Python之爬虫-正则解析-爬取糗图
import requests
import re
import os
if __name__ == '__main__':
if not os.path.exists('./qiutuLibs'):
os.mkdir('./qiutuLibs')
//要访问的地址
url = 'https://www.qiushibaike.com/imgrank/'
//请求头
header = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36 Edg/94.0.992.31'
}
page_text = requests.get(url=url, headers=header).text
ex = '<div class="thumb">.*?<img src="(.*?)" alt.*?</div>'
img_src_list = re.findall(ex,page_text,re.S)
print(img_src_list)
for src in img_src_list:
src = 'https:' + src
img_data = requests.get(url=src,headers=header).content
img_name = src.split('/')[-1]
imgPath = './qiutuLibs/' + img_name
with open(imgPath,'wb')as fp:
fp.write(img_data)
print(img_name,'下载成功!!!')