数据挖掘工程师：如何通过百度地图API抓取建筑物周边位置、房价信息

 function GetDataFromServer() {
     $.ajax({
         type: "GET",
         url: get_data_url,
         dataType: 'json',
         success: function (house_data) {
             // 拿到房屋数据后先显示出来
             displayHouseData(house_data);             // 然后先用街道去查坐标
             myGeo.getPoint(house_data.street, function (point) {
                 if (point) {                     // 如果查到坐标，开始检索周围信息
                     SearchStart(point, house_data);
                 } else {                     // 如果街道没查搭配，再用小区去查坐标
                     myGeo.getPoint(house_data.community, function (repoint) {
                         if (repoint) {                             // 如果查到坐标，开始检索周围信息
                             SearchStart(repoint, house_data)
                         } else {
                             setTimeout(function () {
                                 console.log("Error: no address of " + " id: " + data.id + " community: " + data.community + " street: " + data.street);                                 // 如果还没查到坐标，继续查询下一个房屋，延迟timeInterval秒
                                 GetDataFromServer();
                             }, timeInterval);
                         }
                     }, "北京市");
                 }
             }, "北京市");
         },
         error: function () {
             alert('error')
         },
         timeout: function () {
             alert('time out')
         }
     });
 } 

function SearchStart(point, house_data) {
    // 先在地图上标记出来
    map.centerAndZoom(point, 16);
    map.addOverlay(new BMap.Marker(point));    // 首先查询此房屋的第一个关键词信息（公交车站，idx＝0）
    setTimeout(function () {
        SearchNearby(point, house_data, 0);
    }, timeInterval);
}function SearchNearby(house_loc, house_data, keyword_idx) {
    var nearby_info = [];    // 清除地图覆盖物
    map.clearOverlays();    var local = new BMap.LocalSearch(map, {
        renderOptions: {map: map, autoViewport: false},
        pageCapacity: 50,
        onSearchComplete: function (results) {
            DisplayClear();            if (local.getStatus() == BMAP_STATUS_SUCCESS) {                // 百度地图成功返回，将每个周边信息储存到nearby_info里
                for (var i = 0; i < results.getCurrentNumPois(); i++) {                    var locate = results.getPoi(i);                    if (locate != null) {                        // 查询结果与房屋的距离
                        var distance = parseFloat(map.getDistance(locate.point, house_loc)).toFixed(1);
                        nearby_info.push(locate.title + "/" + locate.point.lng + '/' + locate.point.lat + '/' + distance);
                        DisplayNearbyData(nearby_info, locate, distance)
                    }
                }                // 获得百度地图查询结果后立即发送给服务器
                return sendData(keywords_en[keyword_idx], nearby_info, house_data, house_loc, keyword_idx)
            } else {
                GetDataFromServer();
                console.log("No records with baiduAPI:", local.getStatus());                return false;
            }
        }
    });
    local.searchNearby(keywords[keyword_idx], house_loc, search_range);
}

function sendData(nearby_type, nearby_info, house_data, house_loc, idx) {
    data = "nearby_type=" + nearby_type + "&nearby_info=" + nearby_info + "&id=" + house_data.id + "&lat=" + house_loc.lat + "&lng=" + house_loc.lng;
    $.ajax({
        type: "POST",
        url: post_data_url,
        data: data,
        dataType: "JSON",
        success: function (data) {
            if (flag) {
                console.log("warning", 'pause');
            } else {                // 当查询到最后一个kewords时，请求服务器获得下一个房屋信息
                if (idx == keywords.length - 1) {
                    GetDataFromServer();
                } else {                    // 查询此房屋的下一个关键词信息
                    setTimeout(function () {
                        SearchNearby(house_loc, house_data, idx + 1);
                    }, timeInterval);
                }
                console.log("success", data);
            }            return true;
        },
        error: function () {
            alert('error in post');            return false;
        },
        timeout: function () {
            alert('time out in post');            return false;
        }
    });
}

@@house_id=0def return_next  # 查询下一个房屋信息
  house=House.next_record(@@house_id)  @@house_id=house.id  # 避免重复抓取，跳过已经有相关信息的
  while not house.buses_houses.nil? and not house.buses_houses.blank?
    house=House.next_record(@@house_id)    @@house_id=house.id    break if house == House.last  end

  # TODO
  # 避免重复抓取，现在只能靠bus信息进行判断，希望更全面的信息判断
  # END

  if house == House.last
    redirect_to buses_path, flash: {:success => "抓取完毕"}  else
    respond_to do |format|
      format.json { render :json => house }    end
  endend

def create
  house=House.find_by(id: params[:id])
  house.latitude=params[:lat]
  house.longitude=params[:lng]
  house.save

  insert(house, params, Bus, BusesHouses, 'bus') if params[:nearby_type] == 'bus'
  insert(house, params, Hospital, HospitalsHouses, 'hospital') if params[:nearby_type] == 'hospital'
  insert(house, params, Work, WorksHouses, 'work') if params[:nearby_type] == 'work'
  insert(house, params, School, SchoolsHouses, 'school') if params[:nearby_type] == 'school'
  insert(house, params, Subway, SubwaysHouses, 'subway') if params[:nearby_type] == 'subway'
  insert(house, params, Shop, ShopsHouses, 'shop') if params[:nearby_type] == 'shop'

  render json: params.as_jsonend

def insert(house, params, obj, asso_obj, asso_type)  params[:nearby_info].split(',').each do |row|
    attr=row.split('/')
    bus=obj.find_by(longitude: attr[1], latitude: attr[2])    if bus.nil?
      bus=obj.new(name: attr[0], longitude: attr[1], latitude: attr[2])
      bus.save    end
    asso_obj.create("#{asso_type}_id": bus.id, house_id: house.id, distance: attr[3])  endend