Actualizados

This commit is contained in:
Intel1
2017-09-22 12:39:40 -05:00
committed by GitHub
parent c75b9e1e28
commit 20d589e87a

View File

@@ -1,4 +1,4 @@
# -*- coding: utf-8 -*-
# -*- coding: utf-8 -*-
# --------------------------------------------------------------------------------
# Scraper tools for reading and processing web elements
# --------------------------------------------------------------------------------
@@ -214,6 +214,7 @@ def htmlclean(cadena):
cadena = cadena.replace("<tr>", "")
cadena = cadena.replace("</tr>", "")
cadena = cadena.replace("<![CDATA[", "")
cadena = cadena.replace("<wbr>", "")
cadena = cadena.replace("<Br />", " ")
cadena = cadena.replace("<BR />", " ")
cadena = cadena.replace("<Br>", " ")