[ie/cwtv:movie] Add extractor (#12227)

Closes #12113
Authored by: bashonly

yt_dlp/extractor/_extractors.py

@@ -454,7 +454,10 @@ from .curiositystream import (
     CuriosityStreamIE,
     CuriosityStreamSeriesIE,
 )
-from .cwtv import CWTVIE
+from .cwtv import (
+    CWTVIE,
+    CWTVMovieIE,
+)
 from .cybrary import (
     CybraryCourseIE,
     CybraryIE,

yt_dlp/extractor/cwtv.py

@@ -1,9 +1,12 @@
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
     parse_age_limit,
     parse_iso8601,
+    parse_qs,
     smuggle_url,
     str_or_none,
     update_url_query,
@@ -12,7 +15,8 @@ from ..utils.traversal import traverse_obj
 
 
 class CWTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
+    IE_NAME = 'cwtv'
+    _VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch|guid)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
     _TESTS = [{
         'url': 'https://www.cwtv.com/shows/continuum/a-stitch-in-time/?play=9149a1e1-4cb2-46d7-81b2-47d35bbd332b',
         'info_dict': {
@@ -90,6 +94,9 @@ class CWTVIE(InfoExtractor):
     }, {
         'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?watch=6b15e985-9345-4f60-baf8-56e96be57c63',
         'only_matching': True,
+    }, {
+        'url': 'http://www.cwtv.com/movies/play/?guid=0a8e8b5b-1356-41d5-9a6a-4eda1a6feb6c',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -124,3 +131,50 @@ class CWTVIE(InfoExtractor):
             'ie_key': 'ThePlatform',
             'thumbnail': video_data.get('large_thumbnail'),
         }
+
+
+class CWTVMovieIE(InfoExtractor):
+    IE_NAME = 'cwtv:movie'
+    _VALID_URL = r'https?://(?:www\.)?cwtv\.com/shows/(?P<id>[\w-]+)/?\?(?:[^#]+&)?viewContext=Movies'
+    _TESTS = [{
+        'url': 'https://www.cwtv.com/shows/the-crush/?viewContext=Movies+Swimlane',
+        'info_dict': {
+            'id': '0a8e8b5b-1356-41d5-9a6a-4eda1a6feb6c',
+            'ext': 'mp4',
+            'title': 'The Crush',
+            'upload_date': '20241112',
+            'description': 'md5:1549acd90dff4a8273acd7284458363e',
+            'chapters': 'count:9',
+            'timestamp': 1731398400,
+            'age_limit': 16,
+            'duration': 5337,
+            'series': 'The Crush',
+            'season': 'Season 1',
+            'uploader': 'CWTV',
+            'season_number': 1,
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'thumbnail': r're:https?://.+\.jpe?g',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+    _UUID_RE = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        app_url = (
+            self._html_search_meta('al:ios:url', webpage, default=None)
+            or self._html_search_meta('al:android:url', webpage, default=None))
+        video_id = (
+            traverse_obj(parse_qs(app_url), ('video_id', 0, {lambda x: re.fullmatch(self._UUID_RE, x)}, 0))
+            or self._search_regex([
+                rf'CWTV\.Site\.curPlayingGUID\s*=\s*["\']({self._UUID_RE})',
+                rf'CWTV\.Site\.viewInAppURL\s*=\s*["\']/shows/[\w-]+/watch-in-app/\?play=({self._UUID_RE})',
+            ], webpage, 'video ID'))
+
+        return self.url_result(
+            f'https://www.cwtv.com/shows/{display_id}/{display_id}/?play={video_id}', CWTVIE, video_id)