使用socket和线程池爬取数据

使用socket和线程池爬取数据

# 使用socket和线程池爬取数据
import socket
from urllib.parse import urlparse


def get_url(url):
    #通过socket请求html
    url = urlparse(url)
    host = url.netloc# 提取主域名
    path = url.path
    if path == "":
        path = "/"

    #建立socket连接
    client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    # client.setblocking(False)
    client.connect((host, 80)) #阻塞不会消耗cpu

    #不停的询问连接是否建立好， 需要while循环不停的去检查状态
    #做计算任务或者再次发起其他的连接请求

    client.send("GET {} HTTP/1.1\r\nHost:{}\r\nConnection:close\r\n\r\n".format(path, host).encode("utf8"))

    data = b""
    while True:
        d = client.recv(1024)
        if d:
            data += d
        else:
            break

    data = data.decode("utf8")
    html_data = data.split("\r\n\r\n")[1]# 去掉HTTP请求头
    # print(data)
    print(html_data)
    client.close()

if __name__ == "__main__":
    import time
    start_time = time.time()
    # pip install threadpool
    import threadpool
    pool = threadpool.ThreadPool(10)
    urllist = []
    for i in range(2,20):
        url = "xxx/?page={}/".format(i)
        urllist.append(url)

    requests = threadpool.makeRequests(get_url,urllist)
    [pool.putRequest(req) for req in requests]
    pool.wait()

    # for url in range(2,5):
    #     url = "xxx/?page={}/".format(url)
    #     get_url(url)
    print(time.time()-start_time)