from abc import abstractmethod

from bs4 import BeautifulSoup

import FileUtil
import HtmlUtil


class Site:
 def __init__(self):
 self.file = ''
 self.page_format = ''
 self.post_selector = ''

 @abstractmethod
 def phasePage(self, response):
 pass


# 2 to 2321
class Site3DM(Site):
 def __init__(self):
 super().__init__()
 self.file = './data/Ex3DM.xlsx'
 self.page_format = 'https://dl.3dmgame.com/all_all_{}_time/'
 self.post_selector = 'div[class="listwrap"] > ul > li'

 def phasePage(self, response):
 rtn = ''
 bs = BeautifulSoup(response.content, "lxml")
 list_post = bs.select('div[class="listwrap"] > ul > li')
 # Post解析测试
 # print(list_post[9])
 file = FileUtil.File3DM(self.file)
 for i in range(2, len(list_post)):
 post = list_post[i]
 title_selector = post.select('div[class="bt"] > a')
 title_txt = title_selector[0].contents[0]
 # 获取到标题
 # print(title_txt)
 link_url = title_selector[0].attrs['href']
 # 取得详情链接
 # print(link_url)
 img_selector = post.select('img')
 img_url = img_selector[0].attrs['data-original']
 # 取得图片链接
 # print(img_url)

 # 使用详情链接构造图片名称并下载图片
 img_txt = link_url.split('/')[-1].split('.')[0]
 HtmlUtil.download_pic(int(img_txt) % 100, img_txt + '.jpg', img_url)

 tag_selector = post.select('li[class="li2"] > a')
 tag_txt = ''
 for i_tag in tag_selector:
 # print(i_tag.contents[0], end=',')
 tag_txt += i_tag.contents[0]
 tag_txt += ',' # 标签之间逗号分隔
 # 获取到标签
 # print(tag_txt)
 file.setPost([title_txt, link_url, img_txt, tag_txt])
 file.save()
 return rtn