Last active
November 18, 2025 03:14
-
-
Save drelatgithub/6f2888c2109f29206786105f2d00db5e to your computer and use it in GitHub Desktop.
Docin document downloader
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
| ############################################################################### | |
| # | |
| # Docin document downloader | |
| # | |
| # Valid as of 2022-12-13 | |
| # | |
| ############################################################################### | |
| import argparse | |
| import os | |
| from types import SimpleNamespace | |
| import urllib.request | |
| conf = SimpleNamespace( | |
| docin_pid = 0, | |
| output_dir = "" | |
| ) | |
| def download_image(pid): | |
| i = 0 | |
| while True: | |
| i += 1 | |
| try: | |
| urllib.request.urlretrieve( | |
| "http://211.147.220.164/index.jsp?file={}&pageno={}".format(pid, i), | |
| os.path.join(conf.output_dir, "{}.png".format(i)) | |
| ) | |
| except urllib.error.HTTPError: | |
| break | |
| else: | |
| print("Page", i, "saved.") | |
| if __name__ == "__main__": | |
| # Parse the arguments | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument("docin_pid", type=str, help="The number after \"p-\" in docin url") | |
| parser.add_argument("output_dir", type=str, help="The output directory") | |
| args = parser.parse_args() | |
| conf.docin_pid = args.docin_pid | |
| conf.output_dir = args.output_dir | |
| # Do the work | |
| download_image(conf.docin_pid) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
https://www.docin.com/p-4780561796.html
这个链接没法使用,有办法吗?