Merge 87c8703f90 into eb15fd5a32

[ie/kenh14] Add extractor (#3996 )
Closes #3937 Authored by: krichbanana, pzhlkj6612 Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>
2024-11-25 00:31:26 +01:00 · 2024-11-17 21:33:19 +05:30 · 2024-11-17 14:12:26 +00:00 · 2024-11-17 13:32:12 +01:00 · 2023-06-25 10:47:04 +02:00 · 2023-01-12 21:50:40 +01:00
5 changed files with 222 additions and 54 deletions
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@ -946,6 +946,10 @@ 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,
@ -1665,10 +1669,8 @@ from .rai import (
    RaiIE,
    RaiNewsIE,
    RaiPlayIE,
-    RaiPlayLiveIE,
    RaiPlayPlaylistIE,
    RaiPlaySoundIE,
-    RaiPlaySoundLiveIE,
    RaiPlaySoundPlaylistIE,
    RaiSudtirolIE,
 )
--- a/yt_dlp/extractor/chaturbate.py
+++ b/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)
--- a/yt_dlp/extractor/kenh14.py
+++ b/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)})))
--- a/yt_dlp/extractor/la7.py
+++ b/yt_dlp/extractor/la7.py
@ -7,10 +7,11 @@ from ..utils import float_or_none, int_or_none, parse_duration, unified_strdate

 class LA7IE(InfoExtractor):
    IE_NAME = 'la7.it'
-    _VALID_URL = r'''(?x)https?://(?:
-        (?:www\.)?la7\.it/([^/]+)/(?:rivedila7|video|news)/|
-        tg\.la7\.it/repliche-tgla7\?id=
-    )(?P<id>.+)'''
+    _VALID_URL = [
+        r'https?://(?:www\.)?la7\.it/[^/]+/(?:rivedila7|video|news)/.+-(?P<id>\d{5,})',
+        r'https?://tg\.la7\.it/repliche-tgla7\?id=(?P<id>\d{5,})',
+        r'https?://tg\.la7\.it(?:/[^/]+)+-(?P<id>\d{5,})'
+    ]

    _TESTS = [{
        # single quality video
@ -39,7 +40,7 @@ class LA7IE(InfoExtractor):
            'formats': 'count:8',
        },
    }, {
-        'url': 'http://www.la7.it/omnibus/rivedila7/omnibus-news-02-07-2016-189077',
+        'url': 'https://tg.la7.it/repliche-tgla7?id=464601',
        'only_matching': True,
    }]
    _HOST = 'https://awsvodpkg.iltrovatore.it'
--- a/yt_dlp/extractor/rai.py
+++ b/yt_dlp/extractor/rai.py
@ -10,6 +10,7 @@ from ..utils import (
    filter_dict,
    int_or_none,
    join_nonempty,
+    make_archive_id,
    parse_duration,
    remove_start,
    strip_or_none,
@ -250,7 +251,10 @@ class RaiBaseIE(InfoExtractor):


 class RaiPlayIE(RaiBaseIE):
-    _VALID_URL = rf'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)'
+    _VALID_URL = [
+        rf'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)',
+        r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))',
+    ]
    _TESTS = [{
        'url': 'https://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
        'md5': '8970abf8caf8aef4696e7b1f2adfc696',
@ -321,6 +325,25 @@ class RaiPlayIE(RaiBaseIE):
            'timestamp': 1348495020,
            'upload_date': '20120924',
        },
+    }, {
+        # live stream
+        'url': 'https://www.raiplay.it/dirette/rainews24',
+        'info_dict': {
+            'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
+            'display_id': 'rainews24',
+            'ext': 'mp4',
+            'title': r're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497',
+            'uploader': 'Rai News 24',
+            'creator': 'Rai News 24',
+            'is_live': True,
+            'live_status': 'is_live',
+            'upload_date': '20090502',
+            'timestamp': 1241276220,
+        },
+        'params': {
+            'skip_download': True,
+        },
    }, {
        'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
        'only_matching': True,
@ -354,6 +377,7 @@ class RaiPlayIE(RaiBaseIE):
        return {
            'id': remove_start(media.get('id'), 'ContentItem-') or video_id,
            'display_id': video_id,
+            '_old_archive_ids': [make_archive_id('RaiPlayLive', video_id)] if not re.match(RaiBaseIE._UUID_RE, video_id) else None,
            'title': media.get('name'),
            'alt_title': strip_or_none(alt_title or None),
            'description': media.get('description'),
@ -377,28 +401,6 @@ class RaiPlayIE(RaiBaseIE):
        }


-class RaiPlayLiveIE(RaiPlayIE):  # XXX: Do not subclass from concrete IE
-    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
-    _TESTS = [{
-        'url': 'http://www.raiplay.it/dirette/rainews24',
-        'info_dict': {
-            'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
-            'display_id': 'rainews24',
-            'ext': 'mp4',
-            'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
-            'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497',
-            'uploader': 'Rai News 24',
-            'creator': 'Rai News 24',
-            'is_live': True,
-            'live_status': 'is_live',
-            'upload_date': '20090502',
-            'timestamp': 1241276220,
-            'formats': 'count:3',
-        },
-        'params': {'skip_download': True},
-    }]
-
-
 class RaiPlayPlaylistIE(InfoExtractor):
    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))(?:/(?P<extra_id>[^?#&]+))?'
    _TESTS = [{
@ -463,7 +465,10 @@ class RaiPlayPlaylistIE(InfoExtractor):


 class RaiPlaySoundIE(RaiBaseIE):
-    _VALID_URL = rf'(?P<base>https?://(?:www\.)?raiplaysound\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)'
+    _VALID_URL = [
+        rf'(?P<base>https?://(?:www\.)?raiplaysound\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)',
+        r'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?P<id>[^/?#&]+)$)',
+    ]
    _TESTS = [{
        'url': 'https://www.raiplaysound.it/audio/2021/12/IL-RUGGITO-DEL-CONIGLIO-1ebae2a7-7cdb-42bb-842e-fe0d193e9707.html',
        'md5': '8970abf8caf8aef4696e7b1f2adfc696',
@ -482,7 +487,26 @@ class RaiPlaySoundIE(RaiBaseIE):
            'timestamp': 1638346620,
            'upload_date': '20211201',
        },
-        'params': {'skip_download': True},
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.raiplaysound.it/radio2',
+        'info_dict': {
+            'id': 'b00a50e6-f404-4af6-8f8c-ff3b9af73a44',
+            'display_id': 'radio2',
+            'ext': 'mp4',
+            'title': r're:Rai Radio 2 \d+-\d+-\d+ \d+:\d+',
+            'thumbnail': r're:https://www\.raiplaysound\.it/dl/img/.+png',
+            'uploader': 'rai radio 2',
+            'series': 'Rai Radio 2',
+            'creator': 'raiplaysound',
+            'is_live': True,
+            'live_status': 'is_live',
+        },
+        'params': {
+            'skip_download': 'live',
+        },
    }]

    def _real_extract(self, url):
@ -506,6 +530,7 @@ class RaiPlaySoundIE(RaiBaseIE):
            **info,
            'id': uid or audio_id,
            'display_id': audio_id,
+            '_old_archive_ids': [make_archive_id('RaiPlaySoundLive', audio_id)] if not re.match(RaiBaseIE._UUID_RE, audio_id) else None,
            'title': traverse_obj(media, 'title', 'episode_title'),
            'alt_title': traverse_obj(media, ('track_info', 'media_name'), expected_type=strip_or_none),
            'description': media.get('description'),
@ -521,26 +546,6 @@ class RaiPlaySoundIE(RaiBaseIE):
        }


-class RaiPlaySoundLiveIE(RaiPlaySoundIE):  # XXX: Do not subclass from concrete IE
-    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?P<id>[^/?#&]+)$)'
-    _TESTS = [{
-        'url': 'https://www.raiplaysound.it/radio2',
-        'info_dict': {
-            'id': 'b00a50e6-f404-4af6-8f8c-ff3b9af73a44',
-            'display_id': 'radio2',
-            'ext': 'mp4',
-            'title': r're:Rai Radio 2 \d+-\d+-\d+ \d+:\d+',
-            'thumbnail': r're:^https://www\.raiplaysound\.it/dl/img/.+\.png',
-            'uploader': 'rai radio 2',
-            'series': 'Rai Radio 2',
-            'creator': 'raiplaysound',
-            'is_live': True,
-            'live_status': 'is_live',
-        },
-        'params': {'skip_download': True},
-    }]
-
-
 class RaiPlaySoundPlaylistIE(InfoExtractor):
    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?:programmi|playlist|audiolibri)/(?P<id>[^/?#&]+))(?:/(?P<extra_id>[^?#&]+))?'
    _TESTS = [{
Author	SHA1	Message	Date
nixxo	419d041efa	Merge `87c8703f90` into `eb15fd5a32`	2024-11-17 21:33:19 +05:30
krichbanana	eb15fd5a32	[ie/kenh14] Add extractor (#3996 ) Closes #3937 Authored by: krichbanana, pzhlkj6612 Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>	2024-11-17 14:12:26 +00:00
sepro	7cecd299e4	[ie/chaturbate] Don't break embed detection (#11565 ) Bugfix for `720b3dc453` Authored by: seproDev	2024-11-17 13:32:12 +01:00
nixxo	87c8703f90	Merge branch 'master' into valid-urls-proposal	2023-06-25 10:47:04 +02:00
nixxo	1c3a9489ca	Merge branch 'master' into valid-urls-proposal	2023-01-12 21:50:40 +01:00
nixxo	a73ef8c776	Improved documentation for _VALID_URL Co-authored-by: dirkf <fieldhouse@gmx.net>	2023-01-12 21:40:41 +01:00
nixxo	518d585eb7	_VALID_URLS > _VALID_URL	2022-12-30 23:56:09 +01:00
nixxo	42d0fba2bf	Implemented solution suggested by @dirkf using variadic	2022-12-30 23:55:32 +01:00
nixxo	7b93fb5ddc	[extractor/rai] using new _VALID_URLS property - implemented _VALID_URLS property - deleted a couple of subclasses - added '_old_archive_ids' to manage back-compatibility with removed subclasses (by @pukkandan)	2022-12-16 11:27:14 +01:00
nixxo	74b5d34794	[extractor/la7] testing implementation of new _VALID_URLS property	2022-12-16 11:26:39 +01:00
nixxo	db96683cf1	[core] _VALID_URLS implementation - implemented _VALID_URLS extractor property - improvement suggested by @Grub4k	2022-12-16 11:26:33 +01:00