Created
June 23, 2020 19:43
-
-
Save skhani/c2ceaa8c9ed7c980ac8571a56ac656a4 to your computer and use it in GitHub Desktop.
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 pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter | |
| from pdfminer.converter import TextConverter | |
| from pdfminer.layout import LAParams | |
| from pdfminer.pdfpage import PDFPage | |
| from io import BytesIO | |
| def pdf_to_text(path): | |
| manager = PDFResourceManager() | |
| retstr = BytesIO() | |
| layout = LAParams(all_texts=True) | |
| device = TextConverter(manager, retstr, laparams=layout) | |
| filepath = open(path, 'rb') | |
| interpreter = PDFPageInterpreter(manager, device) | |
| for page in PDFPage.get_pages(filepath, check_extractable=True): | |
| interpreter.process_page(page) | |
| text = retstr.getvalue() | |
| filepath.close() | |
| device.close() | |
| retstr.close() | |
| return text | |
| if __name__ == "__main__": | |
| text = pdf_to_text("yourfile.pdf") | |
| print(text) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment