Python爬虫练习：爬取高德地图地铁线路及站点数据

前言

本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理。

作者：Darcy频道

 

# coding=utf-8

import requests
import time
import json
import ast
import os
import utils
from lxml import etree

PAGE_URL = 'http://map.amap.com/subway/index.html?&1100'
DATA_URL = 'http://map.amap.com/service/subway?srhdata='
HEADER = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"}


def fetchAllCity(url, header):
    r = requests.get(url, header)
    html = r.content
    element = etree.HTML(html)
    options = element.xpath("//a[contains(@class, 'city')]")

    cities = []
    for option in options:
        city = {
            'id': option.get('id'),
            'name': option.get('cityname'),
            'text': option.text
        }
        cities.append(city)
    return cities



def parseCityData(citys):
    lw = open('./lwkt.txt', 'w')
    lw.write('wkt' + '\n')
    pw = open('./pwkt.txt', 'w')
    pw.write('wkt' + '\n')
    for city in citys:
        parseCityPointFromApi(city, lw, pw)


def parseCityPointFromApi(city, lw, pw):
    url = DATA_URL + "{}_drw_{}.json".format(city['id'], city['name'])
    print(url)
    json_str = requests.get(url).text
    res = json.loads(json_str)
    res = res['l']
    for r in res:
        st = r['st']
        coords = []
        for s in st:
            _coords = s.get('sl', '').split(',')
            coords.append(_coords)
            pwkt = '"POINT ({} {})"'.format(_coords[0], _coords[1])
            pw.write(pwkt + '\n')
        new_coords = ','.join(['%s %s' % (coord[0], coord[1]) for coord in coords])
        lwkt = '"LINESTRING(%s)"' % new_coords
        lw.write(lwkt + '\n')



def main():
    cities = fetchAllCity(PAGE_URL, HEADER)
    print(cities)
    parseCityData(cities)



if __name__ == '__main__':
    main()

PS：如有需要Python学习资料的小伙伴可以加下方的群去找免费管理员领取

 

可以免费领取源码、项目实战视频、PDF文件等