Created
September 24, 2022 21:54
-
-
Save edsu/97006eccb0f4884df850d3a20ad6db67 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 demonstrates an inconsistency in results from the Internet Archive CDX | |
# API when querying by scopeType=domain vs scopeType=prefix. For context see: | |
# | |
# https://inkdroid.org/2022/09/24/pdfs/ | |
# | |
# Note: you'll need to | |
# | |
# pip install git+https://github.com/edsu/wayback.git@t88-invalid-month | |
# | |
# until https://github.com/edgi-govdata-archiving/wayback/issues/88 is fixed | |
# | |
import pandas | |
from urllib.parse import urlparse | |
from wayback import WaybackClient | |
ia = WaybackClient() | |
prefix = pandas.DataFrame(ia.search('assets.lapdonline.org', matchType='prefix')) | |
domain = pandas.DataFrame(ia.search('lapdonline.org', matchType='domain')) | |
get_host = lambda s: urlparse(s).netloc | |
prefix['hostname'] = prefix.url.apply(get_host) | |
domain['hostname'] = domain.url.apply(get_host) | |
print(prefix.hostname.value_counts()) | |
print(domain.hostname.value_counts()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment