Created
August 13, 2012 21:04
-
-
Save jjjake/3344096 to your computer and use it in GitHub Desktop.
Given an IA catalog.php URL, returns a list of dictionaries (1 dictionary/row).
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 python | |
import os, sys | |
import requests | |
import json | |
COOKIES = {'logged-in-sig': os.environ['LOGGED_IN_SIG'], | |
'logged-in-user': os.environ['LOGGED_IN_USER'], | |
'verbose': '1', | |
} | |
def get_rows(URL): | |
CATALOG_PARAMS = {'json': 1, 'output': 'json', 'callback': 'foo', | |
'verbose': 1} | |
req = requests.get(URL, params=CATALOG_PARAMS, cookies=COOKIES) | |
rows = [json.loads(x.strip(',').replace('])', '')) for x in | |
req.text.replace('foo','').split('\n') if len(x) > 20] | |
dict_list = [] | |
for row in rows: | |
catalog_dict = dict(identifier=row[0], | |
srvr=row[1], | |
cmd=row[2], | |
time=row[3], | |
submitter=row[4], | |
args=row[5], | |
extra=row[6]) | |
dict_list.append(catalog_dict) | |
return dict_list | |
# USAGE: | |
URL = 'http://www-tracey.us.archive.org/catalog.php?mode=users' | |
print get_rows(URL) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment