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
import requests | |
import sys | |
import json | |
def waybackurls(host, with_subs): | |
if with_subs: | |
url = 'http://web.archive.org/cdx/search/cdx?url=*.%s/*&output=json&fl=original&collapse=urlkey' % host | |
else: | |
url = 'http://web.archive.org/cdx/search/cdx?url=%s/*&output=json&fl=original&collapse=urlkey' % host |
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
import requests | |
import re | |
import sys | |
from multiprocessing.dummy import Pool | |
def robots(host): | |
r = requests.get( | |
'https://web.archive.org/cdx/search/cdx\ | |
?url=%s/robots.txt&output=json&fl=timestamp,original&filter=statuscode:200&collapse=digest' % host) |
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
dc:14:de:8e:d7:c1:15:43:23:82:25:81:d2:59:e8:c0 | 245272 | |
---|---|---|
32:f9:38:a2:39:d0:c5:f5:ba:bd:b7:75:2b:00:f6:ab | 197846 | |
d0:db:8a:cb:74:c8:37:e4:9e:71:fc:7a:eb:d6:40:81 | 152046 | |
34:47:0f:e9:1a:c2:eb:56:eb:cc:58:59:3a:02:80:b6 | 140777 | |
df:17:d6:57:7a:37:00:7a:87:5e:4e:ed:2f:a3:d5:dd | 91904 | |
81:96:a6:8c:3a:75:f3:be:84:5e:cc:99:a7:ab:3e:d9 | 80499 | |
7c:a8:25:21:13:a2:eb:00:a6:c1:76:ca:6b:48:6e:bf | 78172 | |
1c:1e:29:43:d2:0c:c1:75:40:05:30:03:d4:02:d7:9b | 71851 | |
8b:75:88:08:41:78:11:5b:49:68:11:42:64:12:6d:49 | 70786 | |
c2:77:c8:c5:72:17:e2:5b:4f:a2:4e:e3:04:0c:35:c9 | 68654 |