ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

#1105 got fixed (metadata now matches with meta property article:*

Browse Source
This commit is contained in:
Ahmed-Tawfik94
2025-05-19 11:35:13 +08:00
parent 22725ca87b
commit faa98eefbc
1 changed files with 12 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
crawl4ai/utils.py
View File

@@ -1456,6 +1456,12 @@ def extract_metadata_using_lxml(html, doc=None):
content = tag.get("content", "").strip() content = tag.get("content", "").strip()
if property_name and content: if property_name and content:
metadata[property_name] = 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 return metadata
@@ -1531,7 +1537,12 @@ def extract_metadata(html, soup=None):
content = tag.get("content", "").strip() content = tag.get("content", "").strip()
if property_name and content: if property_name and content:
metadata[property_name] = 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 return metadata