[ie/loom] Add extractors (#8686)

[yt-dlp.git] / yt_dlp / extractor / mixch.py

diff --git a/yt_dlp/extractor/mixch.py b/yt_dlp/extractor/mixch.py
index a99ddd172e0580e737602be5d1702e27b37b1761..4be6947289c4dad7f4fa1df47bf666999e1c74eb 100644 (file)
--- a/yt_dlp/extractor/mixch.py
+++ b/yt_dlp/extractor/mixch.py
@@ -1,17 +1,12 @@
-from __future__ import unicode_literals
-
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    traverse_obj,
-)
+from ..utils import UserNotLive, traverse_obj
 
 
 class MixchIE(InfoExtractor):
     IE_NAME = 'mixch'
     _VALID_URL = r'https?://(?:www\.)?mixch\.tv/u/(?P<id>\d+)'
 
-    TESTS = [{
+    _TESTS = [{
         'url': 'https://mixch.tv/u/16236849/live',
         'skip': 'don\'t know if this live persists',
         'info_dict': {
@@ -35,7 +30,7 @@ def _real_extract(self, url):
         initial_js_state = self._parse_json(self._search_regex(
             r'(?m)^\s*window\.__INITIAL_JS_STATE__\s*=\s*(\{.+?\});\s*$', webpage, 'initial JS state'), video_id)
         if not initial_js_state.get('liveInfo'):
-            raise ExtractorError('Livestream has ended.', expected=True)
+            raise UserNotLive(video_id=video_id)
 
         return {
             'id': video_id,
@@ -47,9 +42,40 @@ def _real_extract(self, url):
             'uploader_id': video_id,
             'formats': [{
                 'format_id': 'hls',
-                'url': traverse_obj(initial_js_state, ('liveInfo', 'hls')) or 'https://d1hd0ww6piyb43.cloudfront.net/hls/torte_%s.m3u8' % video_id,
+                'url': (traverse_obj(initial_js_state, ('liveInfo', 'hls'))
+                        or f'https://d1hd0ww6piyb43.cloudfront.net/hls/torte_{video_id}.m3u8'),
                 'ext': 'mp4',
                 'protocol': 'm3u8',
             }],
             'is_live': True,
         }
+
+
+class MixchArchiveIE(InfoExtractor):
+    IE_NAME = 'mixch:archive'
+    _VALID_URL = r'https?://(?:www\.)?mixch\.tv/archive/(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'https://mixch.tv/archive/421',
+        'skip': 'paid video, no DRM. expires at Jan 23',
+        'info_dict': {
+            'id': '421',
+            'title': '96NEKO SHOW TIME',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        html5_videos = self._parse_html5_media_entries(
+            url, webpage.replace('video-js', 'video'), video_id, 'hls')
+        if not html5_videos:
+            self.raise_login_required(method='cookies')
+        infodict = html5_videos[0]
+        infodict.update({
+            'id': video_id,
+            'title': self._html_search_regex(r'class="archive-title">(.+?)</', webpage, 'title')
+        })
+
+        return infodict