避免抓取打印时报错GBK不能转码的解决方法

# -*- coding: utf-8 -*-
import requests
from lxml import etree
import io

import sys

sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030')  # 修改输出编码
url = 'http://*********.com/'
xpath = '//*[@class="lbcon"]/ul/li/a/@href'
content = requests.get(url).content
html = etree.HTML(content)
new_url = html.xpath(xpath)
new_url = '^'.join(new_url)

print(url, new_url)

编码有 utf-8  gbk  gb2312  gb18030 

参考 http://blog.csdn.net/jim7424994/article/details/22675759