diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2021-08-16 20:15:47 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2021-08-16 20:15:49 -0700 |
| commit | 8ccf0e6e935f169d3d6d35da36c767ebf0a4637a (patch) | |
| tree | 22a050c9ab5388af213045ac981f79b82375281b | |
| parent | eab9b929a05da3fa25f4bfaffd84bb0d7b219c73 (diff) | |
| download | sandcrawler-8ccf0e6e935f169d3d6d35da36c767ebf0a4637a.tar.gz sandcrawler-8ccf0e6e935f169d3d6d35da36c767ebf0a4637a.zip | |
html ingest: skip 'about:blank'
Couldn't get adblock rule matcher to match this, for some reason. maybe
a special case?
| -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)) |