使用python,利用requests re模块下载文件
import requests
import re
#获取url
url = "https://www.openvswitch.org/support/dist-docs/"
#获取数据
data = requests.get(url).text
#提取数据,(?P<url>.*?)将匹配的(.*?)的值付给变量url
result = re.findall(r'<a href="(?P<url>.*?).pdf">',data)
print(result)
for i in result:
#拼接下载的链接
new_url = url + i + ".pdf"
filename = i + ".pdf"
#print(new_url)
#访问连接
result = requests.get(new_url)
#下载文件,并保存
with open(filename,mode="wb") as f:
f.write(result.content)