bs4美食杰图片下载

妖狐艹你老母 2022-04-12 13:08 156阅读 0赞

import shutil,os
    from bs4 import BeautifulSoup
    from urllib.request import Request,urlopen,urlretrieve
    import xlwt
    import requests
    class Picture_downLoad(object):
        def __init__(self):
            self.base_url = 'http://www.meishij.net/'
            self.current_page = 1
        def start_Load(self):
            # 判断是否存在指定文件,如果有就删除
            if os.path.exists('cate'):
                #删除树状结构的文件夹
                shutil.rmtree('cate',True)
            os.mkdir('cate')
            os.chdir('cate')
            self.get_page_with_url('https://www.meishij.net/chufang/diy/?&page=1')
        def get_page_with_url(self,url):
            headers = {
                'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0'
            }
            request = Request(url,headers = headers)
            try:
                respone = urlopen(request)
                code = respone.read().decode()
            except Exception as e:
                print('请求失败', + e)
            else:
                self.get_data_with_page(code)
    
        def get_data_with_page(self,code):
            print('正在下载第{}页...'.format(self.current_page))
            soup = BeautifulSoup(code,'lxml')
            page_list = '{}Page1'.format(self.current_page)
            os.mkdir(page_list)
            os.chdir(page_list)
            image_list = soup.select('img.img')
            for image in image_list:
                image_src = image.get('src')
                image_alt = image.get('alt')
                image_alt = image_alt.split('(')[0] + '.jpg'
                image_alt= image_alt.replace('|', '')
                print(image_alt)
                print(image_src)
                urlretrieve(image_src,image_alt)
            os.chdir(os.path.pardir)
            self.current_page += 1
            self.get_next_page(code)
    
        def get_next_page(self, code):
            soup = BeautifulSoup(code, 'lxml')
            next_page = soup.select('a.next')
            next_page=next_page[0]
            url = next_page.get('href')
            self.get_page_with_url(url)
    
    
    
    
    downLoad = Picture_downLoad()
    downLoad.start_Load()