diff options
| -rw-r--r-- | python/sandcrawler/ingest_file.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/python/sandcrawler/ingest_file.py b/python/sandcrawler/ingest_file.py index 1626292..cf87fff 100644 --- a/python/sandcrawler/ingest_file.py +++ b/python/sandcrawler/ingest_file.py @@ -116,6 +116,8 @@ class IngestFileWorker(SandcrawlerWorker): self.max_html_resources = 200 self.base_url_blocklist = [ + "://localhost/", + "://127.0.0.1/", # robot blocking / rate-limited "://hkvalidate.perfdrive.com/", "://ieeexplore.ieee.org/", @@ -127,6 +129,7 @@ class IngestFileWorker(SandcrawlerWorker): "://openlibrary.org/", "://www.openlibrary.org/", "://fatcat.wiki/", + "://scholar.archive.org/", "://orcid.org/", # Domain squats "://bartandjones.com", |