blob: 7da21254a022190ac53beca51593a5c763fdcdab (
plain)
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
|
#!/usr/bin/env python3
import argparse
import re
import sys
import urllib.request
def get(url):
page = urllib.request.urlopen(url)
byts = page.read()
s = byts.decode("utf8")
page.close()
return s
def extract_links(content):
links = re.findall('"((http|ftp)s?://.*?)"', content)
return links
def extract_emails(content):
emails = re.findall('([\w\.,]+@[\w\.,]+\.\w+)', content)
return emails
if __name__ == '__main__':
cli = argparse.ArgumentParser(description='Scrape a web page for stuff.')
cli.add_argument('url', metavar='URL', type=str, help='url to fetch')
cli.add_argument('-e', '--emails', action="store_true", help='get emails')
cli.add_argument('-l', '--links', action="store_true", help='get links')
args = cli.parse_args()
if not (args.emails or args.links):
cli.error("must specify either -e or -l")
content = get(args.url)
if args.emails:
emails = extract_emails(content)
if len(emails) == 0:
print("found no emails")
else:
print("found {} emails:".format(len(emails)))
for email in emails:
print(" {}".format(email))
if args.links:
links = extract_links(content)
if len(links) == 0:
print("found no links")
else:
print("found {} links:".format(len(links)))
for link in links:
print(" {}".format(link[0]))
|
