爬虫爬取斗鱼小姐姐直播间的封面

# -*- coding: utf-8 -*-
"""
Created on Wed Jun 23 21:58:40 2021

@author: xfw
"""
import requests
import os
from urllib import request
import multiprocessing

# 定义默认爬取第一页
def get_douyu_pic(page=1):
	#请求头
    headers={ "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36"
    }
    # 链接
    url = f'https://www.douyu.com/gapi/rknc/directory/yzRec/{page}'
    #请求
    response = requests.get(url, headers=headers)
    print(response)
    if response.status_code == 200:
        print('okay')
    else:
        print('fail')
    girls = response.json()

    lst = girls['data']['rl']
    for girl in lst:
        name = girl['nn']
        img = girl['rs1']
        try:
            request.urlretrieve(img, f'douyu/{page}-{name}.png ')
            request.urlcleanup()
            print(f'/xixi/{page}-{name}.png ','   downloading')
        except:
            print('oh no!')


if __name__ == "__main__":
    if not os.path.exists('douyu'):
        os.mkdir('douyu')
    # 多进程爬取19页
    for i in range(1,20):
        multiprocessing.Process(target=get_douyu_pic, args=(i,)).start()