# -*- coding:utf-8 -*-
from lxml
import etree
import requests
##先进单页测试,然后在进行多页循环 没有解决的问题,动态解决最大页数,目前是默认11页
for page
in range(1,12
):
for i
in range(1,21):
##每页都是20条信息,每一行5列信息
for j
in range(1,6
):
##单页测试
url =
'http://www.tbia.cn/cn/dynamicflight/dynamicflightInfo/list.do?page='+
str(page)
headers =
{
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36'}
data = requests.get(url, headers=
headers)
data.encoding =
'utf-8' ##中文乱码解决方案
s =
etree.HTML(data.text)
info = s.xpath(
'//table[@class="flighttable"]/tbody/tr['+str(i)+
']/td['+str(j)+
']/node()')
# **机场
print(
"第 "+str(page)+
"页"+
"第 "+str(i)+
"行"+
"第 "+str(j)+
"列")
list.append(info)
print(list)
##list即为结果
转载于:https://www.cnblogs.com/0909/p/9889038.html
