X-Git-Url: https://jfr.im/git/yt-dlp.git/blobdiff_plain/12e73423f1df25bfe2fa00434b2688dd7dd9d227..1ba6fe9db5f660d5538588315c23ad6cf0371c5f:/yt_dlp/extractor/plutotv.py

diff --git a/yt_dlp/extractor/plutotv.py b/yt_dlp/extractor/plutotv.py
index 521c70cd1..caffeb21d 100644
--- a/yt_dlp/extractor/plutotv.py
+++ b/yt_dlp/extractor/plutotv.py
@@ -1,6 +1,3 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import re
 import uuid
 
@@ -19,7 +16,16 @@
 
 
 class PlutoTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?pluto\.tv/on-demand/(?P<video_type>movies|series)/(?P<slug>.*)/?$'
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?pluto\.tv(?:/[^/]+)?/on-demand
+        /(?P<video_type>movies|series)
+        /(?P<series_or_movie_slug>[^/]+)
+        (?:
+            (?:/seasons?/(?P<season_no>\d+))?
+            (?:/episode/(?P<episode_slug>[^/]+))?
+        )?
+        /?(?:$|[#?])'''
+
     _INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/'
     _INFO_QUERY_PARAMS = {
         'appName': 'web',
@@ -48,24 +54,21 @@ class PlutoTVIE(InfoExtractor):
                 'episode_number': 3,
                 'duration': 3600,
             }
-        },
-        {
+        }, {
             'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/',
             'playlist_count': 11,
             'info_dict': {
                 'id': '5de6c582e9379ae4912dedbd',
                 'title': 'I Love Money - Season 1',
             }
-        },
-        {
+        }, {
             'url': 'https://pluto.tv/on-demand/series/i-love-money/',
             'playlist_count': 26,
             'info_dict': {
                 'id': '5de6c582e9379ae4912dedbd',
                 'title': 'I Love Money',
             }
-        },
-        {
+        }, {
             'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1',
             'md5': '3cead001d317a018bf856a896dee1762',
             'info_dict': {
@@ -75,7 +78,24 @@ class PlutoTVIE(InfoExtractor):
                 'description': 'When mysterious spacecraft touch down across the globe, an elite team - led by expert translator Louise Banks (Academy Award® nominee Amy Adams) – races against time to decipher their intent.',
                 'duration': 9000,
             }
+        }, {
+            'url': 'https://pluto.tv/en/on-demand/series/manhunters-fugitive-task-force/seasons/1/episode/third-times-the-charm-1-1',
+            'only_matching': True,
+        }, {
+            'url': 'https://pluto.tv/it/on-demand/series/csi-vegas/episode/legacy-2021-1-1',
+            'only_matching': True,
         },
+        {
+            'url': 'https://pluto.tv/en/on-demand/movies/attack-of-the-killer-tomatoes-1977-1-1-ptv1',
+            'md5': '7db56369c0da626a32d505ec6eb3f89f',
+            'info_dict': {
+                'id': '5b190c7bb0875c36c90c29c4',
+                'ext': 'mp4',
+                'title': 'Attack of the Killer Tomatoes',
+                'description': 'A group of scientists band together to save the world from mutated tomatoes that KILL! (1978)',
+                'duration': 5700,
+            }
+        }
     ]
 
     def _to_ad_free_formats(self, video_id, formats, subtitles):
@@ -94,7 +114,7 @@ def _to_ad_free_formats(self, video_id, formats, subtitles):
                     compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8'))
                 continue
             first_segment_url = re.search(
-                r'^(https?://.*/).+\-0+\.ts$', res,
+                r'^(https?://.*/).+\-0+[0-1]0\.ts$', res,
                 re.MULTILINE)
             if first_segment_url:
                 m3u8_urls.add(
@@ -109,7 +129,7 @@ def _to_ad_free_formats(self, video_id, formats, subtitles):
         if ad_free_formats:
             formats, subtitles = ad_free_formats, ad_free_subtitles
         else:
-            self._downloader.report_warning('Unable to find ad-free formats')
+            self.report_warning('Unable to find ad-free formats')
         return formats, subtitles
 
     def _get_video_info(self, video_json, slug, series_name=None):
@@ -126,7 +146,6 @@ def _get_video_info(self, video_json, slug, series_name=None):
             subtitles = self._merge_subtitles(subtitles, subs)
 
         formats, subtitles = self._to_ad_free_formats(video_id, formats, subtitles)
-        self._sort_formats(formats)
 
         info = {
             'id': video_id,
@@ -146,17 +165,13 @@ def _get_video_info(self, video_json, slug, series_name=None):
         return info
 
     def _real_extract(self, url):
-        path = compat_urlparse.urlparse(url).path
-        path_components = path.split('/')
-        video_type = path_components[2]
-        info_slug = path_components[3]
-        video_json = self._download_json(self._INFO_URL + info_slug, info_slug,
-                                         query=self._INFO_QUERY_PARAMS)
+        mobj = self._match_valid_url(url).groupdict()
+        info_slug = mobj['series_or_movie_slug']
+        video_json = self._download_json(self._INFO_URL + info_slug, info_slug, query=self._INFO_QUERY_PARAMS)
 
-        if video_type == 'series':
+        if mobj['video_type'] == 'series':
             series_name = video_json.get('name', info_slug)
-            season_number = int_or_none(try_get(path_components, lambda x: x[5]))
-            episode_slug = try_get(path_components, lambda x: x[7])
+            season_number, episode_slug = mobj.get('season_number'), mobj.get('episode_slug')
 
             videos = []
             for season in video_json['seasons']: