From 76144ccf0f4483e5e162080a2e6cbabcb24dda57 Mon Sep 17 00:00:00 2001
From: dirkf <fieldhouse@gmx.net>
Date: Sat, 26 Feb 2022 13:03:51 +0000
Subject: [PATCH] [Filmarkivet] Add extractor for Filmarkivet.se

https://github.com/yt-dlp/yt-dlp/issues/2885
---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/filmark.py    | 54 ++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+)
 create mode 100644 youtube_dl/extractor/filmark.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 50b7cb4a0..5d10b91f3 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -372,6 +372,7 @@ from .filmon import (
     FilmOnIE,
     FilmOnChannelIE,
 )
+from .filmark import FilmarkIE
 from .filmweb import FilmwebIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
diff --git a/youtube_dl/extractor/filmark.py b/youtube_dl/extractor/filmark.py
new file mode 100644
index 000000000..2eca90b52
--- /dev/null
+++ b/youtube_dl/extractor/filmark.py
@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    merge_dicts,
+    parse_iso8601,
+)
+
+
+class FilmarkIE(InfoExtractor):
+    IE_NAME = 'Filmarkivet.se'
+    _VALID_URL = r'https?://www\.filmarkivet\.se/movies/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.filmarkivet.se/movies/paris-d-moll/',
+        'md5': 'df02cadc719dcc63d43288366f037754',
+        'info_dict': {
+            'id': 'paris-d-moll',
+            'ext': 'mp4',
+            'upload_date': '20200602',
+            'title': 'Paris d-moll',
+            'description': 'md5:319e37ea5542293db37e1e13072fe330',
+            'timestamp': 1591092663,
+        }
+    },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = (
+            self._html_search_regex(r'<title\b[^>]*>\s*([^<]*)</title\b', webpage, '<title>', fatal=False)
+            or self._og_search_title(webpage, fatal=False)
+            or self._html_search_meta('twitter:title', webpage, default=''))
+        title = re.split(r'(\s*-)?\s*[Ff]ilmarkivet', title, 1)[0] or self._generic_title(url)
+
+        ld_json_info = self._search_json_ld(webpage, video_id, default={})
+
+        jwp_info = self._extract_jwplayer_data(webpage, video_id, require_title=False)
+
+        description = (
+            self._og_search_description(webpage)
+            or self._html_search_meta('twitter:description', webpage, default=None))
+        timestamp = parse_iso8601(self._og_search_property('updated_time', webpage, default=None))
+
+        return merge_dicts(
+            jwp_info, ld_json_info, {
+                'title': title,
+                'description': description,
+                'timestamp': timestamp,
+            })