From 826446bd82b0168bc40c3be027b2bfa47313ce19 Mon Sep 17 00:00:00 2001 From: pukkandan Date: Sun, 5 Sep 2021 04:41:02 +0530 Subject: [PATCH] [plutotv] Fix extractor for URLs with `/en` Closes #431 --- yt_dlp/extractor/plutotv.py | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/yt_dlp/extractor/plutotv.py b/yt_dlp/extractor/plutotv.py index b19ff8d02..0cf82466a 100644 --- a/yt_dlp/extractor/plutotv.py +++ b/yt_dlp/extractor/plutotv.py @@ -19,7 +19,16 @@ class PlutoTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?pluto\.tv(?:/en)?/on-demand/(?Pmovies|series)/(?P.*)/?$' + _VALID_URL = r'''(?x) + https?://(?:www\.)?pluto\.tv(?:/en)?/on-demand + /(?Pmovies|series) + /(?P[^/]+) + (?: + /seasons?/(?P\d+) + (?:/episode/(?P[^/]+))? + )? + /?(?:$|[#?])''' + _INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/' _INFO_QUERY_PARAMS = { 'appName': 'web', @@ -146,17 +155,13 @@ 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']: