_rel\'><span>·</span><b>(?P<actor_name>.+?)</b>', webpage)
         actors = []
-        for name in actors_names:
+        for actor_tuple in actors_data:
             actors.append({
-                'given_name': name
+                'given_name': actor_tuple[1],
+                'url': urljoin(url, actor_tuple[0])
             })
         views = int(self._search_regex(r'<div class=\'post_control_time\'>.+?</strong> (?P<views>.+) views</div>', webpage, 'views', group='views'))