nemo-odf-to-txt

#!/usr/bin/python3

import sys
import zipfile
from pathlib import Path
from html.parser import HTMLParser

class Parser(HTMLParser):
    parsed = []
    get_next_data = False
    concat_next_data = False

    def handle_starttag(self, tag, attrs):
        if tag.startswith("text") or tag.startswith("meta"):
            if tag == "text:s":
                self.concat_next_data = True
            self.get_next_data = True

    def handle_endtag(self, tag):
        pass

    def handle_data(self, data):
        if self.get_next_data:
            if data != "\n":
                if self.concat_next_data:
                    self.parsed[-1] += " " + data
                    self.concat_next_data = False
                else:
                    self.parsed.append(data.strip())
                self.get_next_data = False

path = sys.argv[1]

parser = Parser()
zipfile = zipfile.ZipFile(path)
files = zipfile.infolist()

for f in files:
    if f.filename in ("meta.xml", "content.xml"):
        contents = zipfile.read(f.filename).decode()
        parser.feed(contents)
        if len(parser.parsed) == 0:
            continue

        out_str = ", ".join(parser.parsed)
        print(f"{Path(f.filename).stem}: {out_str}\n", flush=True, file=sys.stdout)
        parser.parsed = []
exit(0)