Python - 爬取图片并下载到本地

谁践踏了优雅 2023-07-18 14:13 39阅读 0赞

import requests             #用来模拟浏览器发送网络请求
    from lxml import etree      #解析数据
    from urllib import request  #下载保存urlretrive()
    import time                 #time.sleep让程序延迟几秒再进行
    
    # 函数的封装 def
    def huya_spider():
        # 请求数据：
        url = 'https://www.huya.com/g/2168#tag2609'
        User_Agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36"
        headers = {
        
            'User_Agent':User_Agent
        }
        res = requests.get(url)
        result = res.text
        print(res)
    
    
        data = etree.HTML(result)
        alist = data.xpath('//img[@class="pic"]')
    
        cnt = 0
    
        for woman in alist:
            cnt = cnt + 1
            # 通过已经筛选的数据进行获取对应的图片
            img = woman.xpath('./@data-original')[0]
            img = img.split("?")[0]
    
            #进行保存数据
            name = woman.xpath('./@alt')[0]
    
            path = 'D:\\img\\'
    
            #下载保存
            #异常处理
            try:
                print(img)
                path2 = path + str(cnt) + ".png"
                print(path2)
                request.urlretrieve(img, path2)
            except Exception as e:
                print(e)
                pass
    
            #显示打印进度
            # print("<%s> 下载完毕！" % name)
    
            time.sleep(3)
    
    
    huya_spider()
    
    # print("Hello World!")

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0JsZXNzaW5nWFJZ_size_16_color_FFFFFF_t_70][]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0JsZXNzaW5nWFJZ_size_16_color_FFFFFF_t_70]: /images/20230528/8fa7495b0c074cbd80111d97e172fdef.png