爬虫问题

groldd

import urllib.request
import re

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:56.0) Gecko/20100101 Firefox/56.0')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

def get_img(html):
    p = r'<img class="BDE_Image" src="[^"]+\.jpg"'
    imglist = re.findall(p, html)
    '''
    for each in imglist:
        print(each)

    '''

    for each in imglist:
        filename = each.split("/")[-1]
        urllib.request.urlretrieve(each, filename, None)

  
if __name__ == '__main__':
    url = "http://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&word=meinv"
    get_img(open_url(url))

groldd

代码如上

但是什么都没有得出来

$DIM

首先是有图片的，可能返回的链接跟你想的不一样，后面获取图片正则也变一下，如下：
请求返回的代码：
{"thumbURL":"http://img5.imgtn.bdimg.com/it/u=3976670166,3864977643&fm=27&gp=0.jpg","replaceUrl": [{"ObjURL":"http:\/\/img1.imgtn.bdimg.com\/it\/u=3976670166,3864977643&fm=214&gp=0.jpg","FromURL":"http:\/\/hot.com-web.com.tw\/read.php\/1667.htm"}
baidu网页显示如下：