import requests
import re
import os
if __name__ == '__main__':
url = 'https://www.qiushibaike.com/imgrank/' #热图页url
headers ={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36'
}
#创建一个文件夹保存所有的图片
if not os.path.exists('./images'):
os.mkdir('./images')
#使用通用爬虫对整个页面进去爬取
page_text = requests.get(url=url,headers=headers).text
#对当前页面进行解析
'''
<div class="thumb">
<a href="/article/123730840" target="_blank">
<img src="//pic.qiushibaike.com/system/pictures/12373/123730840/medium/BVB7JAZ3F1ABVJQ2.jpg" alt="糗事#123730840" class="illustration" width="100%" height="auto">
</a>
</div>
'''
#创建正则表达式
ex = '<div class="thumb">.*?<img src="(.*?)" alt=.*?</div>'
#获取当前页的图片的地址列表
img_src_list = re.findall(ex,page_text,re.S) #re.S表示多行匹配
for src in img_src_list:
src = 'https:'+src
#请求数据。context返回二进制数据
image_data = requests.get(url=src,headers=headers).content
#生成图片名称
image_name = src.split('/')[-1]
#图片存储的路径
image_path = './images/'+image_name
with open(image_path,'wb') as fp:
fp.write(image_data)
print(image_name,'下载成功!!')
爬虫学习-爬取图片信息
最新推荐文章于 2022-02-05 11:27:54 发布