1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
|
#!/usr/bin/env python
import sys
import re
import httplib
import os
# compile regular expression to pull out URLs in ITK
# The ignored characters an common delineators, and not strick to the standard
http_re = re.compile(r'(http://[^\s<>\{\}\|\]\[\)\("]*)')
http_dict = dict()
for arg in sys.argv[1:]:
if not os.path.isfile(arg):
continue
f = open(arg)
for l in f.readlines():
mo = http_re.search(l)
if mo is not None:
http_dict[mo.group(1)] = arg
f.close()
if len(http_dict) > 1:
print("Found ", len(http_dict), " unique URLS.")
# compile regular expression to pull out the server address and path
server_re = re.compile(r"http://([^/]+)(/?[^\s]*)")
for url, filename in http_dict.items():
mo = server_re.search(url)
server = mo.group(1)
path = mo.group(2)
try:
# print("Verifying URL: ", url,)
# connect to server and get the path
conn = httplib.HTTPConnection(server)
conn.request("GET", path)
r1 = conn.getresponse()
if r1.status == httplib.OK:
# URL is OK do nothing
# print(" URL: ", url, r1.status, r1.reason)
pass
elif r1.status == httplib.MOVED_PERMANENTLY:
print(filename, ": ERROR (URL needs update): ", url)
print(r1.status, r1.reason, " to: ", r1.getheader("location"))
elif r1.status == httplib.FOUND:
print(
filename,
": INFO URL: ",
url,
r1.status,
r1.reason,
" to: ",
r1.getheader("location"),
)
pass
elif r1.status == httplib.FORBIDDEN:
print(filename, ": INFO URL: ", url, r1.status, r1.reason)
pass
elif r1.status == httplib.NOT_FOUND:
print(filename, ": ERROR URL: ", url, r1.status, r1.reason)
else:
print(filename, ": UNKNOWN URL: ", url, '"', r1.status, '"', r1.reason)
pass
except Exception as e:
print()
print(filename, ": ERROR (exception): ", url)
print(e)
except:
print(filename, ": ERROR (exception): ", url)
print("Unexpected error:", sys.exc_info()[0])
raise
finally:
conn.close()
|
