在python中实现这一点很简单。
urlopen（）函数与不需要身份验证的代理透明地一起工作。在Unix或Windows环境中，在启动Python解释器之前，将http_proxy，ftp_proxy或gopher_proxy环境变量设置为标识代理服务器的URL。
# -*- coding: utf-8 -*-
import sys
from urllib import urlopen
from BeautifulSoup import BeautifulSoup
from Queue import Queue, Empty
from threading import Thread
visited = set()
queue = Queue()
def get_parser(host, root, charset):
def parse():
try:
while True:
url = queue.get_Nowait()
try:
content = urlopen(url).read().decode(charset)
except UnicodeDecodeError:
continue
for link in BeautifulSoup(content).findAll('a'):
try:
href = link['href']
except KeyError:
continue
if not href.startswith('http://'):
href = 'http://%s%s' % (host, href)
if not href.startswith('http://%s%s' % (host, root)):
continue
if href not in visited:
visited.add(href)
queue.put(href)
print href
except Empty:
pass
return parse
if __name__ == '__main__':
host, root, charset = sys.argv[1:]
parser = get_parser(host, root, charset)
queue.put('http://%s%s' % (host, root))
workers = []
for i in range(5):
worker = Thread(target=parser)
worker.start()
workers.append(worker)
for worker in workers:
worker.join()
602392714
清零编程群