网络爬虫之规则——Requests库爬取性能分析

问题：爬取csdn网页100次所需时间

import requests
import time

def get_html(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "返回异常"

if __name__ == "__main__":
    url = "https://www.csdn.net"
    start = time.time()
    for i in range(100):
        get_html(url)
    end = time.time()
    t = end - start
    print("爬取100次" + url + "的时间为" + str(t)[0:5] + 's')

结果如下：

>>> 爬取100次https://www.csdn.net的时间为96.35s