[daystar] Add extractor (#2924)

Closes #2887
Authored by; hatienl0i261299

diff --git a/yt_dlp/extractor/daystar.py b/yt_dlp/extractor/daystar.py
new file mode 100644 (file)
index 0000000..4f59d90
--- /dev/null
+++ b/yt_dlp/extractor/daystar.py
@@ -0,0 +1,48 @@
+from .common import InfoExtractor
+from ..utils import js_to_json, urljoin
+
+
+class DaystarClipIE(InfoExtractor):
+    IE_NAME = 'daystar:clip'
+    _VALID_URL = r'https?://player\.daystar\.tv/(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://player.daystar.tv/0MTO2ITM',
+        'info_dict': {
+            'id': '0MTO2ITM',
+            'ext': 'mp4',
+            'title': 'The Dark World of COVID Pt. 1 | Aaron Siri',
+            'description': 'a420d320dda734e5f29458df3606c5f4',
+            'thumbnail': r're:^https?://.+\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        src_iframe = self._search_regex(r'\<iframe[^>]+src="([^"]+)"', webpage, 'src iframe')
+        webpage_iframe = self._download_webpage(
+            src_iframe.replace('player.php', 'config2.php'), video_id, headers={'Referer': src_iframe})
+
+        sources = self._parse_json(self._search_regex(
+            r'sources\:\s*(\[.*?\])', webpage_iframe, 'm3u8 source'), video_id, transform_source=js_to_json)
+
+        formats, subtitles = [], {}
+        for source in sources:
+            file = source.get('file')
+            if file and source.get('type') == 'm3u8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    urljoin('https://www.lightcast.com/embed/', file),
+                    video_id, 'mp4', fatal=False, headers={'Referer': src_iframe})
+                formats.extend(fmts)
+                subtitles = self._merge_subtitles(subtitles, subs)
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
+            'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
+            'thumbnail': self._search_regex(r'image:\s*"([^"]+)', webpage_iframe, 'thumbnail'),
+            'formats': formats,
+            'subtitles': subtitles,
+        }

diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py
index c9e1a3f4e848779040b193dec423cbe1af891aa5..caab2d8efd9c8e322a0d7f2e94ff743c0fd120ac 100644 (file)
--- a/yt_dlp/extractor/extractors.py
+++ b/yt_dlp/extractor/extractors.py
@@ -348,6 +348,7 @@
     DaumPlaylistIE,
     DaumUserIE,
 )
+from .daystar import DaystarClipIE
 from .dbtv import DBTVIE
 from .dctp import DctpTvIE
 from .deezer import (