1234567891011121314151617181920212223242526272829303132333435363738 |
- #! /usr/bin/env python
- import datetime
- import argparse
- from simplemediawiki import build_user_agent
- import ParabolaWiki
-
- if __name__ == "__main__":
- aparser = argparse.ArgumentParser(description="Download pages from Parabola Wiki and optimize them for offline browsing")
- aparser.add_argument("--output-directory", type=str, required=True, help="Path where the downloaded pages should be stored.")
- aparser.add_argument("--force", action="store_true", help="Ignore timestamp, always download the page from the wiki.")
- aparser.add_argument("--clean", action="store_true", help="Clean the output directory after downloading, useful for removing pages deleted/moved on the wiki. Warning: any unknown files found in the output directory will be deleted!")
- aparser.add_argument("--safe-filenames", action="store_true", help="Force using ASCII file names instead of the default Unicode.")
- args = aparser.parse_args()
- if args.force:
- epoch = datetime.datetime.utcnow()
- else:
- # this should be the date of the latest incompatible change
- epoch = datetime.datetime(2016, 3, 3, 18, 0, 0)
- user_agent = build_user_agent(__file__, ParabolaWiki.__version__, ParabolaWiki.__url__)
- aw = ParabolaWiki.ParabolaWiki(user_agent=user_agent, safe_filenames=args.safe_filenames)
- optimizer = ParabolaWiki.Optimizer(aw, args.output_directory)
- downloader = ParabolaWiki.Downloader(aw, args.output_directory, epoch, cb_download=optimizer.optimize_url)
- aw.print_namespaces()
- for ns in ["0", "4", "12", "14"]:
- downloader.process_namespace(ns)
- downloader.download_images()
- downloader.download_css()
- if args.clean:
- downloader.clean_output_directory()
|