爬取百度图片并把图片存到本地

た入场券 2023-05-30 09:24 23阅读 0赞

爬取百度图片并把图片存到本地：  
用到的模块：

1.  re
2.  requests
3.  urllib
4.  bs4
5.  os

import re
    import requests
    from urllib import error
    from bs4 import BeautifulSoup
    import os
    
    num = 0
    numPicture = 0
    file = ''
    List = []
    
    
    def Find(url):
        global List
        print('正在检测图片总数，请稍等.....')
        t = 0
        i = 1
        s = 0
        while t < 1000:
            Url = url + str(t)
            try:
                Result = requests.get(Url, timeout=7)
            except BaseException:
                t = t + 60
                continue
            else:
                result = Result.text
                pic_url = re.findall('"objURL":"(.*?)",', result, re.S)  # 先利用正则表达式找到图片url
                s += len(pic_url)
                if len(pic_url) == 0:
                    break
                else:
                    List.append(pic_url)
                    t = t + 60
        return s
    
    
    def recommend(url):
        Re = []
        try:
            html = requests.get(url)
        except error.HTTPError as e:
            return
        else:
            html.encoding = 'utf-8'
            bsObj = BeautifulSoup(html.text, 'html.parser')
            div = bsObj.find('div', id='topRS')
            if div is not None:
                listA = div.findAll('a')
                for i in listA:
                    if i is not None:
                        Re.append(i.get_text())
            return Re
    
    
    def dowmloadPicture(html, keyword):
        global num
        # t =0
        pic_url = re.findall('"objURL":"(.*?)",', html, re.S)  # 先利用正则表达式找到图片url
        print('找到关键词:' + keyword + '的图片，即将开始下载图片...')
        for each in pic_url:
            print('正在下载第' + str(num + 1) + '张图片，图片地址:' + str(each))
            try:
                if each is not None:
                    pic = requests.get(each, timeout=7)
                else:
                    continue
            except BaseException:
                print('错误，当前图片无法下载')
                continue
            else:
                string = file + r'\\' + keyword + '_' + str(num) + '.jpg'
                fp = open(string, 'wb')
                fp.write(pic.content)
                fp.close()
                num += 1
            if num >= numPicture:
                return
    
    
    if __name__ == '__main__':  # 主函数入口
        word = input("请输入搜索关键词(可以是人名，地名等): ")
        # 比如百度图片上搜索：苹果
        # add = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=%e8%8b%b9%e6%9e%9c&pn=120'
        url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
        tot = Find(url)
        Recommend = recommend(url)  # 记录相关推荐
        print('经过检测{}类图片共有{}张'.format(word, tot))
        numPicture = int(input('请输入想要下载的图片数量： '))
        file = input('请建立一个存储图片的文件夹，输入文件夹名称即可：')
        y = os.path.exists(file)
        if y == 1:
            print('该文件已存在，请重新输入')
            file = input('请建立一个存储图片的文件夹，)输入文件夹名称即可')
            os.mkdir(file)
        else:
            os.mkdir(file)
        t = 0
        tmp = url
        while t < numPicture:
            try:
                url = tmp + str(t)
                result = requests.get(url, timeout=10)
                print(url)
            except error.HTTPError as e:
                print('网络错误，请调整网络后重试')
                t = t + 60
            else:
                dowmloadPicture(result.text, word)
                t = t + 60
    
        print('当前搜索结束，感谢使用')
        print('猜你喜欢')
        for re in Recommend:
            print(re, end=' ')

执行结果如下，比如搜索杨树：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2N1aV95b25naHVh_size_16_color_FFFFFF_t_70]

存到本地的效果如下图：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2N1aV95b25naHVh_size_16_color_FFFFFF_t_70 1]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2N1aV95b25naHVh_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20191109133141984.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2N1aV95b25naHVh,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2N1aV95b25naHVh_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20191109133411189.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2N1aV95b25naHVh,size_16,color_FFFFFF,t_70