Arcpy基础入门-5、读取自定义格式xml

arcpy作为一种脚本开发语言，其功能的目的是为用户提供强有力的可扩展性。

这一节通过示例，介绍比较下使用python和arcpy读取自定义格式的xml并构建要素的方法。

先简单描述下自定义的xml格式：

j

自定义了一种北京54坐标系的航迹数据，每一个航迹包括了属性和对应的几何点，由于通用的航迹格式GPS只支持经纬度坐标的读取，所以需要自己写脚本，对要素进行处理

将xml格式的数据转化为要素有两种方式：一种是较为常见的创建要素，赋属性的方式，

使用的是arcpy.insertcursor，这种方式和ArcEngine开发有点相似，代码如下：

#coding=utf-8
import arcpy, os, time
import xml.dom.minidom
import random
from arcpy import env
arcpy.env.overwriteOutput = True 

#inGPXFile = arcpy.GetParameterAsText(0)
inpath = 'F:\\gpx\\航迹-settingDB-20150605031316.gpx'
uipath = unicode(inpath , "utf8")

#outputFC = arcpy.GetParameterAsText(1)
outputFC = r'F:\gpx\20150605031316.shp'
uoutputFC = unicode(outputFC , "utf8")

# 打开xml文档
dom = xml.dom.minidom.parse(uipath)
#得到文档元素对象
root = dom.documentElement

def get_attrvalue(node, attrname):
     return node.getAttribute(attrname) if node else ''

def get_nodevalue(node, index = 0):
     if node:
          if node.childNodes:
               return node.childNodes[index].nodeValue   
     else:
          return None

def get_xmlnode(node,name):
    return node.getElementsByTagName(name) if node else []

trk_nodes = get_xmlnode(root,'trk')
#获得节点测试
print trk_nodes

#创建shp
path = os.path.split(outputFC)[0]
name = os.path.split(outputFC)[1]
print path
print name
arcpy.CreateFeatureclass_management(path,name,"POLYLINE")

fieldName1 = "name"
fieldAlias = "轨迹名称"
fieldLength = 50
arcpy.AddField_management(outputFC, fieldName1, "TEXT", "","",fieldLength,
                          fieldAlias, "NULLABLE")

fieldName2 = "time"
fieldAlias = "时间"
fieldLength = 50
arcpy.AddField_management(outputFC, fieldName2, "TEXT", "","",fieldLength,
                          fieldAlias, "NULLABLE")

fieldName3 = "length"
fieldPrecision = 9
fieldAlias = "长度"
arcpy.AddField_management(outputFC, fieldName3, "DOUBLE", fieldPrecision, "", "",
                          fieldAlias, "NULLABLE")

fieldName4 = "jiange"
fieldAlias = "间隔"
arcpy.AddField_management(outputFC, fieldName4, "LONG", "","","",
                          fieldAlias, "NULLABLE")

fieldName5 = "tpkname"
fieldAlias = "图幅名字"
fieldLength = 50
arcpy.AddField_management(outputFC, fieldName5, "TEXT", "","",fieldLength,
                          fieldAlias, "NULLABLE")

fieldName6 = "daino"
fieldAlias = "带号"
arcpy.AddField_management(outputFC, fieldName6, "LONG", "","","",
                          fieldAlias, "NULLABLE")

cur=arcpy.InsertCursor(outputFC)
for trk_node in trk_nodes:

    trk_node_time = get_xmlnode(trk_node,'time')
    trk_node_length = get_xmlnode(trk_node,'length')
    trk_node_jiange = get_xmlnode(trk_node,'jiange')
    trk_node_name = get_xmlnode(trk_node,'name')
    trk_node_daino = get_xmlnode(trk_node,'daino')
    trk_node_tpkname = get_xmlnode(trk_node,'tpkname')

    trk_time =get_nodevalue(trk_node_time[0]).encode('utf-8','ignore')
    trk_length =get_nodevalue(trk_node_length[0]).encode('utf-8','ignore')
    trk_jiange =get_nodevalue(trk_node_jiange[0]).encode('utf-8','ignore')
    trk_name =get_nodevalue(trk_node_name[0]).encode('utf-8','ignore')
    trk_daino =get_nodevalue(trk_node_daino[0]).encode('utf-8','ignore')
    trk_tpkname =get_nodevalue(trk_node_tpkname[0]).encode('utf-8','ignore')


    array = arcpy.Array()
    trkseg_node = get_xmlnode(trk_node,'trkseg')
    print trkseg_node
    trkpt_nodes = get_xmlnode(trkseg_node[0],'trkpt')
    print trkpt_nodes
    for trkpt_node in trkpt_nodes:
         trkpt_node_x = get_xmlnode(trkpt_node,'X')
         trkpt_node_y = get_xmlnode(trkpt_node,'Y')
         trkpt_x =get_nodevalue(trkpt_node_x[0]).encode('utf-8','ignore')
         trkpt_y =get_nodevalue(trkpt_node_y[0]).encode('utf-8','ignore')
         x=float(trkpt_x)
         y=float(trkpt_y)
         pnt=arcpy.Point()
         pnt.X = trkpt_y
         pnt.Y = trkpt_x
         array.add(pnt)
         print x
         print y
    polyline = arcpy.Polyline(array)
    array.removeAll()
    feat= cur.newRow()
    feat.shape = polyline
    feat.setValue("shape",polyline)
    feat.setValue("time",trk_time)
    feat.setValue("length",float(trk_length))
    feat.setValue("jiange",int(trk_jiange))
    feat.setValue("name",trk_name)
    feat.setValue("daino",int(trk_daino))
    feat.setValue("tpkname",trk_tpkname)
    cur.insertRow(feat)
    del  feat
del cur

还有另外一种方式使用arcpy.da模块下面的插入游标，根据arcgis的帮助文档，这种方式速度会更快， 详情见这里，代码如下：

#coding=utf-8
import arcpy, os, time
import xml.dom.minidom
import random
from arcpy import env
arcpy.env.overwriteOutput = True 

inGPXFile = arcpy.GetParameterAsText(0)
#inpath = 'F:\\gpx\\航迹-settingDB-20150605031316.gpx'
#uipath = unicode(inpath , "utf8")

outputFC = arcpy.GetParameterAsText(1)
#outputFC = r'F:\gpx\20150605031316.shp'
#uoutputFC = unicode(outputFC , "utf8")

# 打开xml文档
dom = xml.dom.minidom.parse(inGPXFile)
#得到文档元素对象
root = dom.documentElement

def get_attrvalue(node, attrname):
     return node.getAttribute(attrname) if node else ''

def get_nodevalue(node, index = 0):
     if node:
          if node.childNodes:
               return node.childNodes[index].nodeValue   
     else:
          return None

def get_xmlnode(node,name):
    return node.getElementsByTagName(name) if node else []

trk_nodes = get_xmlnode(root,'trk')
#获得节点测试
print trk_nodes

#创建shp
path = os.path.split(outputFC)[0]
name = os.path.split(outputFC)[1]
print path
print name
arcpy.CreateFeatureclass_management(path,name,"POLYLINE")

fieldName1 = "name"
fieldAlias = "轨迹名称"
fieldLength = 50
arcpy.AddField_management(outputFC, fieldName1, "TEXT", "","",fieldLength,
                          fieldAlias, "NULLABLE")

fieldName2 = "time"
fieldAlias = "时间"
fieldLength = 50
arcpy.AddField_management(outputFC, fieldName2, "TEXT", "","",fieldLength,
                          fieldAlias, "NULLABLE")

fieldName3 = "length"
fieldPrecision = 9
fieldAlias = "长度"
arcpy.AddField_management(outputFC, fieldName3, "DOUBLE", fieldPrecision, "", "",
                          fieldAlias, "NULLABLE")

fieldName4 = "jiange"
fieldAlias = "间隔"
arcpy.AddField_management(outputFC, fieldName4, "LONG", "","","",
                          fieldAlias, "NULLABLE")

fieldName5 = "tpkname"
fieldAlias = "图幅名字"
fieldLength = 50
arcpy.AddField_management(outputFC, fieldName5, "TEXT", "","",fieldLength,
                          fieldAlias, "NULLABLE")

fieldName6 = "daino"
fieldAlias = "带号"
arcpy.AddField_management(outputFC, fieldName6, "LONG", "","","",
                          fieldAlias, "NULLABLE")
cur = arcpy.da.InsertCursor(outputFC, ("time","length","jiange","name","daino","tpkname","SHAPE@"))
for trk_node in trk_nodes:

    trk_node_time = get_xmlnode(trk_node,'time')
    trk_node_length = get_xmlnode(trk_node,'length')
    trk_node_jiange = get_xmlnode(trk_node,'jiange')
    trk_node_name = get_xmlnode(trk_node,'name')
    trk_node_daino = get_xmlnode(trk_node,'daino')
    trk_node_tpkname = get_xmlnode(trk_node,'tpkname')

    trk_time =get_nodevalue(trk_node_time[0]).encode('utf-8','ignore')
    trk_length =get_nodevalue(trk_node_length[0]).encode('utf-8','ignore')
    trk_jiange =get_nodevalue(trk_node_jiange[0]).encode('utf-8','ignore')
    trk_name =get_nodevalue(trk_node_name[0]).encode('utf-8','ignore')
    trk_daino =get_nodevalue(trk_node_daino[0]).encode('utf-8','ignore')
    trk_tpkname =get_nodevalue(trk_node_tpkname[0]).encode('utf-8','ignore')

    
    array = arcpy.Array()
    trkseg_node = get_xmlnode(trk_node,'trkseg')
    print trkseg_node
    trkpt_nodes = get_xmlnode(trkseg_node[0],'trkpt')
    print trkpt_nodes
    for trkpt_node in trkpt_nodes:
         trkpt_node_x = get_xmlnode(trkpt_node,'X')
         trkpt_node_y = get_xmlnode(trkpt_node,'Y')
         trkpt_x =get_nodevalue(trkpt_node_x[0]).encode('utf-8','ignore')
         trkpt_y =get_nodevalue(trkpt_node_y[0]).encode('utf-8','ignore')
         x=float(trkpt_x)
         y=float(trkpt_y)
         pnt=arcpy.Point()
         pnt.X = trkpt_y
         pnt.Y = trkpt_x
         array.add(pnt)
         print x
         print y
    polyline = arcpy.Polyline(array)
    row =[trk_time,float(trk_length),int(trk_jiange),trk_name,int(trk_daino),trk_tpkname,polyline] 
    cur.insertRow(row)

至于如何根据脚本创建模型工具，可以去看下基础入门之3和4