From 39722f43ccf926464cf6ad88c9f740e1aac47fc4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=3D=3FUTF-8=3Fq=3FSergey=3D20M=3DE2=3D80=3DA4=3F=3D?=
 <dstftw@gmail.com>
Date: Mon, 31 May 2021 23:27:20 +0200
Subject: [PATCH] =?UTF-8?q?[eroprofile]=20Fix=20extraction=20(closes=20#23?=
 =?UTF-8?q?200,=20closes=20#23626,=20closes=20#29=E2=80=A6?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

…008)
---
 haruhi_dl/extractor/eroprofile.py | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/haruhi_dl/extractor/eroprofile.py b/haruhi_dl/extractor/eroprofile.py
index c08643a17..9ee549d77 100644
--- a/haruhi_dl/extractor/eroprofile.py
+++ b/haruhi_dl/extractor/eroprofile.py
@@ -6,7 +6,7 @@ from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlencode
 from ..utils import (
     ExtractorError,
-    unescapeHTML
+    merge_dicts,
 )
 
 
@@ -77,19 +77,15 @@ class EroProfileIE(InfoExtractor):
             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
             webpage, 'video id', default=None)
 
-        video_url = unescapeHTML(self._search_regex(
-            r'<source src="([^"]+)', webpage, 'video url'))
         title = self._html_search_regex(
-            r'Title:</th><td>([^<]+)</td>', webpage, 'title')
-        thumbnail = self._search_regex(
-            r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
-            webpage, 'thumbnail', fatal=False)
+            (r'Title:</th><td>([^<]+)</td>', r'<h1[^>]*>(.+?)</h1>'),
+            webpage, 'title')
 
-        return {
+        info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+
+        return merge_dicts(info, {
             'id': video_id,
             'display_id': display_id,
-            'url': video_url,
             'title': title,
-            'thumbnail': thumbnail,
             'age_limit': 18,
-        }
+        })