diff options
Diffstat (limited to 'scraper')
| -rw-r--r-- | scraper/s2-extract-pdf-txt.py | 2 |
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) |
