python爬虫爬取图片无法显示问题

我本身是想实现，爬虫保存搜索而来的图片的。

正常一套流程，获取本页面html中的图像链接之后进行下载

却发现下下来的图片无法显示，并且转过txt之后是一大堆页面源代码

后来发现，实际上搜索出来的图片库获取的图片链接不是真正的源图片链接，点进去实际上再查看单张图片，然后再在里面获取图片链接才是源图片

于是进一步获取此网页的源图片链接。自此问题解决 

import requests
import urllib.request
import os
from bs4 import BeautifulSoup
import socket  # 超时跳过
import urllib.error  # 可能链接挂了
from tqdm import tqdm

def main(user_agent, noun, number, save_root):
    "(1)初始化"
    print("初始化...")

    url = ...

    headers = {
        'user-agent': user_agent
    }
    opener = urllib.request.build_opener()
    opener.addheaders = [('User-Agent', user_agent)]
    urllib.request.install_opener(opener)


    "(2)获取html"
    print("获取html...")
    response1 = requests.get(url=url,headers=headers)
    html1 = response1.text

    soup1 = BeautifulSoup(html1, 'html.parser')
    divs = soup1.find_all('div', class_='imgpt')  # 视具体网页而获取
 

    "(3)获取图片链接"
    print("获取链接与下载...")
    count = 1
    for div in divs:
        # 不是源地址，再次获取
        bing_url = '...' + div.find('a', class_="iusc").get('href')

        try:
            response2 = requests.get(bing_url, headers=headers)

            html2 = response2.text
            soup2 = BeautifulSoup(html2, 'html.parser')

            # 视具体网页而获取
            img_url = soup2.find('div', id="b_content").find('div', id='b_idpdata').get('data-firstimg') 
            img_url = img_url[img_url.index("thumbnailUrl")+len("thumbnailUrl")+3:img_url.index('fhs')-3]

            # 准备
            save_dir = os.path.join(save_root, noun)
            if not os.path.exists(save_dir):
                os.makedirs(save_dir)
            save_path = save_dir + '/%s-%d.jpg' % (noun, count)

            "(4)下载"
            socket.setdefaulttimeout(10)
            try:
                urllib.request.urlretrieve(img_url, save_path)
                print("%s-第%d张下载完毕, from：%s" % (noun, count, img_url))
                count += 1
            except urllib.error.HTTPError:
                print("链接挂了")
            except socket.timeout:
                try:
                    urllib.request.urlretrieve(img_url, save_path)
                    print("%s-第%d张下载完毕, from：%s" % (noun, count, img_url))
                    count += 1
                except socket.timeout:
                    print("\n下载超时，跳过")
            except urllib.error.ContentTooShortError:
                try:
                    urllib.request.urlretrieve(img_url, save_path)
                    print("%s-第%d张下载完毕, from：%s" % (noun, count, img_url))
                    count += 1
                except urllib.error.ContentTooShortError:
                    print("\n似乎网络不太好？已中断")
            except:
                print("未知错误，跳过")
        except:
            print("远程主机强迫关闭了一个现有的连接，跳过")
            pass


if __name__ == "__main__":
    user_agent = ...
    amount = 10
    save_root = 'images'

    print("Download images from noun_vocab: ")
    # noun_file = open('../../data/pororo_data/nouns_vocab.txt', 'r').readlines()
    clean_noun_file = open('../../data/pororo_data/nouns_vocab_choose.txt', 'r+')
    for line in tqdm(clean_noun_file):
        noun = line.replace('\n', '')
        main(user_agent, noun, amount, save_root)
    clean_noun_file.close()