get_image_server.py

#! /usr/bin/env python
# -*- coding: utf-8 -*-

import httplib
from base64 import b64encode
import urllib2
import sys
import datetime
import time
import json
import arcpy


# The URL for the geoportal's document management API.
connection = httplib.HTTPConnection('<GEOPORTALSERVERDOMAIN>')
userAndPass = b64encode(b"<ADMINUSERNAME>:<ADMINPASSWORD>").decode("ascii")
headers = {'Authorization': 'Basic %s' % userAndPass, 'Content-type': 'application/xml'}
log = sys.stdout
site_root = "https://<YOURDOMAINGOESHERE>/arcgis/rest/services/<FOLDER>/<SERVICENAME>/ImageServer"
count = 0
srFrom = arcpy.SpatialReference(3857)
srTo = arcpy.SpatialReference(4326)


def crawl(page):
	for i in range(1, 10):
		the_url = page + "/" + str(i)
		f = urllib2.urlopen(the_url + "?f=json")  # it's a file like object 

		body_content = f.read()

		print body_content

		body_json = json.loads(body_content)
		# body_json = {"error": {"code": 400, "message": "Unable to complete operation.", "details": []}}

		point = arcpy.Point()
		point.X = body_json['attributes']['CenterX']
		point.Y = body_json['attributes']['CenterY']

		point_geometry = arcpy.PointGeometry(point, srFrom)
		projected_point = point_geometry.projectAs(srTo)
		acquisition_date = body_json['attributes']['AcquisitionDate']
		# print str(acquisition_date)
		local_time = time.localtime(acquisition_date/1000)
		# print str(local_time)

		formatted_time = time.strftime('%Y%m%d', local_time)

		body_xml_pre = """<?xml version="1.0" encoding="UTF-8"?><metadata>
			<idinfo>
				<citation>
					<citeinfo>
						<origin>Esri</origin>
						<pubdate>20160916</pubdate>
						<title>""" + body_json['attributes']['GroupName'] + ' - ' + body_json['attributes']['Name'] + """</title>
						<onlink>""" + the_url + """</onlink>
					</citeinfo>
				</citation>
				<descript>
					<abstract>""" + body_json['attributes']['GroupName'] + ' - ' + body_json['attributes']['Name'] + """</abstract>
					<purpose>Supports all ArcGIS Raster Datasets</purpose>
				</descript>
				<timeperd>
					<timeinfo>
						<mdattim>
							<sngdate>
								<caldate>""" + formatted_time + """</caldate>
							</sngdate>
							<sngdate>
								<caldate>Unknown</caldate>
							</sngdate>
						</mdattim>
					</timeinfo>
					<current>publication date</current>
				</timeperd>
				<status>
					<progress>In work</progress>
					<update>Daily</update>
				</status>
				<spdom>
					<bounding>
						<westbc>""" + str(projected_point.firstPoint.X - 0.5) + """</westbc>
						<eastbc>""" + str(projected_point.firstPoint.X + 0.5) + """</eastbc>
						<northbc>""" + str(projected_point.firstPoint.Y - 0.5) + """</northbc>
						<southbc>""" + str(projected_point.firstPoint.Y + 0.5) + """</southbc>
					</bounding>
				</spdom>
				<keywords>"""

		body_xml_post = """</keywords>
				<accconst>None</accconst>
				<useconst>None</useconst>
			</idinfo>
			<metainfo>
				<metd></metd>
				<metc>
					<cntinfo>
						<cntorgp>
							<cntorg></cntorg>
						</cntorgp>
						<cntaddr>
							<addrtype></addrtype>
							<city></city>
							<state></state>
							<postal></postal>
						</cntaddr>
						<cntvoice></cntvoice>
						<cntemail></cntemail>
					</cntinfo>
				</metc>
				<metstdn>FGDC Content Standard for Digital Geospatial Metadata</metstdn>
				<metstdv>FGDC-STD-001-1998</metstdv>
			</metainfo>
		</metadata>"""

		fields = ['OBJECTID', 'Name', 'MinPS', 'MaxPS', 'LowPS', 'HighPS', 'Category', 'GroupName', 'ProductName', 'SunAzimuth', 'SunElevation', 'WRS_Path', 'WRS_Row', 'Best', 'AcquisitionDate', 'DateUpdated', 'SunAzimuth', 'SunElevation', 'CloudCover', 'PR', 'Latest', 'DayOfYear', 'Month', 'SensorName', 'dataset_id']
		body_xml_info = ""
		for field in fields:
			value = body_json['attributes'][field]
			if field == 'CloudCover':
				value = 100 * value
			body_xml_info += "<theme><themekt>" + field + "</themekt><themekey>" + str(
				value) + "</themekey></theme>"

		body_xml = body_xml_pre + body_xml_info + body_xml_post
		connection.request('PUT', '/<GEOPORTALCONTEXTNAME>/rest/metadata/item', body_xml, headers)
		result = connection.getresponse()
		result.read()
		log.write('%s %s\n' % (result.status, the_url))

		f.close()


def main():
	start = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
	crawl(site_root)
	end = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
	log.write('Start %s\n' % start)
	log.write('End %s\n' % end)


if __name__ == '__main__':
	main()