Update and fix smotrim.ru extractor (see description)

- Added support for links with 'channel' type - Extract json info from api's json dictionary - Added thumbnail url - Fixed outdated broken links in _TESTS - Get many video formats from m3u8 playlist
2 weeks ago · 60b582751d
parent 71f30921a2
commit 60b582751d
1 changed files with 108 additions and 55 deletions
--- a/yt_dlp/extractor/smotrim.py
+++ b/yt_dlp/extractor/smotrim.py
@ -1,65 +1,118 @@
-from .common import InfoExtractor
-from ..utils import ExtractorError
+import re
+
+from yt_dlp.extractor.common import InfoExtractor
+from yt_dlp.utils import ExtractorError


 class SmotrimIE(InfoExtractor):
-    _VALID_URL = r'https?://smotrim\.ru/(?P<type>brand|video|article|live)/(?P<id>[0-9]+)'
-    _TESTS = [{  # video
-        'url': 'https://smotrim.ru/video/1539617',
-        'md5': 'b1923a533c8cab09679789d720d0b1c5',
-        'info_dict': {
-            'id': '1539617',
-            'ext': 'mp4',
-            'title': 'Полиглот. Китайский с нуля за 16 часов! Урок №16',
-            'description': '',
+    _VALID_URL = r"https?://smotrim\.ru/(?P<type>brand|video|article|live|channel)/(?P<id>[0-9]+)"
+    _TESTS = [
+        {
+            "url": "https://smotrim.ru/video/3003613",
+            "info_dict": {
+                "id": "3003613",
+                "ext": "mp4",
+                "title": "Погода. на 2 августа 2025 года",
+                "thumbnail": "https://cdn-st2.smotrim.ru/vh/pictures/xw/635/545/7.jpg",
+            },
+            "add_ie": ["RUTV"],
+        },
+        {
+            "url": "https://smotrim.ru/article/4609632",
+            "info_dict": {
+                "id": "3000761",
+                "ext": "mp4",
+                "title": "Новости культуры. Ольга Любимова провела рабочую встречу в Еврейской автономной области",
+                "thumbnail": "https://cdn-st2.smotrim.ru/vh/pictures/xw/638/386/6.jpg",
+            },
+            "add_ie": ["RUTV"],
        },
-        'add_ie': ['RUTV'],
-    }, {  # article (geo-restricted? plays fine from the US and JP)
-        'url': 'https://smotrim.ru/article/2813445',
-        'md5': 'e0ac453952afbc6a2742e850b4dc8e77',
-        'info_dict': {
-            'id': '2431846',
-            'ext': 'mp4',
-            'title': 'Новости культуры. Съёмки первой программы "Большие и маленькие"',
-            'description': 'md5:94a4a22472da4252bf5587a4ee441b99',
+        {
+            "url": "https://smotrim.ru/brand/64356",
+            "info_dict": {
+                "id": "2885093",
+                "ext": "mp4",
+                "title": "Большие и маленькие. 6-й сезон 8-й выпуск",
+                "thumbnail": "https://cdn-st2.smotrim.ru/vh/pictures/xw/527/187/3.jpg",
+            },
+            "add_ie": ["RUTV"],
        },
-        'add_ie': ['RUTV'],
-    }, {  # brand, redirect
-        'url': 'https://smotrim.ru/brand/64356',
-        'md5': '740472999ccff81d7f6df79cecd91c18',
-        'info_dict': {
-            'id': '2354523',
-            'ext': 'mp4',
-            'title': 'Большие и маленькие. Лучшее. 4-й выпуск',
-            'description': 'md5:84089e834429008371ea41ea3507b989',
+        {  # GEO RESTRICTED
+            "url": "https://smotrim.ru/live/19201",
+            "info_dict": {
+                "id": "381308c7-a066-4c4f-9656-83e2e792a7b4",
+                "ext": "mp4",
+                "title": "Россия К",
+                "thumbnail": "https://cdn-st2.smotrim.ru/vh/pictures/xw/441/085/7.png",
+            },
+            "add_ie": ["RUTV"],
        },
-        'add_ie': ['RUTV'],
-    }, {  # live
-        'url': 'https://smotrim.ru/live/19201',
-        'info_dict': {
-            'id': '19201',
-            'ext': 'mp4',
-            # this looks like a TV channel name
-            'title': 'Россия Культура. Прямой эфир',
-            'description': '',
+        {  # GEO RESTRICTED, REDIRECT FROM live, CANONICAL FOR live urls
+            "url": "https://smotrim.ru/channel/4",
+            "info_dict": {
+                "id": "4",
+                "ext": "mp4",
+                "title": "Россия К",
+                "thumbnail": "https://cdn-st2.smotrim.ru/vh/pictures/xw/441/085/7.png",
+            },
+            "add_ie": ["RUTV"],
        },
-        'add_ie': ['RUTV'],
-    }]
+    ]

    def _real_extract(self, url):
-        video_id, typ = self._match_valid_url(url).group('id', 'type')
-        rutv_type = 'video'
-        if typ not in ('video', 'live'):
-            webpage = self._download_webpage(url, video_id, f'Resolving {typ} link')
-            # there are two cases matching regex:
-            # 1. "embedUrl" in JSON LD (/brand/)
-            # 2. "src" attribute from iframe (/article/)
-            video_id = self._search_regex(
-                r'"https://player.smotrim.ru/iframe/video/id/(?P<video_id>\d+)/',
-                webpage, 'video_id', default=None)
+        video_id, type = self._match_valid_url(url).group("id", "type")
+        webpage = self._download_webpage(url, video_id, f"Resolving {type} link")
+        iframe_url = self._search_regex(
+            r'<iframe\b[^>]+\bsrc=["\'](https?://player\.smotrim\.ru/iframe/[^"\']+)',
+            webpage,
+            "iframe URL",
+        )
+        if type in {"live", "channel"}:
+            # iframe_url = "https://player.smotrim.ru/iframe/live/uid/381308c7-a066-4c4f-9656-83e2e792a7b4/showZoomBtn/false/isPlay/true/mute/true/sid/smotrim_rk/"
+            video_id = re.search(
+                r"(?P<video_id>[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})",
+                iframe_url,
+            )
            if not video_id:
-                raise ExtractorError('There are no video in this page.', expected=True)
-        elif typ == 'live':
-            rutv_type = 'live'
-
-        return self.url_result(f'https://player.vgtrk.com/iframe/{rutv_type}/id/{video_id}')
+                raise ExtractorError(
+                    "There are no player uuid in this page.", expected=True
+                )
+            video_id = video_id.group("video_id")
+            jsondata_url = (
+                f"https://player.smotrim.ru/iframe/datalive/uid/{video_id}/sid/smotrim"
+            )
+        else:
+            # iframe_url = "https://player.smotrim.ru/iframe/video/id/3000761/sid/smotrim/isPlay/true/mute/true/?acc_video_id=3204061"
+            video_id = re.search(
+                r"^https?://player\.smotrim\.ru/iframe/video/id/(?P<video_id>\d+)/sid/",
+                iframe_url,
+            )
+            if not video_id:
+                raise ExtractorError(
+                    "There are no player id in this page.", expected=True
+                )
+            video_id = video_id.group("video_id")
+            jsondata_url = (
+                f"https://player.smotrim.ru/iframe/datavideo/id/{video_id}/sid/smotrim"
+            )
+        try:
+            json_info = self._download_json(
+                jsondata_url, video_id, "Downloading player config JSON metadata"
+            )
+        except Exception as e:
+            raise ExtractorError(str(e), expected=True)
+        m3u8_url = json_info["data"]["playlist"]["medialist"][0]["sources"]["m3u8"][
+            "auto"
+        ]
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            m3u8_url, video_id, "mp4", m3u8_id="hls"
+        )
+        return {
+            "id": video_id,
+            "title": json_info["data"]["playlist"]["medialist"][0]["title"],
+            "thumbnail": json_info["data"]["playlist"]["medialist"][0]["pictures"][
+                "16:9"
+            ],
+            "formats": formats,
+            "subtitles": subtitles,
+        }