（47）-- 用线程简单爬取网络页面

#用线程简单爬取网络页面

from urllib import request
from multiprocessing import Process,Queue

def downloader(url_queue):
    p = url_queue.get()
    response = request.urlopen(p)

    html = response.read()
    content = html.decode("utf-8")
    path_list=p.split('/')
    file_name = path_list[-1]

    with open(file_name,"w",encoding = "utf-8") as f:
        f.write(content)


if __name__ == "__main__":

    url_queue = Queue()

    s1 = "http://www.langlang2017.com/index.html"
    s2 = "http://www.langlang2017.com/route.html"
    s3 = "http://www.langlang2017.com/FAQ.html"
    url_queue.put(s1)
    url_queue.put(s2)
    url_queue.put(s3)

    p1 = Process(target=downloader, args=(url_queue, ))
    p1.start()

    p2 = Process(target=downloader, args=(url_queue, ))
    p2.start()

    p3 = Process(target=downloader, args=(url_queue, ))
    p3.start()

兄弟连学python

Python学习交流、资源共享群：563626388 QQ