Merge f2767e2ce0 into f3411af12e

Authored by: megumintyan

yt_dlp/extractor/_extractors.py

@@ -370,6 +370,7 @@
 from .chilloutzone import ChilloutzoneIE
 from .chzzk import (
     CHZZKLiveIE,
+    CHZZKChannelIE,
     CHZZKVideoIE,
 )
 from .cinemax import CinemaxIE

yt_dlp/extractor/chzzk.py

@@ -87,6 +87,91 @@ def _real_extract(self, url):
         }
 
 
+def _make_vod_result(data):
+    assert isinstance(data, dict)
+    if not data.get('videoId'):
+        return
+    return {
+        '_type': 'url_transparent',
+        'id': data.get('videoId'),
+        'title': data.get('videoTitle'),
+        'url': f'https://chzzk.naver.com/video/{data.get("videoNo")}',
+        'thumbnail': data.get('thumbnailImageUrl'),
+        'timestamp': data.get('publishDateAt'),
+        'view_count': data.get('readCount'),
+        'duration': data.get('duration'),
+        'age_limit': 19 if data.get('adult') else 0,
+        'was_live': True if data.get('videoType') == 'REPLAY' else False,
+    }
+
+
+class CHZZKChannelIE(InfoExtractor):
+    IE_NAME = 'chzzk:channel'
+    _VALID_URL = r'https?://chzzk\.naver\.com/(?P<id>[\da-f]{32})'
+    _TESTS = [{
+        'note': 'Both video and replay included',
+        'url': 'https://chzzk.naver.com/68f895c59a1043bc5019b5e08c83a5c5',
+        'info_dict': {
+            'id': '68f895c59a1043bc5019b5e08c83a5c5',
+            'channel_id': '68f895c59a1043bc5019b5e08c83a5c5',
+            'description': '나는 머찐 라디유 나는 머찐 라디유' * 26 + '나는 라디유',
+            'channel': '라디유radiyu',
+            'title': '라디유radiyu',
+            'channel_is_verified': False,
+        },
+        'playlist_mincount': 4,
+    }, {
+        'note': 'Video list paging',
+        'url': 'https://chzzk.naver.com/2d4aa2f79b0a397d032c479ef1b37a67',
+        'info_dict': {
+            'id': '2d4aa2f79b0a397d032c479ef1b37a67',
+            'channel_id': '2d4aa2f79b0a397d032c479ef1b37a67',
+            'description': '',
+            'channel': '진짜후추',
+            'title': '진짜후추',
+            'channel_is_verified': False,
+        },
+        'playlist_mincount': 86,
+    }]
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+        # even if channel got banned, the video list is still available. but downloading videos leads to error
+        channel_meta = self._download_json(
+            f'https://api.chzzk.naver.com/service/v1/channels/{channel_id}', channel_id,
+            note='Downloading channel info', errnote='Unable to download channel info')
+        if channel_meta.get('code') != 200:
+            raise ExtractorError('The channel is not available: %s(%s)' % (
+                channel_meta.get("message"), channel_meta.get("code")), expected=True)
+
+        channel_meta = channel_meta.get('content')
+        if not channel_meta or not channel_meta.get('channelId'):
+            raise ExtractorError('The channel does not exist', expected=True)
+
+        total_count = 0
+        videos = []
+        current_count = 0
+        while current_count <= total_count:
+            videos_page = self._download_json(
+                f'https://api.chzzk.naver.com/service/v1/channels/{channel_id}/videos', channel_meta['channelName'],
+                query={'sortType': 'LATEST', 'pagingType': 'PAGE', 'size': 18, 'videoType': '', 'page': current_count},
+                note='Downloading videos page(%s/%s)' % (current_count + 1, total_count + 1), errnote='Unable to download videos page')
+            if videos_page.get('code') != 200:
+                raise ExtractorError('Unable to download videos page: %s(%s){videos_page.get("message")}' % (
+                    videos_page.get("message"), videos_page.get("code")), expected=True)
+            videos_page = videos_page['content']
+            videos.extend(map(_make_vod_result, videos_page['data']))
+            total_count = videos_page['totalPages']
+            current_count += 1
+        if len(videos) != total_count:
+            self.to_screen('Warning: The total count of videos is not equal to the actual count: %s != %s' % (len(videos), total_count))
+
+        return self.playlist_result(
+            videos, channel_id, channel_meta['channelName'], channel_meta['channelDescription'],
+            channel=channel_meta['channelName'], channel_id=channel_id, channel_is_verified=channel_meta['verifiedMark'],
+        )
+
+
 class CHZZKVideoIE(InfoExtractor):
     IE_NAME = 'chzzk:video'
     _VALID_URL = r'https?://chzzk\.naver\.com/video/(?P<id>\d+)'

yt_dlp/extractor/matchtv.py

@@ -1,51 +1,35 @@
-import random
-
 from .common import InfoExtractor
-from ..utils import xpath_text
 
 
 class MatchTVIE(InfoExtractor):
-    _VALID_URL = r'https?://matchtv\.ru(?:/on-air|/?#live-player)'
+    _VALID_URL = [
+        r'https?://matchtv\.ru/on-air/?(?:$|[?#])',
+        r'https?://video\.matchtv\.ru/iframe/channel/106/?(?:$|[?#])',
+    ]
     _TESTS = [{
-        'url': 'http://matchtv.ru/#live-player',
+        'url': 'http://matchtv.ru/on-air/',
         'info_dict': {
             'id': 'matchtv-live',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': r're:^Матч ТВ - Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
-            'is_live': True,
+            'live_status': 'is_live',
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'http://matchtv.ru/on-air/',
+        'url': 'https://video.matchtv.ru/iframe/channel/106',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = 'matchtv-live'
-        video_url = self._download_json(
-            'http://player.matchtv.ntvplus.tv/player/smil', video_id,
-            query={
-                'ts': '',
-                'quality': 'SD',
-                'contentId': '561d2c0df7159b37178b4567',
-                'sign': '',
-                'includeHighlights': '0',
-                'userId': '',
-                'sessionId': random.randint(1, 1000000000),
-                'contentType': 'channel',
-                'timeShift': '0',
-                'platform': 'portal',
-            },
-            headers={
-                'Referer': 'http://player.matchtv.ntvplus.tv/embed-player/NTVEmbedPlayer.swf',
-            })['data']['videoUrl']
-        f4m_url = xpath_text(self._download_xml(video_url, video_id), './to')
-        formats = self._extract_f4m_formats(f4m_url, video_id)
+        webpage = self._download_webpage('https://video.matchtv.ru/iframe/channel/106', video_id)
+        video_url = self._html_search_regex(
+            r'data-config="config=(https?://[^?"]+)[?"]', webpage, 'video URL').replace('/feed/', '/media/') + '.m3u8'
         return {
             'id': video_id,
             'title': 'Матч ТВ - Прямой эфир',
             'is_live': True,
-            'formats': formats,
+            'formats': self._extract_m3u8_formats(video_url, video_id, 'mp4', live=True),
         }