From faa98eefbc4f3f87f8751bbb5c534cba4f8507c1 Mon Sep 17 00:00:00 2001
From: Ahmed-Tawfik94 <tawfik@kidocode.com>
Date: Mon, 19 May 2025 11:35:13 +0800
Subject: [PATCH] #1105 got fixed (metadata now matches with  meta property
 article:*

---
 crawl4ai/utils.py | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/crawl4ai/utils.py b/crawl4ai/utils.py
index bfa8ce9d..ebf15f24 100644
--- a/crawl4ai/utils.py
+++ b/crawl4ai/utils.py
@@ -1456,6 +1456,12 @@ def extract_metadata_using_lxml(html, doc=None):
         content = tag.get("content", "").strip()
         if property_name and content:
             metadata[property_name] = content
+        # getting the article Values
+    metadata.update({
+        tag['property'].strip():tag["content"].strip()
+        for tag in head.find_all("meta", attrs={"property": re.compile(r"^article:")})
+          if tag.has_attr('property') and tag.has_attr('content')
+    })
 
     return metadata
 
@@ -1531,7 +1537,12 @@ def extract_metadata(html, soup=None):
         content = tag.get("content", "").strip()
         if property_name and content:
             metadata[property_name] = content
-
+        # getting the article Values
+    metadata.update({
+        tag['property'].strip():tag["content"].strip()
+        for tag in head.find_all("meta", attrs={"property": re.compile(r"^article:")})
+          if tag.has_attr('property') and tag.has_attr('content')
+    })
     return metadata