Python3实现批量下载百度搜索图片

时间:2022-07-12 18:31:47

 Python3实现批量下载百度搜索图片

原文请参考:http://blog.csdn.net/guyuealian/article/details/78730200,这里做了部分修改,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 jsonimport itertoolsimport urllibimport requestsimport osimport reimport sysprint("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valuechar_table = {ord(key): ord(value) for key, value in char_table.items()}# 解码图片URLdef 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URLre_url = re.compile(r'"objURL":"(.*?)"')def resolveImgUrl(html):    imgUrls = [decode(x) for x in re_url.findall(html)]    return imgUrlsdef 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 Truedef mkDir(dirName):    dirpath = os.path.join(sys.path[0], dirName)    if not os.path.exists(dirpath):        os.mkdir(dirpath)    return dirpathif __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


运行效果: