Created
April 28, 2021 12:29
-
-
Save lebedov/3518142a5c2431b8c9a28d323100558a to your computer and use it in GitHub Desktop.
How to use pdfbox's PDFTextStripper class in Python.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
""" | |
How to use pdfbox's PDFTextStripper class in Python. | |
""" | |
import pathlib | |
import pkg_resources | |
import re | |
import urllib.request | |
import appdirs | |
import jpype | |
import jpype.imports | |
import numpy as np | |
# Replace with path to pdfbox jar file: | |
a = appdirs.AppDirs('python-pdfbox') | |
cache_dir = pathlib.Path(a.user_cache_dir) | |
file_list = list(cache_dir.glob('pdfbox-app-*.jar')) | |
def f(s): | |
v = re.search('pdfbox-app-([\w\.\-]+)\.jar', s.name).group(1) | |
return pkg_resources.parse_version(v) | |
jpype.addClassPath(sorted(file_list, key=f)[-1]) | |
if not jpype.isJVMStarted(): | |
jpype.startJVM(jpype.getDefaultJVMPath(), '-Djava.awt.headless=true', convertStrings=False) | |
from java.awt.image import BufferedImage | |
from java.io import File | |
from org.apache.pdfbox.pdmodel import PDDocument | |
from org.apache.pdfbox.text import PDFTextStripper | |
def extract_text(in_file): | |
""" | |
Extract text of PDF file. | |
Parameters | |
---------- | |
in_file : str | |
Path to input PDF file. | |
Returns | |
------- | |
text : str | |
Extracted text. | |
""" | |
doc = PDDocument.load(File(in_file)) | |
pdf_text_stripper = PDFTextStripper() | |
text = pdf_text_stripper.getText(doc) | |
return str(text) | |
if __name__ == '__main__': | |
import os | |
import tempfile | |
import urllib | |
# Download sample multipage PDF: | |
data = urllib.request.urlopen('https://researchtorevenue.files.wordpress.com/2015/04/1r41ai10801601_fong.pdf').read() | |
fd, name = tempfile.mkstemp() | |
f = open(name, 'wb') | |
f.write(data) | |
f.close() | |
result = extract_text(name) | |
os.unlink(name) |
@lebedov Thank you again. You nailed it !!! The file was corrupted I downloaded it again and it's working now. Thank you !!!
Nice example, almost looks easier than using the CLI!
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
@sfinotti The file size looks suspiciously small - check that its SHA256 checksum satisfies what is listed on Apache's website using
sha256sum
. If it doesn't match, try downloading the jar file again (the script works fine with 2.0.26 on my system).