import requests
import re
#获取
def getHTMLText(url, loginheaders):
    try:
        r = requests.get(url, headers=loginheaders, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""
#url与header
url = 'http://news.fzu.edu.cn/'
loginheaders = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36',
}
data = getHTMLText(url,loginheaders)
tdlist1 = re.findall(r'src=".*.jpg', data)
#print(tdlist1)
#去掉前面的src，最后与网页组成图片的正确路径
data1 = []
for i in range(len(tdlist1)):
    flag = 'http://news.fzu.edu.cn'+tdlist1[i][5:]
#    print(flag)
    res = requests.get(flag)
    with open("picture/{}.jpg".format(i), "wb") as f:
        f.write(res.content)
    print("成功下载")
#print(data1)