[infomaniak] Add VOD2 embed extractor (#33234)

Co-authored-by: dirkf <fieldhouse@gmx.net>

youtube_dl/extractor/extractors.py

@@ -527,6 +527,7 @@ from .imgur import (
 from .ina import InaIE
 from .inc import IncIE
 from .indavideo import IndavideoEmbedIE
+from .infomaniak import InfomaniakVod2IE
 from .infoq import InfoQIE
 from .instagram import (
     InstagramIE,

youtube_dl/extractor/infomaniak.py

@@ -0,0 +1,90 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str as str
+from ..utils import (
+    ExtractorError,
+    merge_dicts,
+    parse_duration,
+    str_or_none,
+    T,
+    traverse_obj,
+    url_or_none,
+)
+
+
+class InfomaniakVod2IE(InfoExtractor):
+    IE_NAME = 'infomaniak:vod2'
+    _VALID_URL = r'https?://player\.vod2\.infomaniak\.com/embed/(?P<id>[0-9a-z]+)'
+    _TEST = {
+        'url': 'https://player.vod2.infomaniak.com/embed/1jhvl2uqg6ywp',
+        'md5': '08c3a89906b70a614fa0fdb057e8a22e',
+        'info_dict': {
+            'id': '1jhvl2uqg6xis',
+            'display_id': '1jhvl2uqg6ywp',
+            'ext': 'mp4',
+            'title': 'Conférence à Dyo, octobre 2022',
+            'thumbnail': r're:https?://.+\.(?:jpe?g|png)$',
+        },
+    }
+
+    def _real_extract(self, url):
+        share_id = self._match_id(url)
+        share = self._download_json(
+            'https://api.infomaniak.com/2/vod/res/shares/%s.json' % (share_id,),
+            share_id)
+        entries = []
+        for media in traverse_obj(share, (
+                'data', 'media', lambda _, v: v.get('source').get)):
+            media_id = media.get('id') or share_id
+            source = media['source']
+            formats = []
+
+            for src, src_url in traverse_obj(('hls', 'dash', 'best'), (
+                    lambda _, v: source.get(v), T(lambda x: (x, source[x])))):
+                if src == 'hls':
+                    formats.extend(self._extract_m3u8_formats(
+                        src_url, media_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id=src, fatal=False))
+                elif src == 'dash':
+                    formats.extend(self._extract_mpd_formats(
+                        src_url, media_id, mpd_id=src, fatal=False))
+                elif src == 'best':
+                    formats.append({
+                        'url': src_url,
+                        'format_id': 'http',
+                        'preference': 10,
+                    })
+
+            self._sort_formats(formats)
+
+            entries.append(merge_dicts(
+                traverse_obj(media, {
+                    'id': ('id', T(str_or_none)),
+                    'title': ('title', T(str)),
+                    'duration': ('duration', T(parse_duration)),
+                    'thumbnail': ('thumbnails', ('poster', 'image'), T(url_or_none), any),
+                }), {
+                    'formats': formats,
+                }))
+
+        n_entries = len(entries)
+        if n_entries == 1:
+            return merge_dicts({
+                'id': share_id,
+                'display_id': share_id,
+            }, entries[0], rev=True)
+
+        entries = [e for e in entries if e.get('id')]
+        n_entries -= len(entries)
+        if n_entries > 0:
+            self.report_warning(
+                'Share contains multiple media entries, but %d item(s) are missing an id and will be skipped. '
+                'If this looks incorrect, please report the URL.' % n_entries,
+                share_id, only_once=True)
+        elif not entries:
+            # Keep the error message actionable for site support requests
+            raise ExtractorError('Unable to find any media in share JSON', expected=True)
+
+        return self.playlist_result(entries, playlist_id=share_id)