xpath爬取图片，得不到src ，python求解决

import requests
from lxml import etree
def main():
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3883.400 QQBrowser/10.8.4559.400'}
    url = "https://pic.sogou.com/pics?query=%E4%BA%94%E6%98%9F%E7%BA%A2%E6%97%97%E5%9B%BE%E7%89%87&rawQuery=%E4%BA%94%E6%98%9F%E7%BA%A2%E6%97%97%E5%9B%BE%E7%89%87&st=255&mood=5&dm=0&mode=1"
    resp = requests.get(url, headers=headers)
    resp.encoding = "utf-8"
    child_tree = etree.HTML(resp.text)
    imgs = child_tree.xpath('//div[@class="figure-result"]//a/img')
    for img in imgs:
        src = img.xpath('./@src')
        print(src)

if __name__ == '__main__':
    main()

图片是js解析出来的，xpath无效，数据在js变量里面，正则提取下数据用json.loads加载获取

代码如下

import requests
import re
import json
def main():
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3883.400 QQBrowser/10.8.4559.400'}
    url = "https://pic.sogou.com/pics?query=%E4%BA%94%E6%98%9F%E7%BA%A2%E6%97%97%E5%9B%BE%E7%89%87&rawQuery=%E4%BA%94%E6%98%9F%E7%BA%A2%E6%97%97%E5%9B%BE%E7%89%87&st=255&mood=5&dm=0&mode=1"
    resp = requests.get(url, headers=headers)
    resp.encoding = "utf-8"

    jsonstr=re.findall(r'window\.__INITIAL_STATE__=(.+?);\(function\(\){var s;',resp.text,re.S)[0]
    
    data=json.loads(jsonstr)
    for item in data['searchList']['searchList']:
        print(item['title'])
        print(item['picUrl'])

    '''
    child_tree = etree.HTML(resp.text)
    #imgs = child_tree.xpath('//div[@class="figure-result"]//a/img')
    #for img in imgs:
    #    src = img.xpath('./@src')
        print(src)
    '''
 
if __name__ == '__main__':
    main()
 

可能是反爬了，你输出resp.text看看响应内容和你网页看到是不是一样

麻烦把imgs输出一下看看

您好，我是有问必答小助手，您的问题已经有小伙伴帮您解答，感谢您对有问必答的支持与关注！
PS：问答VIP年卡 【限时加赠：IT技术图书免费领】，了解详情>>> https://vip.csdn.net/askvip?utm_source=1146287632