Skip to content

Commit

Permalink
Use concrete path
Browse files Browse the repository at this point in the history
  • Loading branch information
traverseda committed Aug 15, 2021
1 parent aba1192 commit 702a229
Showing 1 changed file with 3 additions and 2 deletions.
5 changes: 3 additions & 2 deletions textract/parsers/pdf_parser.py
Expand Up @@ -48,13 +48,14 @@ def extract_pdfminer(self, filename, **kwargs):
#Nested try/except loops? Not great
#Try the normal pdf2txt, if that fails try the python3
# pdf2txt, if that fails try the python2 pdf2txt
pdf2txt_path = shutil.which('pdf2txt.py')
try:
stdout, _ = self.run(['pdf2txt.py', filename])
except OSError:
try:
stdout, _ = self.run(['python3','pdf2txt.py', filename])
stdout, _ = self.run(['python3',pdf2txt_path, filename])
except ShellError:
stdout, _ = self.run(['python2','pdf2txt.py', filename])
stdout, _ = self.run(['python2',pdf2txt_path, filename])
return stdout

def extract_tesseract(self, filename, **kwargs):
Expand Down

0 comments on commit 702a229

Please sign in to comment.