Download files referenced in Slack JSON export

slack_file_downloader.py

import os
import argparse
import json

import requests


class SlackFileDownloader:
    def __init__(self, output_dir, slack_token):
        self.output_dir = output_dir
        self.slack_token = slack_token

    def parse_export(self, export_file):
        with open(export_file, 'r') as f:
            content = f.read()
        events = json.loads(content)
        for event in events:
            self.process_event(event)

    def process_event(self, event):
        event_file = event.get('file')
        if event_file:
            file_url = event_file.get('url_private')
            file_name = event_file.get('name')
            self.download_file(file_url, file_name)

    def download_file(self, url, name):
        print(f"Downloading file: {name}")
        headers = {'Authorization': f"Bearer {self.slack_token}"}
        r = requests.get(url, stream=True, headers=headers)
        save_path = os.path.join(self.output_dir, name)
        os.makedirs(os.path.dirname(save_path), exist_ok=True)
        with open(save_path, 'wb') as f:
            for chunk in r.iter_content(chunk_size=1024):
                if chunk:
                    f.write(chunk)


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Download file attachments related to Slack export')
    parser.add_argument('-f', '--file', help='Exported Slack JSON', required=True)
    parser.add_argument('-t', '--token', help='Slack API token (legacy)', required=True)
    parser.add_argument('-o', '--output', help='Output directory', default="files")
    args = parser.parse_args()
    slack_downloader = SlackFileDownloader(output_dir=args.output, slack_token=args.token)
    slack_downloader.parse_export(args.file)

Slack data can be exported using a tool like slack-history-export. Script requires a legacy Slack API token which can be obtained here.