diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2021-09-03 10:37:18 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2021-09-03 10:37:18 -0700 |
| commit | d963a61ea3e4bf278fd62047b258722967cd20c9 (patch) | |
| tree | 52a219e09480b78d866abf62c68309fc356a320a | |
| parent | f074a6aafd9af06866829d35555afe10286126fb (diff) | |
| download | sandcrawler-d963a61ea3e4bf278fd62047b258722967cd20c9.tar.gz sandcrawler-d963a61ea3e4bf278fd62047b258722967cd20c9.zip | |
HTML ingest: skip noisy print() statement
| -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 a1938e9..abcc428 100644 --- a/python/sandcrawler/html_metadata.py +++ b/python/sandcrawler/html_metadata.py @@ -661,7 +661,7 @@ def _extract_generic(doc: HTMLParser, selector: str, attrs: List[str], type_name if skip: continue if url: - print(url, file=sys.stderr) + #print(url, file=sys.stderr) resources.append(dict(url=url.strip(), type=type_name)) return resources |