From ef692647393a3a5ec5bdbc0bfbbd118b89da5669 Mon Sep 17 00:00:00 2001 From: Jules Laplace Date: Sun, 10 Feb 2019 17:26:21 +0100 Subject: s2-extract-pdf-txt.py --- scraper/s2-extract-pdf-txt.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scraper/s2-extract-pdf-txt.py b/scraper/s2-extract-pdf-txt.py index 4537d265..269bb29e 100644 --- a/scraper/s2-extract-pdf-txt.py +++ b/scraper/s2-extract-pdf-txt.py @@ -20,7 +20,7 @@ def extract_pdf_txt(): for fn in glob.iglob('datasets/s2/pdf/*/*/*.pdf'): path = os.path.dirname(fn) out_fn = os.path.join(path, 'paper.txt') - if not os.path.exists(): + if not os.path.exists(out_fn): fns.append((fn, out_fn)) parallelize(extract_txt, paths) -- cgit v1.2.3-70-g09d2