README.md

An extremely hacky, quickly thrown together script to extract various revisios of a specific Discourse post on discourse.ubuntu.com. Uses the "markdown diff" to extract the "current" revision and dumps them to individual markdown files

Does Discourse actually have an API for this? I couldn't find it...

discourse_revs.py

#!/usr/bin/python3

import sys
import json
from pathlib import Path
from urllib.request import urlopen
from html.parser import HTMLParser


class TableParser(HTMLParser):
    def __init__(self, column):
        super().__init__()
        self.extract_column = column
        self.current_col = 0
        self.state = 'top'
        self.content = ''

    def handle_starttag(self, tag, attrs):
        if tag == 'table' and self.state == 'top':
            self.content = ''
            self.state = 'table'
        elif tag == 'tr' and self.state == 'table':
            self.state = 'tr'
            self.current_col = 0
        elif tag == 'td' and self.state == 'tr':
            self.current_col += 1

    def handle_endtag(self, tag):
        if tag == 'tr' and self.state == 'tr':
            self.state = 'table'
        elif tag == 'table' and self.state == 'table':
            self.state = 'top'

    def handle_data(self, data):
        if self.current_col == self.extract_column:
            self.content += data


def main():
    for rev in range(96, 107):
        parser = TableParser(column=2)
        with urlopen(f'https://discourse.ubuntu.com/posts/120902/revisions/{rev}.json') as fp:
            data = json.load(fp)
            changes = data['body_changes']['side_by_side_markdown']
            parser.feed(changes)
            Path(f'revision{rev}.md').write_text(parser.content)


if __name__ == '__main__':
    sys.exit(main())