Created
August 7, 2016 12:21
-
-
Save hghwng/324cc28b007a8f650ce3aac5df099ef8 to your computer and use it in GitHub Desktop.
Convert Dynalist flavored OPML to Org Mode
This file contains hidden or 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 | |
| import bs4 | |
| def convert_element(lines, level=1): | |
| result = '' | |
| for line in lines: | |
| if not isinstance(line, bs4.element.Tag) or \ | |
| line.name != 'outline': | |
| continue | |
| result += '*' * level + ' ' + line.attrs.get('text', '') + '\n' | |
| if 'note' in line.attrs: | |
| result += line.attrs['note'].replace('\r', '\n') + '\n' | |
| result += convert_element(line.children, level + 1) | |
| return result | |
| def convert_file(path): | |
| root = bs4.BeautifulSoup(open(path), "lxml") | |
| return convert_element(root.select('html body opml')[0]) | |
| def main(): | |
| import sys | |
| output_path = sys.argv[1][:-4] + 'org' | |
| result = convert_file(sys.argv[1]) | |
| open(output_path, 'w').write(result) | |
| if __name__ == '__main__': | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thanks @hghwng and @d4h0!
I needed
bs4andlxmltoo, thuspip install pypandoc bs4 lxml. (Plusbrew install pandoc parallelon macOS.)