python爬虫二——数据解析

1.正则

爬取图片

import requests
import re
import os
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:87.0) Gecko/20100101 Firefox/87.0"
}
# url = 'https://pic.qiushibaike.com/system/pictures/12425/124253455/medium/BS3559JFPXJ1DILD.jpg'
# image_data = requests.get(url=url).content
# with open('./qiutu.jpg','wb') as fp:
#     fp.write(image_data)
if not os.path.exists('./qiutulibs'):   #创建文件夹
    os.mkdir('./qiutulibs')
url = 'https://www.qiushibaike.com/imgrank/page/3/'
page_text = requests.get(url=url,headers=headers).text

# <div class="thumb">
# <a href="/article/124244751" target="_blank">
# <img src="//pic.qiushibaike.com/system/pictures/12424/124244751/medium/7GJFY2TA3IC372SX.jpg" alt="糗事#124244751" class="illustration" width="100%" height="auto">
# </a>
# </div>
res = '<div class="thumb">.*?<img src="(.*?)" alt.*?</div>'
page_l