利用爬虫爬取网页数据
import re
import requests
a=int(input('请输入起始页码'))
b=int(input('请输入结束页码'))
for page in range(a,b):
url=f'http://www.netbian.com/index_{page}.htm'
headers={
'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Mobile Safari/537.36 Edg/122.0.0.0'
}
response=requests.get(url=url,headers=headers)
response.encoding=response.apparent_encoding
#img_info=re.findall('',response.text)
#正则表达式形式
img_info=re.findall(r'',response.text)
#print(img_info)
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#对响应先进行编码再进行解码
img_url=re.findall('target="_blank">