diff options
| -rw-r--r-- | python/sandcrawler/html_metadata.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/python/sandcrawler/html_metadata.py b/python/sandcrawler/html_metadata.py index c805f0a..fb1e421 100644 --- a/python/sandcrawler/html_metadata.py +++ b/python/sandcrawler/html_metadata.py @@ -652,6 +652,9 @@ def _extract_generic(doc: HTMLParser, selector: str, attrs: List[str], type_name if not attr in node.attrs: continue url = node.attrs.get(attr) + # special-case a couple meta urls which don't match with adblock rules + if url in ['about:blank',]: + continue if url: resources.append(dict(url=url.strip(), type=type_name)) |