python爬取aspx数据

参考：

https://github.com/lxl0928/ricedata_spider

 

# coding: utf-8

import json
import urllib.request
from datetime import datetime
from collections import OrderedDict

import requests
from lxml import etree

cnt_now = datetime.now()
cnt_time = "{}{}{}{}{}".format(cnt_now.year, cnt_now.month, cnt_now.day, cnt_now.hour, cnt_now.minute)

url = "http://www.ricedata.cn/gene/accessions_switch.aspx?p={}&cloned=true"
user_agent = "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"
headers = {"User-Agent": user_agent}

result_path = "./doc/{}.xlsx".format(cnt_time)
xls_data = OrderedDict()
result_biao &