爬取网页时调用tostring()中文乱码("&#数字;")解决方案

1. 出现乱码的代码

import requests
import re
from lxml import etree
with open('real_case.html', 'r', encoding='utf-8') as f:
    c = f.read()
tree = etree.HTML(c)
table_element = tree.xpath("//div[@class='table-box'][1]/table/tbody/tr")
#正则表达式过滤掉<>
pattern1_attrib = re.compile(r"<.*?>")
for row in table_element:
    try:
        td1 = row.xpath('td')[0]
        #调用tostring()后出现乱码
        s1 = etree.tostring(td1).decode('utf-8')
        s1 = pattern1_attrib.sub('', s1)
        print(s1)
    except Exception as error:
        pass

乱码：

2. 修正过后的代码
   引入HTML包，使用unescape()方法

import requests
import re
from lxml import etree
#引入HTML包
import html

with open('real_case.html', 'r', encoding='utf-8') as f:
    c = f.read()
tree = etree.HTML(c)
table_element = tree.xpath("//div[@class='table-box'][1]/table/tbody/tr")

pattern1_attrib = re.compile(r"<.*?>")
for row in table_element:
    try:
        td1 = row.xpath('td')[0]
        s1 = etree.tostring(td1).decode('utf-8')
        s1 = pattern1_attrib.sub('', s1)
        # unescape() 此函数使用HTML5标准定义的规则将字符转换成对应的unicode字符。
        s1 = html.unescape(s1)
        print(s1)
    except Exception as error:
        pass

结果：