From 6ff4dca52c413e66da10cac1fe3b5c7c3ee4315c Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Fri, 18 Feb 2022 19:42:17 -0800 Subject: ingest: handle more fileset failure modes --- python/sandcrawler/fileset_strategies.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'python/sandcrawler/fileset_strategies.py') diff --git a/python/sandcrawler/fileset_strategies.py b/python/sandcrawler/fileset_strategies.py index 9bca551..cccc061 100644 --- a/python/sandcrawler/fileset_strategies.py +++ b/python/sandcrawler/fileset_strategies.py @@ -338,7 +338,11 @@ class WebFilesetStrategy(FilesetIngestStrategy): continue file_meta = gen_file_metadata(resource.body) - file_meta, _html_resource = fix_transfer_encoding(file_meta, resource) + try: + file_meta, _html_resource = fix_transfer_encoding(file_meta, resource) + except: + m.status = "transfer-encoding-error" + continue if self.ingest_strategy == "web-file": file_file_meta = file_meta -- cgit v1.2.3