[ie/IlPost] Add extractor (#9001)

Authored by: CapacitorSet

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index b49e0366c03a4e5bea6e7e2214941acf45d02e14..5fc39d111b17f33316880c2006e3b21738cc7bcc 100644 (file)
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -787,6 +787,7 @@
     IHeartRadioIE,
     IHeartRadioPodcastIE,
 )
+from .ilpost import IlPostIE
 from .iltalehti import IltalehtiIE
 from .imdb import (
     ImdbIE,

diff --git a/yt_dlp/extractor/ilpost.py b/yt_dlp/extractor/ilpost.py
new file mode 100644 (file)
index 0000000..ae98399
--- /dev/null
+++ b/yt_dlp/extractor/ilpost.py
@@ -0,0 +1,69 @@
+import functools
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    url_or_none,
+    urlencode_postdata,
+)
+from ..utils.traversal import traverse_obj
+
+
+class IlPostIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ilpost\.it/episodes/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.ilpost.it/episodes/1-avis-akvasas-ka/',
+        'md5': '43649f002d85e1c2f319bb478d479c40',
+        'info_dict': {
+            'id': '2972047',
+            'ext': 'mp3',
+            'display_id': '1-avis-akvasas-ka',
+            'title': '1. Avis akvasas ka',
+            'url': 'https://www.ilpost.it/wp-content/uploads/2023/12/28/1703781217-l-invasione-pt1-v6.mp3',
+            'timestamp': 1703835014,
+            'upload_date': '20231229',
+            'duration': 2495.0,
+            'availability': 'public',
+            'series_id': '235598',
+            'description': '',
+        }
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        endpoint_metadata = self._search_json(
+            r'var\s+ilpostpodcast\s*=', webpage, 'metadata', display_id)
+        episode_id = endpoint_metadata['post_id']
+        podcast_id = endpoint_metadata['podcast_id']
+        podcast_metadata = self._download_json(
+            endpoint_metadata['ajax_url'], display_id, data=urlencode_postdata({
+                'action': 'checkpodcast',
+                'cookie': endpoint_metadata['cookie'],
+                'post_id': episode_id,
+                'podcast_id': podcast_id,
+            }))
+
+        episode = traverse_obj(podcast_metadata, (
+            'data', 'postcastList', lambda _, v: str(v['id']) == episode_id, {dict}), get_all=False)
+        if not episode:
+            raise ExtractorError('Episode could not be extracted')
+
+        return {
+            'id': episode_id,
+            'display_id': display_id,
+            'series_id': podcast_id,
+            'vcodec': 'none',
+            **traverse_obj(episode, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'url': ('podcast_raw_url', {url_or_none}),
+                'thumbnail': ('image', {url_or_none}),
+                'timestamp': ('timestamp', {int_or_none}),
+                'duration': ('milliseconds', {functools.partial(float_or_none, scale=1000)}),
+                'availability': ('free', {lambda v: 'public' if v else 'subscriber_only'}),
+            }),
+        }