From 434f6ff6b9b9c218791b92adc010194698f7fbb8 Mon Sep 17 00:00:00 2001
From: ElDonad <elidoset@gmail.com>
Date: Sun, 5 Jan 2025 18:24:52 +0100
Subject: [PATCH] [ie/digiteka] Fix testing and some formatting errors

---
 yt_dlp/extractor/digiteka.py | 72 ++++++++++++++++++++++--------------
 1 file changed, 44 insertions(+), 28 deletions(-)

diff --git a/yt_dlp/extractor/digiteka.py b/yt_dlp/extractor/digiteka.py
index e70c342019..7bd5d2099f 100644
--- a/yt_dlp/extractor/digiteka.py
+++ b/yt_dlp/extractor/digiteka.py
@@ -1,6 +1,7 @@
 from .common import InfoExtractor
 from ..utils import int_or_none
 
+
 class DigitekaIE(InfoExtractor):
     _VALID_URL = r'''(?x)
         https?://(?:www\.)?(?:digiteka\.net|ultimedia\.com)/
@@ -22,31 +23,52 @@ class DigitekaIE(InfoExtractor):
             )
             /id
         )/(?P<id>[\d+a-z]+)'''
-    _EMBED_REGEX = [r'<(?:iframe|script)(?:(?!>)[\s\S])*(?:data-)?src=["\'](?P<url>(?:https?:)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/(?P<embed_type>generic|musique)(?:/[^/]+)*/(?:src|article)/(?P<id>[\d+a-z]+))']
+    _EMBED_REGEX = [
+        r'<(?:iframe|script)(?:(?!>)[\s\S])*(?:data-)?src=["\'](?P<url>(?:https?:)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/(?P<embed_type>generic|musique)(?:/[^/]+)*/(?:src|article)/(?P<id>[\d+a-z]+))',
+    ]
     _TESTS = [
-        {'url': 'https://www.ultimedia.com/deliver/generic/iframe/mdtk/01747256/zone/60/src/x8smpxf'}, # direct url
-        {'url': 'https://www.boursorama.com/bourse/actualites/le-retour-des-taux-negatifs-est-il-possible-169e3e0cf337df132285b41e124dc98e'} # from an embed
+        {
+            'url': 'https://www.ultimedia.com/deliver/generic/iframe/mdtk/01747256/zone/60/src/x8smpxf',
+            'info_dict': {
+                'id': 'x8smpxf',
+                'title': 'B. Bazin (Saint-Gobain) \'Notre cours de bourse a doublé depuis 2 ans et il a encore du potentiel !\'',
+                'thumbnail': 'https://vod.digiteka.com/x8smpxf/thumbnails/e7c0403e5ff43ef78ee7baa8e27d3c26fb1deaa4-858x480.jpg',
+                'url': 'https://assets.digiteka.com/encoded/04ddd4e10a9bb92f2a6e15d5adf40c9154db532a/mp4/d2da1c9e12f03d3f_480.mp4',
+                'ext': 'mp4',
+            },
+        },
+    ]
+    _WEBPAGE_TESTS = [
+        {
+            'url': 'https://www.boursorama.com/bourse/actualites/le-retour-des-taux-negatifs-est-il-possible-169e3e0cf337df132285b41e124dc98e',
+            'info_dict': {
+                'id': 'xvussq5',
+                'title': 'Le retour des taux négatifs est-il possible ? ',
+                'thumbnail': 'https://vod.digiteka.com/xvussq5/thumbnails/9a4df121fc0532ab4d0befbece630fd7725d91a7-858x480.jpg',
+                'url': 'https://assets.digiteka.com/encoded/0308c71b8ba91157ae76f0ca21c58f80e63ccf7a/mp4/0dde8b5bc0a8f240_480.mp4',
+                'ext': 'mp4',
+            },
+        },
     ]
 
     def _fallback_to_iframe_content(self, url, video_id):
         iframe_content = self._download_webpage(url, video_id)
-        VIDEO_URL_REGEX = '<meta property="og:video" content="(?P<url>.*)"/>'
-        VIDEO_TITLE_REGEX = '<meta property="og:title" content="(?P<title>.*)"/>'
-        VIDEO_THUMBNAIL_REGEX = '<meta property="og:image" content="(?P<thumbnail>.*)"/>'
 
-        video_url = self._search_regex(VIDEO_URL_REGEX, iframe_content, 'url')
+        video_url = self._og_search_video_url(iframe_content)
         video_format = video_url.split('.')[-1]
-        video_title = self._search_regex(VIDEO_TITLE_REGEX, iframe_content, 'title')
-        video_thumbnail = self._search_regex(VIDEO_THUMBNAIL_REGEX, iframe_content, 'thumbnail')
+        video_title = self._og_search_title(iframe_content)
+        video_thumbnail = self._og_search_thumbnail(iframe_content)
 
         return {
             'id': video_id,
             'title': video_title,
             'thumbnail': video_thumbnail,
-            'formats': [{
-                'url': video_url,
-                'ext': video_format,
-            }]
+            'formats': [
+                {
+                    'url': video_url,
+                    'ext': video_format,
+                },
+            ],
         }
 
     def _real_extract(self, url):
@@ -58,9 +80,9 @@ class DigitekaIE(InfoExtractor):
 
         deliver_info = self._download_json(
             f'http://www.ultimedia.com/deliver/video?video={video_id}&topic={video_type}',
-            video_id)
+            video_id,
+        )
         if not deliver_info:
-            # Apparently some video's deliver_info are not accessible this way anymore
             return self._fallback_to_iframe_content(url, video_id)
         yt_id = deliver_info.get('yt_id')
         if yt_id:
@@ -68,25 +90,19 @@ class DigitekaIE(InfoExtractor):
 
         jwconf = deliver_info['jwconf']
 
-
         formats = []
 
         for source in jwconf['playlist'][0]['sources']:
             if source['file'] is not False:
-                formats.append({
-                    'url': source['file'],
-                    'format_id': source.get('label'),
-                })
-        if len(formats) == 0:
-            # the file urls are not available from the json directly anymore, but
-            # can be found in the iframe content
+                formats.append(
+                    {
+                        'url': source['file'],
+                        'format_id': source.get('label'),
+                    },
+                )
+        if not formats:
             return self._fallback_to_iframe_content(url, video_id)
 
-        formats.append({
-            'url': video_url,
-            'ext': video_format,
-        })
-
         title = deliver_info['title']
         thumbnail = jwconf.get('image')
         duration = int_or_none(deliver_info.get('duration'))