eml by futakuro splitter

emlsplit.py

import sys
import re
from email.parser import BytesParser, Parser
from email.policy import default
from pathlib import Path
from urllib.parse import urlparse
from html.parser import HTMLParser

class URLConverter(HTMLParser):
    def __init__(self, mapping):
        super().__init__()
        self._mapping = mapping
        self._out = ''
    def handle_decl(self, decl):
        self._out = self._out + '<!' + decl + '>'
    def handle_starttag(self, tag, attrs):
        def mapper(attrs_):
            for (k, v) in attrs_:
                check = (k == 'src' or k == 'href') and v in self._mapping
                yield k, self._mapping[v] if check else v
        self._out = self._out + '<' + tag + ' ' + ' '.join(k + '="' + v + '"' for (k,v) in mapper(attrs)) + '>'
    def handle_endtag(self, tag):
        self._out = self._out + '</' + tag + '>'
    def handle_data(self, data):
        self._out = self._out + data
    def get_output(self):
        return self._out

def make_path(in_path: str) -> Path:
    if not in_path:
        return None
    url = urlparse(in_path)
    path = Path(url.path)
    if 'res' in path.parts:
        return Path('.').joinpath(path.parts[-1])
    else:
        return Path('.').joinpath(*path.parts[-2:])

def process(input: str):
    with open(input, 'rb') as fp:
        mapping = {}
        msg = BytesParser(policy=default).parse(fp)
        # 1st walk for making mapping
        for part in msg.walk():
            if not re.match(r'text', part.get_content_type()):
                url = part.get("Content-Location")
                loc = urlparse(url).path if url else None
                path = make_path(loc)
                mapping[url] = str(path)
        # 2nd walk for actual output
        for part in msg.walk():
            loc = part.get("Content-Location")
            loc = urlparse(loc).path if loc else None
            path = make_path(loc)
            print(part.get_content_type(), path)
            if path:
                if re.match(r'text', part.get_content_type()):
                    part.set_charset('cp932')
                content = part.get_content()
                if not path.parent.exists():
                    path.parent.mkdir()
                with open(path, 'wb') as out:
                    if type(content) == bytes:
                        out.write(part.get_content())
                    else:
                        parser = URLConverter(mapping)
                        parser.feed(part.get_content())
                        out.write(parser.get_output().encode('utf-8'))


if __name__ == "__main__":
    process(sys.argv[1])