import requests, os, re
from  fake_useragent import FakeUserAgent
class BQBSpider(object):
    os_path = os.getcwd()+'/爱斗图/'
    if not os.path.exists(os_path):
        os.mkdir(os_path)

    def __init__(self):
        '''1.准备数据'''
        user_agent = FakeUserAgent().random
        self.start_url = 'https://adoutu.com/picture/list/{}'
        self.headers = {
            'User-Agent': 'user_agent'
        }

    def parse_start_url(self):
        ''' 2.发送请求，获取响应 '''

        # 循环遍历模拟翻页
        for page in range(1, 2777):
            # 地址的完整性拼接
            start_url = self.start_url.format(page)
            # 发送请求
            response = requests.get(start_url, headers=self.headers)
            '''调用其他方法，前面加self,传递数据'''
            self.parse_response_data(response,page)

    def parse_response_data(self, response, page):
        '''3.解析数据，数据提取'''
        # 解析响应
        resp_data = response.content.decode()
        # 数据提取
        img_url_list = re.findall(r'src="(.*?)"', resp_data)
        '''三木运算符结合列表推导式的判断'''
        img_url_list = [img_url for img_url in img_url_list if 'http' in img_url]
        for img_url in img_url_list:
            # 去除表情包的名称和格式
            img_name = img_url[30:]
            # 发送请求，获取二进制数据
            data = requests.get(img_url).content
            self.save_data(data,img_name)

    def save_data(self,data,img_name):
        '''4.保存数据'''
        with open(self.os_path + img_name,'wb')as f:
            f.write(data)
        print(f'{img_name}===========保存完成')

if __name__ == '__main__':
    f = BQBSpider()
    f.parse_start_url()