使用python爬取中国地震局网站的地震数据

0.简介：以python爬取的地震数据作为动态数据源，可利用ArcGIS二次开发设计一个地震监测分析系统。篇章有限，这里重点记录爬虫部分。

1.数据来源：

 

 

 

2.示例代码如下：

# -*- coding: utf-8 -*-
"""
Created on Thur Sep 19 08:31:07 2019

@author: L JL
"""
import requests
import urllib
import json
import csv
from bs4 import BeautifulSoup
from lxml import etree


#print(soup)


def get_one_page(i):
    try:
        url = 'http://ditu.92cha.com/dizhen.php?page= %s &dizhen_ly=china&dizhen_zjs=5&dizhen_zje=10&dizhen_riqis=2016-01-01&dizhen_riqie=2019-12-30' % (str(i))
        head = {
           'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/17.17134"}
        data = requests.get(url,headers = head)
        #print(data)
        return data
    except RequestException:
        print('爬取失败')

def parse_one_page(html,ulist):
    soup = BeautifulSoup(html.text,'lxml')
    trs = soup.find_all('tr')
    i = 0
    for tr in trs:
        if i == 0:       ##效率低 待改进
            i += 1
        else:            
            ui = []
            for td in tr:
                #print(td.string)
                ui.append(td.string) 
            ulist.append(ui)
            i = i + 1
            
    
def save_contents(ulist):
     with open(r'data0.csv', 'w', encoding='utf-8-sig', newline='') as f:
        csv.writer(f).writerow(['发震时间', '震级', '经度', '维度', '深度（km）', '位置'])
        for i in range(len(ulist)):
            csv.writer(f).writerow([ulist[i][1],ulist[i][3],ulist[i][5],ulist[i][7],ulist[i][9],ulist[i][11]])

        
def main(page):
    ulist = []
    for i in range(1,page):        
        html = get_one_page(i)
        parse_one_page(html,ulist)
    save_contents(ulist)   
    print('结束')

    
if __name__ == '__main__':
    main(21)         ##需爬取的页数

 

3.爬取结果如下图所示：

 

4.方案设计：

 

 

 

 

 ---------------------------------------------------------2019.9--------------------------------------------------------------------