import requests
from bs4 import BeautifulSoup
import os  #导入os模块class TuKuSpider():"""docstring for TuKuSpider"""def __init__(self):self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'}self.url='http://588ku.com/tuku/jiepai.html'self.folder_path='E:\TuKuImg'def get_img_url(self):print('开始请求页面')init_response = self.request(self.url)all_img = BeautifulSoup(init_response.text,'lxml').find_all('img',class_='lazy')print('开始创建文件夹')self.mkdir(self.folder_path)  #创建文件夹print('开始切换文件夹')os.chdir(self.folder_path)   #切换路径至上面创建的文件夹for each in all_img:img_url = each.get('data-original')img_name = each.get('alt')if img_name == None:img_name = 'NoName'if img_url[-3:]=='png':img_url_final = 'http:'+img_urlimg_response = self.request(img_url_final)self.save_png(img_url_final,img_name)else:img_url = img_url[:img_url.index('.jpg')+4]img_url_final = 'http:'+img_urlimg_response = self.request(img_url_final)self.save_jpg(img_url_final,img_name)def request(self,url):r=requests.get(url,headers=self.headers)return rdef save_jpg(self, url, name): ##保存图片print('开始请求图片地址，过程会有点长...')img = self.request(url)file_name = name + '.jpg'print('开始保存图片')f = open(file_name, 'ab')f.write(img.content)print(file_name,'图片保存成功！')f.close()def save_png(self, url, name): ##保存图片print('开始请求图片地址，过程会有点长...')img = self.request(url)file_name = name + '.png'print('开始保存图片')f = open(file_name, 'ab')f.write(img.content)print(file_name,'图片保存成功！')f.close()def mkdir(self, path):  ##这个函数创建文件夹path = path.strip()isExists = os.path.exists(path)if not isExists:print('创建名字叫做', path, '的文件夹')os.makedirs(path)print('创建成功！')else:print(path, '文件夹已经存在了，不再创建')a = TuKuSpider()
a.get_img_url()