爬虫代码 python

 

 

 

import requests
import urllib
import os
import time

print('欢迎使用Aking爬虫图片下载器!')
time.sleep(0.5)
print('欢迎使用Aking爬虫图片下载器!!')
time.sleep(0.5)
print('欢迎使用Aking爬虫图片下载器!!!')
time.sleep(0.5)
print('准备就绪！')
time.sleep(0.5)
keyword = str(input('请输入关键词:'))
folder = 'C:/Users/Administrator/Desktop/456'
sum_old = int(input('请输入需要下载的数量（最低为30，尽量为30倍数）:'))
sum = int(sum_old / 30)


if not os.path.exists(str(folder)):
    print('正在创建文件夹！')
    os.mkdir(str(folder))
    print('文件夹已创建！')



def is_chinese(string):
    for ch in string:
        if u'\u4e00' <= ch <= u'\u9fff':
            return True

    return False


class GetImage():
    def __init__(self, keyword=(), paginator=1):
        self.url = "http://image.baidu.com/search/acjson?"
        self.headers = {
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
        }
        self.keyword = keyword    #定义关键词
        self.paginator = paginator    #定义要爬取的页数

    def get_param(self):
        params = []
        #判断中文，是中文就重编码
        if is_chinese(self.keyword):
            keyword = urllib.parse.quote(self.keyword)
            for i in range(1, self.paginator + 1):
                params.append(
                    'tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord={}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=&hd=1&latest=0&copyright=0&word={}&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&cg=star&pn={}&rn=30&gsm=78&1557125391211='.format(
                        keyword, keyword, 30 * i))
        else:
            keyword = self.keyword
            for i in range(1, self.paginator + 1):
                params.append(
                    'tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord={}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=&hd=1&latest=0&copyright=0&word={}&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&cg=star&pn={}&rn=30&gsm=78&1557125391211='.format(
                        keyword, keyword, 30 * i))
        return params

    def get_urls(self, params):
        urls = []
        for param in params:
            urls.append(self.url + param)

        return urls

    def get_image_url(self, urls):
        image_url = []
        for url in urls:
            json_data = requests.get(url, headers=self.headers).json()
            json_data = json_data.get('data')
            for i in json_data:
                if i:
                    image_url.append(i.get('thumbURL'))

        return image_url

    def get_image(self, image_url,prefix=None):
        file_name = os.path.join(str(folder), self.keyword)
        print('开始下载！')
        print('文件会下载到'+str(file_name)+'，目录下。')
        if not os.path.exists(file_name):
            os.mkdir(file_name)

        for index, url in enumerate(image_url, start=1):

            img_name=str(index) if prefix is None else str(prefix)+'_'+str(index)
            with open(file_name + '/{}.jpg'.format(img_name), 'wb') as f:
                f.write(requests.get(url, headers=self.headers).content)

            if index != 0 and index % 30 == 0:
                print("第{}张下载完成！".format(index))

    def __call__(self, *args, **kwargs):

        params = self.get_param()
        urls = self.get_urls(params)
        image_url = self.get_image_url(urls)
        self.get_image(image_url)

    def run(self,prefix=None):

        params = self.get_param()
        urls = self.get_urls(params)
        image_url = self.get_image_url(urls)
        self.get_image(image_url,prefix=prefix)


if __name__ == '__main__':
    spider = GetImage(str(keyword), sum)
    spider.run(prefix='senlin_')