Created
May 7, 2015 13:55
-
-
Save recall704/578cc46ab191557c2424 to your computer and use it in GitHub Desktop.
爬取 http://pachong.org/ 中的代理ip 和 port
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
#coding:utf-8 | |
import re | |
import requests | |
url = 'http://pachong.org/high.html' | |
req = requests.get(url) | |
if req.status_code == 200: | |
html = req.text | |
else: | |
html = '' | |
# 匹配ip 和 端口对应 js | |
p = re.compile(r'''<tr data-id="\d+" data-type=\"high\">.*?<td.*?</td>.*?<td>(?P<ip>.*?)</td>.*?write\((?P<port>.*?)\);</script>''',re.S) | |
p2 = re.compile(r'var.*?;') | |
l1 = p.findall(html) | |
l2 = p2.findall(html) | |
l3 = [] | |
for l in l2: | |
temp = l.strip('var') | |
temp = temp.strip() | |
l3.append(temp) | |
for l in l3: | |
exec(l) | |
# print l1 | |
result = [] | |
for l_t in l1: | |
if isinstance(l_t[1],basestring): | |
port_str = 'port=' + l_t[1] | |
exec(port_str) | |
t = (l_t[0],port) | |
result.append(t) | |
else: | |
pass | |
print result |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment