[extractor/hytale] Add extractor (#4326)

Authored by: llamasblade, pukkandan

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index daef6a83dae7875c87c901d76d5c36a6c65590e8..e0721608bd9a8cd49f68a7bd522aa2bd6acb400a 100644 (file)
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -665,6 +665,7 @@
     HungamaAlbumPlaylistIE,
 )
 from .hypem import HypemIE
+from .hytale import HytaleIE
 from .icareus import IcareusIE
 from .ichinanalive import (
     IchinanaLiveIE,

diff --git a/yt_dlp/extractor/hytale.py b/yt_dlp/extractor/hytale.py
new file mode 100644 (file)
index 0000000..0f4dcc3
--- /dev/null
+++ b/yt_dlp/extractor/hytale.py
@@ -0,0 +1,58 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import traverse_obj
+
+
+class HytaleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hytale\.com/news/\d+/\d+/(?P<id>[a-z0-9-]+)'
+    _TESTS = [{
+        'url': 'https://hytale.com/news/2021/07/summer-2021-development-update',
+        'info_dict': {
+            'id': 'summer-2021-development-update',
+            'title': 'Summer 2021 Development Update',
+        },
+        'playlist_count': 4,
+        'playlist': [{
+            'md5': '0854ebe347d233ee19b86ab7b2ead610',
+            'info_dict': {
+                'id': 'ed51a2609d21bad6e14145c37c334999',
+                'ext': 'mp4',
+                'title': 'Avatar Personalization',
+                'thumbnail': r're:https://videodelivery\.net/\w+/thumbnails/thumbnail\.jpg',
+            }
+        }]
+    }, {
+        'url': 'https://www.hytale.com/news/2019/11/hytale-graphics-update',
+        'info_dict': {
+            'id': 'hytale-graphics-update',
+            'title': 'Hytale graphics update',
+        },
+        'playlist_count': 2,
+    }]
+
+    def _real_initialize(self):
+        media_webpage = self._download_webpage(
+            'https://hytale.com/media', None, note='Downloading list of media', fatal=False) or ''
+
+        clips_json = traverse_obj(
+            self._search_json(
+                r'window\.__INITIAL_COMPONENTS_STATE__\s*=\s*\[',
+                media_webpage, 'clips json', None),
+            ('media', 'clips')) or []
+
+        self._titles = {clip.get('src'): clip.get('caption') for clip in clips_json}
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        entries = [
+            self.url_result(
+                f'https://cloudflarestream.com/{video_hash}/manifest/video.mpd?parentOrigin=https%3A%2F%2Fhytale.com',
+                title=self._titles.get(video_hash), url_transparent=True)
+            for video_hash in re.findall(
+                r'<stream\s+class\s*=\s*"ql-video\s+cf-stream"\s+src\s*=\s*"([a-f0-9]{32})"',
+                webpage)
+        ]
+
+        return self.playlist_result(entries, playlist_id, self._og_search_title(webpage))