Merge 38741ad6e5 into eb15fd5a32

Closes #3937
Authored by: krichbanana, pzhlkj6612

Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>

yt_dlp/extractor/_extractors.py

@@ -580,6 +580,7 @@ from .eagleplatform import (
 )
 from .ebaumsworld import EbaumsWorldIE
 from .ebay import EbayIE
+from .echo360 import Echo360IE
 from .egghead import (
     EggheadCourseIE,
     EggheadLessonIE,
@@ -946,6 +947,10 @@ from .kaltura import KalturaIE
 from .kankanews import KankaNewsIE
 from .karaoketv import KaraoketvIE
 from .kelbyone import KelbyOneIE
+from .kenh14 import (
+    Kenh14PlaylistIE,
+    Kenh14VideoIE,
+)
 from .khanacademy import (
     KhanAcademyIE,
     KhanAcademyUnitIE,

yt_dlp/extractor/chaturbate.py

@@ -79,7 +79,7 @@ class ChaturbateIE(InfoExtractor):
             'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
         }
 
-    def _extract_from_webpage(self, video_id, tld):
+    def _extract_from_html(self, video_id, tld):
         webpage = self._download_webpage(
             f'https://chaturbate.{tld}/{video_id}/', video_id,
             headers=self.geo_verification_headers(), impersonate=True)
@@ -151,4 +151,4 @@ class ChaturbateIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id, tld = self._match_valid_url(url).group('id', 'tld')
-        return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld)
+        return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld)

yt_dlp/extractor/echo360.py

@@ -0,0 +1,90 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext, parse_duration, traverse_obj, update_url
+
+
+class Echo360IE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?P<host>echo360\.(?:ca|net\.au|org|org\.au|org\.uk))/
+        media/(?P<id>[\da-fA-F]{8}-(?:[\da-fA-F]{4}-){3}[\da-fA-F]{12})/public
+    '''
+
+    _TESTS = [
+        {
+            'url': 'https://echo360.org.uk/media/1d8392aa-a3e7-4e78-94cf-b6532c27208c/public',
+            'info_dict': {
+                'id': '3c7ae6e0-fa19-432d-aa21-c283b4276f2a',
+                'ext': 'mp4',
+                'title': '3-4 Force + moment + mechanics.mp4',
+                'duration': 4731.888,
+            },
+            'params': {'skip_download': 'm3u8'}
+        },
+        {
+            'url': 'https://echo360.net.au/media/f04960a9-2efc-4b63-87b5-72e629081d15/public',
+            'info_dict': {
+                'id': '6098a147-2d65-40f3-b9e9-a0204afe450c',
+                'ext': 'mp4',
+                'title': 'EXSC634_Online_Workshop_Week_4.mp4',
+                'duration': 6659.72,
+            },
+            'params': {'skip_download': 'm3u8'}
+        },
+    ]
+
+    def _call_api(self, host, video_id, media_id, session_token, **kwargs):
+        return self._download_json(
+            f'https://{host}/api/ui/echoplayer/public-links/{video_id}/media/{media_id}/player-properties',
+            video_id, headers={'Authorization': f'Bearer {session_token}'}, **kwargs)
+
+    def _get_query_string(self, uri, query_strings):
+        uri_base = update_url(uri, query=None, fragment=None)
+        for query_string in query_strings:
+            try:
+                if re.match(query_string['uriPattern'], uri_base):
+                    return query_string['queryString']
+            except re.error as re_error:
+                self.report_warning(f'Error in query string pattern `{re_error.pattern}`: {re_error.msg}')
+        return None
+
+    def _parse_mediapackage(self, video):
+        video_id = video['playableAudioVideo']['mediaId']
+        query_strings = traverse_obj(video, ('sourceQueryStrings', 'queryStrings', ...))
+
+        formats = []
+        for track in traverse_obj(video, ('playableAudioVideo', 'playableMedias', lambda _, v: v['uri'])):
+            href = update_url(track['uri'], query=self._get_query_string(track['uri'], query_strings))
+            if track.get('isHls') or determine_ext(href) == 'm3u8':
+                hls_formats = self._extract_m3u8_formats(
+                    href, video_id, live=track.get('isLive'), m3u8_id='hls', fatal=False)
+
+                for hls_format in hls_formats:
+                    query_string = self._get_query_string(hls_format['url'], query_strings)
+                    hls_format['extra_param_to_segment_url'] = query_string
+                    hls_format['url'] = update_url(hls_format['url'], query=query_string)
+
+                formats.extend(hls_formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': video.get('mediaName'),
+            'duration': traverse_obj(video, ('playableAudioVideo', 'duration', {parse_duration})),
+        }
+
+    def _real_extract(self, url):
+        host, video_id = self._match_valid_url(url).group('host', 'id')
+        webpage = self._download_webpage(url, video_id)
+
+        player_config = self._search_json(
+            r'Echo\["mediaPlayerBootstrapApp"\]\("', webpage, 'player config',
+            video_id, transform_source=lambda x: x.replace(R'\"', '"'))
+
+        urlh = self._request_webpage(
+            f'https://{host}/api/ui/sessions/{player_config["sessionId"]}',
+            video_id, 'Open video session', 'Unable to open video session')
+
+        return self._parse_mediapackage(self._call_api(
+            host, player_config.get('shareLinkId') or player_config['publicLinkId'],
+            player_config['mediaId'], urlh.headers['Token'])['data'])

yt_dlp/extractor/kenh14.py

@@ -0,0 +1,160 @@
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_attribute,
+    get_elements_html_by_class,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    remove_start,
+    strip_or_none,
+    unescapeHTML,
+    update_url,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class Kenh14VideoIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P<id>[0-9]+)\.chn'
+    _TESTS = [{
+        'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
+        'md5': '1ed67f9c3a1e74acf15db69590cf6210',
+        'info_dict': {
+            'id': '316173',
+            'ext': 'mp4',
+            'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
+            'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
+            'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
+            'tags': [],
+            'uploader': 'Unbox Therapy',
+            'upload_date': '20220517',
+            'view_count': int,
+            'duration': 722.86,
+            'timestamp': 1652764468,
+        },
+    }, {
+        'url': 'https://video.kenh14.vn/video-316174.chn',
+        'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd',
+        'info_dict': {
+            'id': '316174',
+            'ext': 'mp4',
+            'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu',
+            'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc',
+            'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
+            'tags': [],
+            'upload_date': '20220517',
+            'view_count': int,
+            'duration': 70.04,
+            'timestamp': 1652766021,
+        },
+    }, {
+        'url': 'https://video.kenh14.vn/0-344740.chn',
+        'md5': 'b843495d5e728142c8870c09b46df2a9',
+        'info_dict': {
+            'id': '344740',
+            'ext': 'mov',
+            'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi',
+            'description': 'md5:2a2dbb4a7397169fb21ee68f09160497',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$',
+            'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'],
+            'uploader': 'Quang Vũ',
+            'upload_date': '20241024',
+            'view_count': int,
+            'duration': 198.88,
+            'timestamp': 1729741590,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '')
+        direct_url = attrs['data-vid']
+
+        metadata = self._download_json(
+            'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format(
+                remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False)
+
+        formats = [{'url': f'https://{direct_url}', 'format_id': 'http', 'quality': 1}]
+        subtitles = {}
+        video_data = self._download_json(
+            f'https://{direct_url}.json', video_id, note='Downloading video data', fatal=False)
+        if hls_url := traverse_obj(video_data, ('hls', {url_or_none})):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                hls_url, video_id, m3u8_id='hls', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+        if dash_url := traverse_obj(video_data, ('mpd', {url_or_none})):
+            fmts, subs = self._extract_mpd_formats_and_subtitles(
+                dash_url, video_id, mpd_id='dash', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+
+        return {
+            **traverse_obj(metadata, {
+                'duration': ('duration', {parse_duration}),
+                'uploader': ('author', {strip_or_none}),
+                'timestamp': ('uploadtime', {parse_iso8601(delimiter=' ')}),
+                'view_count': ('views', {int_or_none}),
+            }),
+            'id': video_id,
+            'title': (
+                traverse_obj(metadata, ('title', {strip_or_none}))
+                or clean_html(self._og_search_title(webpage))
+                or clean_html(get_element_by_class('vdbw-title', webpage))),
+            'formats': formats,
+            'subtitles': subtitles,
+            'description': (
+                clean_html(self._og_search_description(webpage))
+                or clean_html(get_element_by_class('vdbw-sapo', webpage))),
+            'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')),
+            'tags': traverse_obj(self._html_search_meta('keywords', webpage), (
+                {lambda x: x.split(';')}, ..., filter)),
+        }
+
+
+class Kenh14PlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P<id>[0-9]+)\.chn'
+    _TESTS = [{
+        'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
+        'info_dict': {
+            'id': '71',
+            'title': 'Trần Tình (Naked love) mùa 2',
+            'description': 'md5:e9522339304956dea931722dd72eddb2',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
+        },
+        'playlist_count': 9,
+    }, {
+        'url': 'https://video.kenh14.vn/playlist/0-72.chn',
+        'info_dict': {
+            'id': '72',
+            'title': 'Lau Lại Đầu Từ',
+            'description': 'Cùng xem xưa và nay có gì khác biệt nhé!',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
+        },
+        'playlist_count': 6,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        category_detail = get_element_by_class('category-detail', webpage) or ''
+        embed_info = traverse_obj(
+            self._yield_json_ld(webpage, playlist_id),
+            (lambda _, v: v['name'] and v['alternateName'], any)) or {}
+
+        return self.playlist_from_matches(
+            get_elements_html_by_class('video-item', webpage), playlist_id,
+            (clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
+            getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']),
+            ie=Kenh14VideoIE, playlist_description=(
+                clean_html(get_element_by_class('description', category_detail))
+                or unescapeHTML(embed_info.get('alternateName'))),
+            thumbnail=traverse_obj(
+                self._og_search_thumbnail(webpage),
+                ({url_or_none}, {update_url(query=None)})))