Skip to content

A feature-rich command-line audio/video downloader

[ie/puhutv] Fix playlists extraction (#11955)

e2dk4r36e873822bdb
diff --git a/yt_dlp/extractor/puhutv.py b/yt_dlp/extractor/puhutv.py
index b62050ecd5..a9552ec944 100644
--- a/yt_dlp/extractor/puhutv.py
+++ b/yt_dlp/extractor/puhutv.py
@@ -6,6 +6,7 @@ from ..utils import (
int_or_none,
parse_resolution,
str_or_none,
+ traverse_obj,
try_get,
unified_timestamp,
url_or_none,
@@ -18,20 +19,21 @@ class PuhuTVIE(InfoExtractor):
IE_NAME = 'puhutv'
_TESTS = [{
# film
- 'url': 'https://puhutv.com/sut-kardesler-izle',
- 'md5': 'a347470371d56e1585d1b2c8dab01c96',
+ 'url': 'https://puhutv.com/bi-kucuk-eylul-meselesi-izle',
+ 'md5': '4de98170ccb84c05779b1f046b3c86f8',
'info_dict': {
- 'id': '5085',
- 'display_id': 'sut-kardesler',
+ 'id': '11909',
+ 'display_id': 'bi-kucuk-eylul-meselesi',
'ext': 'mp4',
- 'title': 'Süt Kardeşler',
- 'description': 'md5:ca09da25b7e57cbb5a9280d6e48d17aa',
+ 'title': 'Bi Küçük Eylül Meselesi',
+ 'description': 'md5:c2ab964c6542b7b26acacca0773adce2',
'thumbnail': r're:^https?://.*\.jpg$',
- 'duration': 4832.44,
- 'creator': 'Arzu Film',
- 'timestamp': 1561062602,
+ 'duration': 6176.96,
+ 'creator': 'Ay Yapım',
+ 'creators': ['Ay Yapım'],
+ 'timestamp': 1561062749,
'upload_date': '20190620',
- 'release_year': 1976,
+ 'release_year': 2014,
'view_count': int,
'tags': list,
},
@@ -181,7 +183,7 @@ class PuhuTVSerieIE(InfoExtractor):
'playlist_mincount': 205,
}, {
# a film detail page which is using same url with serie page
- 'url': 'https://puhutv.com/kaybedenler-kulubu-detay',
+ 'url': 'https://puhutv.com/bizim-icin-sampiyon-detay',
'only_matching': True,
}]
@@ -194,24 +196,19 @@ class PuhuTVSerieIE(InfoExtractor):
has_more = True
while has_more is True:
season = self._download_json(
- f'https://galadriel.puhutv.com/seasons/{season_id}',
+ f'https://appservice.puhutv.com/api/seasons/{season_id}/episodes?v=2',
season_id, f'Downloading page {page}', query={
'page': page,
- 'per': 40,
- })
- episodes = season.get('episodes')
- if isinstance(episodes, list):
- for ep in episodes:
- slug_path = str_or_none(ep.get('slugPath'))
- if not slug_path:
- continue
- video_id = str_or_none(int_or_none(ep.get('id')))
- yield self.url_result(
- f'https://puhutv.com/{slug_path}',
- ie=PuhuTVIE.ie_key(), video_id=video_id,
- video_title=ep.get('name') or ep.get('eventLabel'))
+ 'per': 100,
+ })['data']
+
+ for episode in traverse_obj(season, ('episodes', lambda _, v: v.get('slug') or v['assets'][0]['slug'])):
+ slug = episode.get('slug') or episode['assets'][0]['slug']
+ yield self.url_result(
+ f'https://puhutv.com/{slug}', PuhuTVIE, episode.get('id'), episode.get('name'))
+
page += 1
- has_more = season.get('hasMore')
+ has_more = traverse_obj(season, 'has_more')
def _real_extract(self, url):
playlist_id = self._match_id(url)
@@ -226,7 +223,10 @@ class PuhuTVSerieIE(InfoExtractor):
self._extract_entries(seasons), playlist_id, info.get('name'))
# For films, these are using same url with series
- video_id = info.get('slug') or info['assets'][0]['slug']
+ video_id = info.get('slug')
+ if video_id:
+ video_id = video_id.removesuffix('-detay')
+ else:
+ video_id = info['assets'][0]['slug'].removesuffix('-izle')
return self.url_result(
- f'https://puhutv.com/{video_id}-izle',
- PuhuTVIE.ie_key(), video_id)
+ f'https://puhutv.com/{video_id}-izle', PuhuTVIE, video_id)