爬虫实战---爬取图片

爬虫实战---爬取图片

---

import requests
import re
for page in range(1,11):
    if page==1:
        url="http://www.netbian.com/meinv/index.htm"
    else:
        url=f'http://www.netbian.com/meinv/index_{page}.htm'
    headers={
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36 Core/1.94.178.400 QQBrowser/11.2.5170.400'
    }
 
    response=requests.get(url,headers=headers)
    response.encoding=response.apparent_encoding
    img_info=re.findall('<a href="(.*?)" title=".*?" target="_blank"><img src=".*?" alt="(.*?)" />',response.text)
	#(.*?)表示我们要的信息，.*?表示要查找的信息
    for link,title in img_info:
        link_url='http://www.netbian.com'+link
        response_1 = requests.get(url=link_url,headers=headers)
        response_1.encoding=response_1.apparent_encoding
        img_url=re.findall('target="_blank"><img src="(.*?)" alt=".*?"',response_1.text)[0]
        print(img_url)
        img_content = requests.get(url=img_url,headers=headers).content
        with open('img\\'+title+'.jpg',mode='wb') as f:
            f.write(img_content)