diff options
Diffstat (limited to 'python/sandcrawler/fileset_strategies.py')
-rw-r--r-- | python/sandcrawler/fileset_strategies.py | 6 |
1 files changed, 5 insertions, 1 deletions
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 |