Python3实现批量下载百度搜索图片

快来打我* 2022-06-04 06:27 274阅读 0赞

# ** Python3实现批量下载百度搜索图片** #

**目录**

Python3实现批量下载百度搜索图片

1.通过关键字下载百度搜索的图片

2.根据链接URL下载图片

--------------------

## 1.通过关键字下载**百度搜索的图片** ##

在别人的代码基础做了修改，增加了关键字word定义，下载图片数量的imageNum设置，以及图像保存路径和名字的设置，需要requests模块的支持，直接使用pip安装即可，命令：*pip install requests*

# -*- coding: utf-8 -*-
    
    import json
    import itertools
    import urllib
    import requests
    import os
    import re
    import sys
    print("hah")
    #############################################################
    word="眼镜"                 #图片搜索的关键字，目前仅支持单个关键词
    imageNum =10;               #下载图片的数目
    saveImagePath="glasses3"    #保存图片的途径
    indexOffset=0               #图像命名起始点
    #############################################################
    
    str_table = {
        '_z2C$q': ':',
        '_z&e3B': '.',
        'AzdH3F': '/'
    }
    
    char_table = {
        'w': 'a',
        'k': 'b',
        'v': 'c',
        '1': 'd',
        'j': 'e',
        'u': 'f',
        '2': 'g',
        'i': 'h',
        't': 'i',
        '3': 'j',
        'h': 'k',
        's': 'l',
        '4': 'm',
        'g': 'n',
        '5': 'o',
        'r': 'p',
        'q': 'q',
        '6': 'r',
        'f': 's',
        'p': 't',
        '7': 'u',
        'e': 'v',
        'o': 'w',
        '8': '1',
        'd': '2',
        'n': '3',
        '9': '4',
        'c': '5',
        'm': '6',
        '0': '7',
        'b': '8',
        'l': '9',
        'a': '0'
    }
    
    # str 的translate方法需要用单个字符的十进制unicode编码作为key
    # value 中的数字会被当成十进制unicode编码转换成字符
    # 也可以直接用字符串作为value
    char_table = {ord(key): ord(value) for key, value in char_table.items()}
    
    # 解码图片URL
    def decode(url):
        # 先替换字符串
        for key, value in str_table.items():
            url = url.replace(key, value)
        # 再替换剩下的字符
        return url.translate(char_table)
    
    # 生成网址列表
    def buildUrls(word):
        word = urllib.parse.quote(word)
        url = r"http://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&fp=result&queryWord={word}&cl=2&lm=-1&ie=utf-8&oe=utf-8&st=-1&ic=0&word={word}&face=0&istype=2nc=1&pn={pn}&rn=60"
        urls = (url.format(word=word, pn=x) for x in itertools.count(start=0, step=60))
        return urls
    
    # 解析JSON获取图片URL
    re_url = re.compile(r'"objURL":"(.*?)"')
    def resolveImgUrl(html):
        imgUrls = [decode(x) for x in re_url.findall(html)]
        return imgUrls
    
    def downImg(imgUrl, dirpath, imgName):
        filename = os.path.join(dirpath, imgName)
        try:
            res = requests.get(imgUrl, timeout=15)
            if str(res.status_code)[0] == "4":
                print(str(res.status_code), ":" , imgUrl)
                return False
        except Exception as e:
            print("抛出异常：", imgUrl)
            print(e)
            return False
        with open(filename, "wb") as f:
            f.write(res.content)
        return True
    
    
    def mkDir(dirName):
        dirpath = os.path.join(sys.path[0], dirName)
        if not os.path.exists(dirpath):
            os.mkdir(dirpath)
        return dirpath
    
    if __name__ == '__main__':
        print("=" * 50)
       # word = input("请输入你要下载的图片关键词：\n")
    
        dirpath = mkDir(saveImagePath)
    
        urls = buildUrls(word)
        index = 0
        for url in urls:
            print("正在请求：", url)
            html = requests.get(url, timeout=10).content.decode('utf-8')
            imgUrls = resolveImgUrl(html)
            if len(imgUrls) == 0:  # 没有图片则结束
                break
            for url in imgUrls:
                if downImg(url, dirpath, str(index+indexOffset) + ".jpg"):
                    index += 1
                    print("正在下载第 %s 张" % (index+indexOffset))
                    if index==imageNum:
                        break
            if index==imageNum:
                print("---------------------下载完成----------------------")
                print("下载结果保存在脚本目录下的文件夹中，文件名字：" + saveImagePath)
                break

--------------------

## 2.根据链接URL下载图片 ##

如果已知图片的URL地址，可直接通过下面的方法下载

# -*-coding: utf-8 -*-
    """
        @Project: dataset
        @File   : download_url_image.py
        @Author : panjq
        @E-mail : pan_jinquan@163.com
        @Date   : 2018-07-12 10:00:19
    """
    
    import requests
    import os
    
    def downImg(imgUrl, dirpath, imgName):
        filename = os.path.join(dirpath, imgName)
        try:
            res = requests.get(imgUrl, timeout=15)
            if str(res.status_code)[0] == "4":
                print(str(res.status_code), ":" , imgUrl)
                return False
        except Exception as e:
            print("抛出异常：", imgUrl)
            print(e)
            return False
        with open(filename, "wb") as f:
            f.write(res.content)
        return True
    
    #读取txt数据函数
    def download_url_image(fileName,out_dir):
        '''
        读取txt中URL下载链接,并下载到指定文件中
        :param fileName: 保存URl的TXT文件
        :param out_dir:  下载图片的保存目录
        :return: None
        '''
    
        Data=[]
        with open(fileName) as txtData:
            lines=txtData.readlines()
            for line in lines:
                try:
                    lineData=line.strip()#去除空白和逗号“,”
                    str_list = lineData.split(';')
                    image_url=str_list[0]
                    image_name=image_url.split('/')[-1]
                    downImg(image_url,out_dir,image_name)
                    print(image_url)
                except:
                    print("下载失败：",image_url)
                    continue
    
    if __name__ == '__main__':
        fileName='/home/ubuntu/project/tfTest/image_list.txt'
        out_dir="/home/ubuntu/project/tfTest/dataset"
        download_url_image(fileName,out_dir)

其中image\_list.txtb保存URL的地址：

> https://farm3.staticflickr.com/2334/1828778894\_271415878a\_o.jpg;4;369  
> https://farm4.staticflickr.com/3149/2355285447\_290193393a\_o.jpg;0;295  
> https://farm3.staticflickr.com/2090/1792526652\_8f37410561\_o.jpg;3;2332  
> https://farm3.staticflickr.com/2099/1791684639\_044827f860\_o.jpg;7;5920  
>

资料参考：http://blog.csdn.net/guyuealian/article/details/78730200