python xpath提取td标签_python 爬取td标签对应的值

[root@yyjk /tmp]#cat a2.py

# !/usr/bin/env python

# -*- coding: utf-8 -*-

import urllib2

import urllib

import cookielib

import json

import httplib

import re

import requests

import StringIO

import time

from lxml import etree

s = requests.session()

print s.headers

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0'

}

data = {'username':'thinkgem','password':'R6k_5QTs'}

# data = urllib.urlencode(data)

response = s.post(login_url, data=data, headers=headers,timeout=10)

data={'pageNo':'1','pageSize':'100'}

fh2=open('fh2.html','r')

fh3=fh2.read()

htmlEmt=etree.HTML(fh3)

result= htmlEmt.xpath('//td')

fo

标签：python,urllib,爬取,headers,htmlEmt,import,td,data,fh2

来源： https://blog.csdn.net/zhaoyangjian724/article/details/111588382