aboutsummaryrefslogtreecommitdiffstats
path: root/mapreduce/tests/test_extraction_cdx_grobid.py
diff options
context:
space:
mode:
Diffstat (limited to 'mapreduce/tests/test_extraction_cdx_grobid.py')
-rw-r--r--mapreduce/tests/test_extraction_cdx_grobid.py1
1 files changed, 0 insertions, 1 deletions
diff --git a/mapreduce/tests/test_extraction_cdx_grobid.py b/mapreduce/tests/test_extraction_cdx_grobid.py
index 514a830..1d32c9f 100644
--- a/mapreduce/tests/test_extraction_cdx_grobid.py
+++ b/mapreduce/tests/test_extraction_cdx_grobid.py
@@ -121,7 +121,6 @@ def test_parse_cdx_skip(job):
job.mapper_init()
-
print("warc format")
raw = "com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz"
info, status = job.mapper(None, raw).__next__()