[ie/tvw:news] Add extractor (#12907)

Authored by: fries1234

yt_dlp/extractor/_extractors.py

@@ -1781,6 +1781,7 @@ from .rtve import (
     RTVEALaCartaIE,
     RTVEAudioIE,
     RTVELiveIE,
+    RTVEProgramIE,
     RTVETelevisionIE,
 )
 from .rtvs import RTVSIE
@@ -2234,6 +2235,7 @@ from .tvplay import (
 from .tvplayer import TVPlayerIE
 from .tvw import (
     TvwIE,
+    TvwNewsIE,
     TvwTvChannelsIE,
 )
 from .tweakers import TweakersIE

yt_dlp/extractor/rtve.py

@@ -6,9 +6,11 @@ import urllib.parse
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    InAdvancePagedList,
     clean_html,
     determine_ext,
     float_or_none,
+    int_or_none,
     make_archive_id,
     parse_iso8601,
     qualities,
@@ -371,3 +373,62 @@ class RTVETelevisionIE(InfoExtractor):
             raise ExtractorError('The webpage doesn\'t contain any video', expected=True)
 
         return self.url_result(play_url, ie=RTVEALaCartaIE.ie_key())
+
+
+class RTVEProgramIE(RTVEBaseIE):
+    IE_NAME = 'rtve.es:program'
+    IE_DESC = 'RTVE.es programs'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/play/videos/(?P<id>[\w-]+)/?(?:[?#]|$)'
+    _TESTS = [{
+        'url': 'https://www.rtve.es/play/videos/saber-vivir/',
+        'info_dict': {
+            'id': '111570',
+            'title': 'Saber vivir - Programa de ciencia y futuro en RTVE Play',
+        },
+        'playlist_mincount': 400,
+    }]
+    _PAGE_SIZE = 60
+
+    def _fetch_page(self, program_id, page_num):
+        return self._download_json(
+            f'https://www.rtve.es/api/programas/{program_id}/videos',
+            program_id, note=f'Downloading page {page_num}',
+            query={
+                'type': 39816,
+                'page': page_num,
+                'size': 60,
+            })
+
+    def _entries(self, page_data):
+        for video in traverse_obj(page_data, ('page', 'items', lambda _, v: url_or_none(v['htmlUrl']))):
+            yield self.url_result(
+                video['htmlUrl'], RTVEALaCartaIE, url_transparent=True,
+                **traverse_obj(video, {
+                    'id': ('id', {str}),
+                    'title': ('longTitle', {str}),
+                    'description': ('shortDescription', {str}),
+                    'duration': ('duration', {float_or_none(scale=1000)}),
+                    'series': (('programInfo', 'title'), {str}, any),
+                    'season_number': ('temporadaOrden', {int_or_none}),
+                    'season_id': ('temporadaId', {str}),
+                    'season': ('temporada', {str}),
+                    'episode_number': ('episode', {int_or_none}),
+                    'episode': ('title', {str}),
+                    'thumbnail': ('thumbnail', {url_or_none}),
+                }),
+            )
+
+    def _real_extract(self, url):
+        program_slug = self._match_id(url)
+        program_page = self._download_webpage(url, program_slug)
+
+        program_id = self._html_search_meta('DC.identifier', program_page, 'Program ID', fatal=True)
+
+        first_page = self._fetch_page(program_id, 1)
+        page_count = traverse_obj(first_page, ('page', 'totalPages', {int})) or 1
+
+        entries = InAdvancePagedList(
+            lambda idx: self._entries(self._fetch_page(program_id, idx + 1) if idx else first_page),
+            page_count, self._PAGE_SIZE)
+
+        return self.playlist_result(entries, program_id, self._html_extract_title(program_page))

yt_dlp/extractor/tvw.py

@@ -10,12 +10,15 @@ from ..utils import (
     unified_timestamp,
     url_or_none,
 )
-from ..utils.traversal import find_element, traverse_obj
+from ..utils.traversal import find_element, find_elements, traverse_obj
 
 
 class TvwIE(InfoExtractor):
     IE_NAME = 'tvw'
-    _VALID_URL = r'https?://(?:www\.)?tvw\.org/video/(?P<id>[^/?#]+)'
+    _VALID_URL = [
+        r'https?://(?:www\.)?tvw\.org/video/(?P<id>[^/?#]+)',
+        r'https?://(?:www\.)?tvw\.org/watch/?\?(?:[^#]+&)?eventID=(?P<id>\d+)',
+    ]
     _TESTS = [{
         'url': 'https://tvw.org/video/billy-frank-jr-statue-maquette-unveiling-ceremony-2024011211/',
         'md5': '9ceb94fe2bb7fd726f74f16356825703',
@@ -75,6 +78,20 @@ class TvwIE(InfoExtractor):
             'display_id': 'washington-to-washington-a-new-space-race-2022041111',
             'categories': ['Washington to Washington', 'General Interest'],
         },
+    }, {
+        'url': 'https://tvw.org/watch?eventID=2025041235',
+        'md5': '7d697c02f110b37d6a47622ea608ca90',
+        'info_dict': {
+            'id': '2025041235',
+            'ext': 'mp4',
+            'title': 'Legislative Review - Medicaid Postpartum Bill Sparks Debate & Senate Approves Automatic Voter Registration',
+            'thumbnail': r're:^https?://.*\.(?:jpe?g|png)$',
+            'description': 'md5:37d0f3a9187ae520aac261b3959eaee6',
+            'timestamp': 1745006400,
+            'upload_date': '20250418',
+            'location': 'Hayner Media Center',
+            'categories': ['Legislative Review'],
+        },
     }]
 
     def _real_extract(self, url):
@@ -125,6 +142,41 @@ class TvwIE(InfoExtractor):
         }
 
 
+class TvwNewsIE(InfoExtractor):
+    IE_NAME = 'tvw:news'
+    _VALID_URL = r'https?://(?:www\.)?tvw\.org/\d{4}/\d{2}/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://tvw.org/2024/01/the-impact-issues-to-watch-in-the-2024-legislative-session/',
+        'info_dict': {
+            'id': 'the-impact-issues-to-watch-in-the-2024-legislative-session',
+            'title': 'The Impact - Issues to Watch in the 2024 Legislative Session',
+            'description': 'md5:65f0b33ec8f18ff1cd401c5547aa5441',
+        },
+        'playlist_count': 6,
+    }, {
+        'url': 'https://tvw.org/2024/06/the-impact-water-rights-and-the-skookumchuck-dam-debate/',
+        'info_dict': {
+            'id': 'the-impact-water-rights-and-the-skookumchuck-dam-debate',
+            'title': 'The Impact - Water Rights and the Skookumchuck Dam Debate',
+            'description': 'md5:185f3a2350ef81e3fa159ac3e040a94b',
+        },
+        'playlist_count': 1,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        video_ids = traverse_obj(webpage, (
+            {find_elements(cls='invintus-player', html=True)}, ..., {extract_attributes}, 'data-eventid'))
+
+        return self.playlist_from_matches(
+            video_ids, playlist_id,
+            playlist_title=remove_end(self._og_search_title(webpage, default=None), ' - TVW'),
+            playlist_description=self._og_search_description(webpage, default=None),
+            getter=lambda x: f'https://tvw.org/watch?eventID={x}', ie=TvwIE)
+
+
 class TvwTvChannelsIE(InfoExtractor):
     IE_NAME = 'tvw:tvchannels'
     _VALID_URL = r'https?://(?:www\.)?tvw\.org/tvchannels/(?P<id>[^/?#]+)'