Merge ab81421072 into eb15fd5a32

Closes #3937
Authored by: krichbanana, pzhlkj6612

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

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,
@@ -1422,6 +1426,7 @@ from .nuum import (
 from .nuvid import NuvidIE
 from .nytimes import (
     NYTimesArticleIE,
+    NYTimesAudioIE,
     NYTimesCookingIE,
     NYTimesCookingRecipeIE,
     NYTimesIE,

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/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)})))

yt_dlp/extractor/nytimes.py

@@ -10,6 +10,7 @@ from ..utils import (
     float_or_none,
     get_elements_html_by_class,
     int_or_none,
+    js_to_json,
     merge_dicts,
     mimetype2ext,
     parse_iso8601,
@@ -418,3 +419,223 @@ class NYTimesCookingRecipeIE(InfoExtractor):
             'thumbnails': [{'url': thumb_url} for thumb_url in traverse_obj(
                 recipe_data, ('image', 'crops', 'recipe', ..., {url_or_none}))],
         }
+
+
+class NYTimesAudioIE(NYTimesBaseIE):
+    _VALID_URL = r"https?://(?:www\.)?nytimes\.com/\d{4}/\d{2}/\d{2}/(?:podcasts|books)/(?:[\w-]+/)?(?P<id>[^./?#]+)(?:\.html)?"
+    _TESTS = [
+        {
+            "url": "http://www.nytimes.com/2016/10/14/podcasts/revelations-from-the-final-weeks.html",
+            "md5": "cd402e44a059c8caf3b5f514c9264d0f",
+            "info_dict": {
+                "id": "100000004709062",
+                "title": "Revelations From the Final Weeks",
+                "ext": "mp3",
+                "description": "md5:fb5c6b93b12efc51649b4847fe066ee4",
+                "timestamp": 1476448332,
+                "upload_date": "20161014",
+                "creators": [''],
+                "series": "The Run-Up",
+                "episode": "‘He Was Like an Octopus’",
+                "episode_number": 20,
+                "duration": 2130,
+                "thumbnail": r"re:https?://\w+\.nyt.com/images/.*\.jpg",
+            },
+        },
+        {
+            "url": "https://www.nytimes.com/2023/11/25/podcasts/poultry-slam.html",
+            "info_dict": {
+                "id": "100000009191248",
+                "title": "Poultry Slam",
+                "ext": "mp3",
+                "description": "md5:1e6f16b21bb9287b8a1fe563145a72fe",
+                "timestamp": 1700911084,
+                "upload_date": "20231125",
+                "creators": [],
+                "series": "This American Life",
+                "episode": "Poultry Slam",
+                "duration": 3523,
+                "thumbnail": r"re:https?://\w+\.nyt.com/images/.*\.png",
+            },
+            "params": {
+                "skip_download": True,
+            },
+        },
+        {
+            "url": "http://www.nytimes.com/2016/10/16/books/review/inside-the-new-york-times-book-review-the-rise-of-hitler.html",
+            "info_dict": {
+                "id": "100000004709479",
+                "title": "Inside The New York Times Book Review: The Rise of Hitler",
+                "ext": "mp3",
+                "description": "md5:288161c98c098a0c24f07a94af7108c3",
+                "timestamp": 1476461513,
+                "upload_date": "20161014",
+                "creators": ['Pamela Paul'],
+                "series": "",
+                "episode": "The Rise of Hitler",
+                "duration": 3475,
+                "thumbnail": r"re:https?://\w+\.nyt.com/images/.*\.jpg",
+            },
+            "params": {
+                "skip_download": True,
+            },
+        },
+        {
+            "url": "https://www.nytimes.com/2023/12/07/podcasts/the-daily/nikki-haley.html",
+            "info_dict": {
+                "id": "100000009214128",
+                "title": "Nikki Haley’s Moment",
+                "ext": "mp3",
+                "description": "md5:bf9f532fe689967ef1c458bcb057f3e5",
+                "timestamp": 1701946819,
+                "upload_date": "20231207",
+                "creators": [],
+                "series": "The Daily",
+                "episode": "Listen to ‘The Daily’: Nikki Haley’s Moment",
+                "duration": 1908,
+            },
+            "params": {
+                "skip_download": True,
+            },
+        },
+        {
+            "url": "https://www.nytimes.com/2023/12/18/podcasts/israel-putin.html",
+            "md5": "708b4fd393ca103280fe9e56d91b08b5",
+            "info_dict": {
+                "id": "100000009227362",
+                "title": "Pressure Mounts on Israel, and Putin Profits Off Boycott",
+                "ext": "mp3",
+                "description": "Hear the news in five minutes.",
+                "timestamp": 1702897212,
+                "upload_date": "20231218",
+                "creators": [],
+                "series": "The Headlines",
+                "episode": "The Headlines",
+                "duration": 298,
+                "thumbnail": r"re:https?://\w+\.nyt.com/images/.*\.jpg",
+            },
+        },
+    ]
+
+    def _extract_content_from_block(self, block):
+        return traverse_obj(
+            block,
+            {
+                "creators": ("data", "track", "credit", all),
+                "duration": (
+                    ("data", "media"),
+                    ("track", "length"),
+                    ("duration", None),
+                    {int_or_none},
+                ),
+                "series": (
+                    ("data", "media"),
+                    ("podcast", "podcastSeries"),
+                    ("title", None),
+                    {str_or_none},
+                ),
+                "episode": (
+                    ("data", "media"),
+                    ("track", "headline"),
+                    ("title", "default"), {str}),
+                "episode_number": (
+                    "data",
+                    "podcast",
+                    "episode",
+                    {lambda v: v.split()[1]},
+                    {int_or_none},
+                ),
+                "url": (
+                    ("data", "media"),
+                    ("track", "fileUrl"),
+                    ("source", None),
+                    {url_or_none},
+                ),
+                "vcodec": "none",
+            },
+            get_all=False,
+        )
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+
+        art_json = self._search_json(
+            r"window\.__preloadedData\s*=",
+            webpage,
+            "media details",
+            page_id,
+            transform_source=js_to_json,
+        )["initialData"]["data"]["article"]
+
+        blocks = traverse_obj(
+            art_json,
+            (
+                "sprinkledBody",
+                "content",
+                lambda _, v: v["__typename"]
+                in ("InteractiveBlock", "HeaderMultimediaBlock"),
+                "media",
+            ),
+        )
+        if not blocks:
+            raise ExtractorError("Unable to extract any media blocks from webpage")
+
+        common_info = {
+            "title": remove_end(
+                self._html_extract_title(webpage), " - The New York Times"
+            ),
+            "description": self._html_search_meta(
+                ["og:description", "twitter:description"], webpage
+            ),
+            "id": traverse_obj(
+                art_json, ("sourceId")
+            ),  # poltry slam is under art_json > 'sourceId'
+            **traverse_obj(
+                art_json,
+                {
+                    "id": (
+                        "sprinkledBody",
+                        "content",
+                        ...,
+                        "media",
+                        "sourceId",
+                        any,
+                        {str},
+                    ),
+                    "title": ("headline", "default"),
+                    "description": ("summary"),
+                    "timestamp": ("firstPublished", {parse_iso8601}),
+                    "thumbnails": (
+                        "promotionalMedia",
+                        "assetCrops",
+                        ...,
+                        "renditions",
+                        ...,
+                        all,
+                        {self._extract_thumbnails},
+                    ),
+                },
+            ),
+        }
+
+        entries = []
+        for block in blocks:
+            if block.get("html"):
+                block = self._search_json(
+                    r"function\s+getFlexData\(\)\s*\{\s*return",
+                    block.get("html"),
+                    "Retrieve the inner JSON",
+                    page_id,
+                )
+            entries.append(
+                merge_dicts(self._extract_content_from_block(block), common_info)
+            )
+
+        if len(entries) > 1:
+            return self.playlist_result(entries, page_id, **common_info)
+
+        return {
+            "id": page_id,
+            **entries[0],
+        }