爬取糗事百科热图

完整代码

import requests
import re
from fake_useragent import UserAgent
import os
if not os.path.exists('./qiutu'):
    os.mkdir('./qiutu')
baseurl = 'https://www.qiushibaike.com/imgrank/page/'
headers = {
    'User-Agent': UserAgent().random
}
findImgSrc = r'<div class="thumb">.*?<img src="(.*?) alt="'


def getImage(baseurl, i):
    url = baseurl+str(i)
    respones = requests.get(url, headers=headers)
    images = re.findall(findImgSrc, respones.text, re.S)
    for image in images:
        url = 'https:'+image[:-1]
        respones_cp = requests.get(url=url, headers=headers)
        image_name = image.split('/')[-1]
        image_name = image_name[:20]
        image_path = './qiutu/'+image_name
        with open(image_path, 'wb') as fp:
            fp.write(respones_cp.content)
            print(image_name+'sucessfully download')


if __name__ == '__main__':
    for i in range(2, 10):
        getImage(baseurl, i)