summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJules Laplace <julescarbon@gmail.com>2019-02-10 17:26:21 +0100
committerJules Laplace <julescarbon@gmail.com>2019-02-10 17:26:21 +0100
commitef692647393a3a5ec5bdbc0bfbbd118b89da5669 (patch)
tree2981f6814af5d2d95e369878f0ed89724b5e2bf6
parent9c9b834222c47ad19eb562de3c7c9762dd0c99a6 (diff)
s2-extract-pdf-txt.py
-rw-r--r--scraper/s2-extract-pdf-txt.py2
1 files changed, 1 insertions, 1 deletions
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)