aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rwxr-xr-xmapreduce/extraction_cdx_grobid.py2
1 files changed, 1 insertions, 1 deletions
diff --git a/mapreduce/extraction_cdx_grobid.py b/mapreduce/extraction_cdx_grobid.py
index 227a026..040538c 100755
--- a/mapreduce/extraction_cdx_grobid.py
+++ b/mapreduce/extraction_cdx_grobid.py
@@ -163,7 +163,7 @@ class MRExtractCdxGrobid(MRJob):
extra=grobid_response.text)
info['grobid0:status'] = {'status': 'partial'}
- info['grobid0:tei_xml'] = grobid_response.text
+ info['grobid0:tei_xml'] = grobid_response.content
# Convert TEI XML to JSON
try: