nadya-p
/ pdf_to_text.py
Last active
August 15, 2022 04:42
Extract text contents of PDF files recursively
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
| from tika import parser | |
| import os | |
| def extract_text_from_pdfs_recursively(dir): | |
| for root, dirs, files in os.walk(dir): | |
| for file in files: | |
| path_to_pdf = os.path.join(root, file) | |
| [stem, ext] = os.path.splitext(path_to_pdf) | |
| if ext == '.pdf': |