# -*- coding:utf8 -*-importrequestsimportjsonfromurllibimportparseimportosimporttimeclassBaiduImageSpider(object):
def__init__(self):
self.json_count=0# 请求到的json文件数量（一个json文件包含30个图像文件）self.url='https://image.baidu.com/search/acjson?tn=resultjson_com&logid=5179920884740494226&ipn=rj&ct' \
'=201326592&is=&fp=result&queryWord={' \
'}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=0&hd=&latest=&copyright=&word={' \
'}&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&nojc=&pn={' \
'}&rn=30&gsm=1e&1635054081427= 'self.directory=r"C:\Users\86180\Desktop\素材\python素材\爬虫测试\{}"# 存储目录  这里需要修改为自己希望保存的目录  {}不要丢self.header= {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) ''Chrome/95.0.4638.54 Safari/537.36 Edg/95.0.1020.30 '        }
# 创建存储文件夹defcreate_directory(self, name):
self.directory=self.directory.format(name)
# 如果目录不存在则创建ifnotos.path.exists(self.directory):
os.makedirs(self.directory)
self.directory+=r'\{}'# 获取图像链接defget_image_link(self, url):
list_image_link= []
strhtml=requests.get(url, headers=self.header)  # Get方式获取网页数据jsonInfo=json.loads(strhtml.text)
forindexinrange(30):
list_image_link.append(jsonInfo['data'][index]['thumbURL'])
returnlist_image_link# 下载图片defsave_image(self, img_link, filename):
res=requests.get(img_link, headers=self.header)
ifres.status_code==404:
print(f"图片{img_link}下载出错------->")
withopen(filename, "wb") asf:
f.write(res.content)
print("存储路径："+filename)
# 入口函数defrun(self):
searchName=input("查询内容：")
searchName_parse=parse.quote(searchName)  # 编码self.create_directory(searchName)
pic_number=0# 图像数量forindexinrange(self.json_count):
pn= (index+1)*30request_url=self.url.format(searchName_parse, searchName_parse, str(pn))
list_image_link=self.get_image_link(request_url)
forlinkinlist_image_link:
pic_number+=1self.save_image(link, self.directory.format(str(pic_number)+'.jpg'))
time.sleep(0.2)  # 休眠0.2秒，防止封ipprint(searchName+"----图像下载完成--------->")
if__name__=='__main__':
spider=BaiduImageSpider()
spider.json_count=10# 定义下载10组图像，也就是三百张spider.run()