import pymysql
import pandas as pd
from lxml import etree
import re
#连接数据库的参数
config = {
'host':'127.0.0.1',
'port':3306,
'user':'root',
'password':'f012464998',
'db':'我的',
'charset':'utf8mb4',
'cursorclass':pymysql.cursors.DictCursor,
}
# #连接数据库
db = pymysql.connect(**config)
# #创建游标
cursor = db.cursor()
# ## 执行SQL,并返回收影响行数
cursor.execute('select body from dianxin_data_comments')
result = cursor.fetchall()
# print(type(result)) #list 查询结果是一个list,而pd.read_sql 读入了一个dataframe;
print(type(result[-1]))
print(result[-1])
print(len(result))
df3 = pd.DataFrame(result) #将查询结果转为一个dataframe。
# df3.to_csv("yidong.csv")
print(df3["body"][1])
print(type(df3["body"][1]))
a = df3["body"][2]
a= etree.HTML(a)
dom = a.xpath("//div/a/text()")
print(dom)