diff options
| -rw-r--r-- | python/sandcrawler/ingest_file.py | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/python/sandcrawler/ingest_file.py b/python/sandcrawler/ingest_file.py index eca8bf8..c79973f 100644 --- a/python/sandcrawler/ingest_file.py +++ b/python/sandcrawler/ingest_file.py @@ -116,8 +116,9 @@ class IngestFileWorker(SandcrawlerWorker): self.max_html_resources = 200 self.base_url_blocklist = [ - # robot blocking + # robot blocking / rate-limited "://hkvalidate.perfdrive.com/", + "://ieeexplore.ieee.org/", # temporary, until we implement specific fetch and 'petabox' output "://archive.org/", "://www.archive.org/", |