Python之使用正則函數處理文本里的雜質

# -*- coding: utf-8 -*-
import re


class Tool():
 # 去除img標籤,7位長空格
 removeImg = re.compile('<img.*?>| {7}|')
 # 刪除span標籤
 removeSpan = re.compile('<span.*?>| {7}|')
 # 刪除超連接標籤
 removeAddr = re.compile('<a.*?>|</a>')
 # 把換行的標籤換爲\n
 replaceLine = re.compile('<tr>|<div>|</div>|</p>')
 # 將表格製表<td>替換爲\t
 replaceTD = re.compile('<td>')
 # 把段落開頭換爲\n加空兩格
 replacePara = re.compile('<p.*?>')
 # 將換行符或雙換行符替換爲\n
 replaceBR = re.compile('<br><br>|<br>')
 # 將其他標籤剔除
 removeExtraTag = re.compile('<.*?>')

 def replace(self, content):
 content = re.sub(self.removeImg, "", content)
 content = re.sub(self.removeSpan, "", content)
 content = re.sub(self.removeAddr, "", content)
 content = re.sub(self.replaceLine, "\n", content)
 content = re.sub(self.replaceTD, "\t", content)
 content = re.sub(self.replacePara, "\n ", content)
 content = re.sub(self.replaceBR, "\n", content)
 content = re.sub(self.removeExtraTag, "", content)
 # strip()將先後多餘內容刪除
 return content.strip()