From 2415e66f889f38503b73e8ebc5f43ca342390e5c Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel.baumann@progress-linux.org>
Date: Mon, 15 Apr 2024 18:49:24 +0200
Subject: Adding upstream version 2024.03.10.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
---
 yt_dlp/extractor/movingimage.py | 50 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)
 create mode 100644 yt_dlp/extractor/movingimage.py

(limited to 'yt_dlp/extractor/movingimage.py')

diff --git a/yt_dlp/extractor/movingimage.py b/yt_dlp/extractor/movingimage.py
new file mode 100644
index 0000000..cdd8ba4
--- /dev/null
+++ b/yt_dlp/extractor/movingimage.py
@@ -0,0 +1,50 @@
+from .common import InfoExtractor
+from ..utils import (
+    unescapeHTML,
+    parse_duration,
+)
+
+
+class MovingImageIE(InfoExtractor):
+    _VALID_URL = r'https?://movingimage\.nls\.uk/film/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://movingimage.nls.uk/film/3561',
+        'md5': '4caa05c2b38453e6f862197571a7be2f',
+        'info_dict': {
+            'id': '3561',
+            'ext': 'mp4',
+            'title': 'SHETLAND WOOL',
+            'description': 'md5:c5afca6871ad59b4271e7704fe50ab04',
+            'duration': 900,
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = self._extract_m3u8_formats(
+            self._html_search_regex(r'file\s*:\s*"([^"]+)"', webpage, 'm3u8 manifest URL'),
+            video_id, ext='mp4', entry_protocol='m3u8_native')
+
+        def search_field(field_name, fatal=False):
+            return self._search_regex(
+                r'<span\s+class="field_title">%s:</span>\s*<span\s+class="field_content">([^<]+)</span>' % field_name,
+                webpage, 'title', fatal=fatal)
+
+        title = unescapeHTML(search_field('Title', fatal=True)).strip('()[]')
+        description = unescapeHTML(search_field('Description'))
+        duration = parse_duration(search_field('Running time'))
+        thumbnail = self._search_regex(
+            r"image\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'thumbnail': thumbnail,
+        }
-- 
cgit v1.2.3