Last active
April 22, 2022 17:13
-
-
Save edsu/4ef1a23feb60f456d7a4fbaf4da28e7f to your computer and use it in GitHub Desktop.
This file contains 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
#!/usr/bin/env python3 | |
# This is an example of seeing what unique HTML webpages there are in the | |
# Wayback Machine for the http://myshtetl.org/ website after 2022-03-01. | |
from wayback import WaybackClient | |
wb = WaybackClient() | |
pages = set() | |
for rec in wb.search('http://myshtetl.org/', matchType='prefix', from_date='2022-03-01'): | |
if 'html' in rec.mime_type and rec.status_code == 200 and rec.url not in pages: | |
pages.add(rec.url) | |
print(rec.url) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment