diff options
Diffstat (limited to 'python')
| -rw-r--r-- | python/sandcrawler/html_metadata.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/sandcrawler/html_metadata.py b/python/sandcrawler/html_metadata.py index 1c054fa..1e58778 100644 --- a/python/sandcrawler/html_metadata.py +++ b/python/sandcrawler/html_metadata.py @@ -599,7 +599,7 @@ def _extract_generic(doc: HTMLParser, selector: str, attrs: List[str], type_name continue url = node.attrs.get(attr) if url: - resources.append(dict(url=url, type=type_name)) + resources.append(dict(url=url.strip(), type=type_name)) return resources |