python 进程

1创建一个爬虫程序

import requests
urls = [
    'https://www.cnblogs.com/#p{page}'
    for page in range(1, 50+1)
]

def craw(url):
    r = requests.get(url)
    print(url, len(r.text))

craw(urls[0])

2定义单进程和多进程

import blob_spider
import threading
import time

def single_thread():
    print("singe_thread begin")
    for url in blob_spider.urls:
        blob_spider.craw(url)
    print("singe_thread end")


def multi_thread():
    print("multi_thread begin")
    threads = []
    for url in blob_spider.urls:
        threads.append(
            threading.Thread(target=blob_spider.craw, args=(url, )) # 创建线程
        )

    for thread in threads:
        thread.start()

    for thread in threads:
        thread.join()
    print("multi_thread end")

if __name__ == "__main__":
    start = time.time()
    single_thread()
    end = time.time()
    print("single_thread用时：{}".format(end-start))
    start = time.time()
    multi_thread()
    end = time.time()
    print("multi_thread用时：{}".format(end - start))