-
-
Save tlkahn/d587376ab8987067457a478f421ca64d 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
| #!/usr/bin/env python | |
| # parse_toc.py | |
| from pdfminer.pdfparser import PDFParser | |
| from pdfminer.pdfdocument import PDFDocument | |
| def parse(filename, maxlevel): | |
| fp = open(filename, 'rb') | |
| parser = PDFParser(fp) | |
| doc = PDFDocument(parser) | |
| outlines = doc.get_outlines() | |
| for (level, title, dest, a, se) in outlines: | |
| if level <= maxlevel: | |
| title_words = title \ | |
| .encode('utf8') \ | |
| .replace(b'\n', b'') \ | |
| .decode('utf8') \ | |
| .split()[1:] | |
| title = ' '.join(title_words) | |
| print('*' * level, title) | |
| if __name__ == '__main__': | |
| import sys | |
| if len(sys.argv) != 3: | |
| print('Usage: %s xxx.pdf level' % sys.argv[0]) | |
| sys.exit(2) | |
| parse(sys.argv[1], int(sys.argv[2])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
upgrade to work with python 3.7