Michele Weigle weiglemc

URI-Rs for LSU Women's Basketball Main Webpage

For each set, I'm also showing the number of mementos with HTTP 200 status per year in the Wayback Machine.

To query any of these in the Internet Archive's Wayback Machine, just add the prefix https://web.archive.org/web/*/

Table

Left-Aligned	Center Aligned	Right Aligned
col 3 is	some wordy text	$1600

	# grab-cdx.py

	from requests import Session
	from rich.console import Console
	from urllib.parse import urlencode

	URIR = "https://www.cnn.com/"
	FROM = "20150424"
	TO = "20220923"
	OTHER_PARAMS = "&from=" + FROM + "&to=" + TO + "&collapse=timestamp:8&filter=statuscode:200" # only one entry per day, 200 OK

	# run from untracked/html as
	# % python3 ../../capture-html.py < ../../cnn-to-request.txt >> ../../cnn-html-list.txt
	import sys
	import time
	import requests

	WAIT = 10 # seconds to wait between requests
	TIMEOUT = 60 # seconds to wait for timeout
	DONE_URI_LIST = "../../cnn-html-list.txt"

	# run the script on a set of URI-Ms:
	# python3 capture-requests.py < to-request.txt >> requests-log.txt

	# process the results and generate a new list of URI-Ms that were requested:
	# awk '{if ($1 ~ /cnn\.com(:80)?[\/]+$/ && $2 == "200") print $0}' requests-log.txt \| sort -t '/' -k 5 >! requests.txt

	# https://pypi.org/project/selenium-wire/#installation
	import sys
	import time
	from seleniumwire import webdriver # Import from seleniumwire