diff options
Diffstat (limited to 'mapreduce/extraction_cdx_grobid.py')
| -rwxr-xr-x | mapreduce/extraction_cdx_grobid.py | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/mapreduce/extraction_cdx_grobid.py b/mapreduce/extraction_cdx_grobid.py index a4a13f8..63f290a 100755 --- a/mapreduce/extraction_cdx_grobid.py +++ b/mapreduce/extraction_cdx_grobid.py @@ -61,6 +61,7 @@ class MRExtractCdxGrobid(MRJob): r = requests.post(self.options.grobid_uri + "/api/processFulltextDocument", files={'input': content}) if r.status_code is not 200: + # if invalid file, get a 400 with JSON body with 'description' key (and others) # XXX: return None return r |