[ie/NowCanal] Add extractor (#14584)

Authored by: pferreir

yt_dlp/extractor/_extractors.py

@@ -268,6 +268,7 @@ from .bitchute import (
     BitChuteChannelIE,
     BitChuteIE,
 )
+from .bitmovin import BitmovinIE
 from .blackboardcollaborate import (
     BlackboardCollaborateIE,
     BlackboardCollaborateLaunchIE,
@@ -1368,6 +1369,7 @@ from .nova import (
     NovaIE,
 )
 from .novaplay import NovaPlayIE
+from .nowcanal import NowCanalIE
 from .nowness import (
     NownessIE,
     NownessPlaylistIE,

yt_dlp/extractor/bitmovin.py

@@ -0,0 +1,74 @@
+import re
+
+from .common import InfoExtractor
+from ..utils.traversal import traverse_obj
+
+
+class BitmovinIE(InfoExtractor):
+    _VALID_URL = r'https?://streams\.bitmovin\.com/(?P<id>\w+)'
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//streams\.bitmovin\.com/(?P<id>\w+)[^"\']+)']
+    _TESTS = [{
+        'url': 'https://streams.bitmovin.com/cqkl1t5giv3lrce7pjbg/embed',
+        'info_dict': {
+            'id': 'cqkl1t5giv3lrce7pjbg',
+            'ext': 'mp4',
+            'title': 'Developing Osteopathic Residents as Faculty',
+            'thumbnail': 'https://streams.bitmovin.com/cqkl1t5giv3lrce7pjbg/poster',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://streams.bitmovin.com/cgl9rh94uvs51rqc8jhg/share',
+        'info_dict': {
+            'id': 'cgl9rh94uvs51rqc8jhg',
+            'ext': 'mp4',
+            'title': 'Big Buck Bunny (Streams Docs)',
+            'thumbnail': 'https://streams.bitmovin.com/cgl9rh94uvs51rqc8jhg/poster',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+    _WEBPAGE_TESTS = [{
+        # bitmovin-stream web component
+        'url': 'https://www.institutionalinvestor.com/article/2bsw1in1l9k68mp9kritc/video-war-stories-over-board-games/best-case-i-get-fired-war-stories',
+        'info_dict': {
+            'id': 'cuiumeil6g115lc4li3g',
+            'ext': 'mp4',
+            'title': '[media] War Stories over Board Games: “Best Case: I Get Fired” ',
+            'thumbnail': 'https://streams.bitmovin.com/cuiumeil6g115lc4li3g/poster',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        # iframe embed
+        'url': 'https://www.clearblueionizer.com/en/pool-ionizers/mineral-pool-vs-saltwater-pool/',
+        'info_dict': {
+            'id': 'cvpvfsm1pf7itg7cfvtg',
+            'ext': 'mp4',
+            'title': 'Pool Ionizer vs. Salt Chlorinator',
+            'thumbnail': 'https://streams.bitmovin.com/cvpvfsm1pf7itg7cfvtg/poster',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        yield from super()._extract_embed_urls(url, webpage)
+        for stream_id in re.findall(r'<bitmovin-stream\b[^>]*\bstream-id=["\'](?P<id>\w+)', webpage):
+            yield f'https://streams.bitmovin.com/{stream_id}'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        player_config = self._download_json(
+            f'https://streams.bitmovin.com/{video_id}/config', video_id)['sources']
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            player_config['hls'], video_id, 'mp4')
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(player_config, {
+                'title': ('title', {str}),
+                'thumbnail': ('poster', {str}),
+            }),
+        }

yt_dlp/extractor/nowcanal.py

@@ -0,0 +1,37 @@
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+
+
+class NowCanalIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nowcanal\.pt(?:/[\w-]+)+/detalhe/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.nowcanal.pt/ultimas/detalhe/pedro-sousa-hjulmand-pode-ter-uma-saida-limpa-do-sporting-daqui-a-um-ano',
+        'md5': '047f17cb783e66e467d703e704bbc95d',
+        'info_dict': {
+            'id': '6376598467112',
+            'ext': 'mp4',
+            'title': 'Pedro Sousa «Hjulmand pode ter uma saída limpa do Sporting daqui a um ano»',
+            'description': '',
+            'uploader_id': '6108484330001',
+            'duration': 65.237,
+            'thumbnail': r're:^https://.+\.jpg',
+            'timestamp': 1754440620,
+            'upload_date': '20250806',
+            'tags': ['now'],
+        },
+    }, {
+        'url': 'https://www.nowcanal.pt/programas/frente-a-frente/detalhe/frente-a-frente-eva-cruzeiro-ps-e-rita-matias-chega',
+        'only_matching': True,
+    }]
+
+    _BC_URL_TMPL = 'https://players.brightcove.net/6108484330001/chhIqzukMq_default/index.html?videoId={}'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_json(
+            r'videoHandler\.addBrightcoveVideoWithJson\(\[',
+            webpage, 'video data', display_id)['brightcoveVideoId']
+
+        return self.url_result(self._BC_URL_TMPL.format(video_id), BrightcoveNewIE)

yt_dlp/extractor/rinsefm.py

@@ -3,12 +3,14 @@ from ..utils import (
     MEDIA_EXTENSIONS,
     determine_ext,
     parse_iso8601,
-    traverse_obj,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class RinseFMBaseIE(InfoExtractor):
+    _API_BASE = 'https://rinse.fm/api/query/v1'
+
     @staticmethod
     def _parse_entry(entry):
         return {
@@ -45,8 +47,10 @@ class RinseFMIE(RinseFMBaseIE):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        entry = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['entry']
+
+        entry = self._download_json(
+            f'{self._API_BASE}/episodes/{display_id}', display_id,
+            note='Downloading episode data from API')['entry']
 
         return self._parse_entry(entry)
 
@@ -58,32 +62,35 @@ class RinseFMArtistPlaylistIE(RinseFMBaseIE):
         'info_dict': {
             'id': 'resources',
             'title': '[re]sources',
-            'description': '[re]sources est un label parisien piloté par le DJ et producteur Tommy Kid.',
+            'description': 'md5:fd6a7254e8273510e6d49fbf50edf392',
         },
         'playlist_mincount': 40,
     }, {
-        'url': 'https://rinse.fm/shows/ivy/',
+        'url': 'https://www.rinse.fm/shows/esk',
         'info_dict': {
-            'id': 'ivy',
-            'title': '[IVY]',
-            'description': 'A dedicated space for DNB/Turbo House and 4x4.',
+            'id': 'esk',
+            'title': 'Esk',
+            'description': 'md5:5893d7c1d411ae8dea7fba12f109aa98',
         },
-        'playlist_mincount': 7,
+        'playlist_mincount': 139,
     }]
 
     def _entries(self, data):
         for episode in traverse_obj(data, (
-            'props', 'pageProps', 'episodes', lambda _, v: determine_ext(v['fileUrl']) in MEDIA_EXTENSIONS.audio),
+            'episodes', lambda _, v: determine_ext(v['fileUrl']) in MEDIA_EXTENSIONS.audio),
         ):
             yield self._parse_entry(episode)
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
-        webpage = self._download_webpage(url, playlist_id)
-        title = self._og_search_title(webpage) or self._html_search_meta('title', webpage)
-        description = self._og_search_description(webpage) or self._html_search_meta(
-            'description', webpage)
-        data = self._search_nextjs_data(webpage, playlist_id)
+
+        api_data = self._download_json(
+            f'{self._API_BASE}/shows/{playlist_id}', playlist_id,
+            note='Downloading show data from API')
 
         return self.playlist_result(
-            self._entries(data), playlist_id, title, description=description)
+            self._entries(api_data), playlist_id,
+            **traverse_obj(api_data, ('entry', {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+            })))