代码

此脚本对于审核元数据很有用。 该脚本可以在多个 enterprise 地理数据库上运行，并将创建包含以下列的输出 CSV 文件：“地理数据库”、“要素数据集”、“要素类”、“空间参考”、“行计数”、“列计数”、“元数据标题”、“元数据描述”、“元数据摘要”、“元数据积分”、“元数据访问”约束'。

要使用此脚本，您需要更改第 19 行以指向您的 SDE 连接文件。

import csv
import os

from arcpy import Describe
from arcpy import env
from arcpy import GetCount_management
from arcpy import ListDatasets
from arcpy import ListFeatureClasses
from arcpy import ListFields
from arcpy import metadata as md

# the output CSV file name
output_csv_file = 'enterprise_gdbs_results.csv'

# or use this to make the output CSV file name the same as the script name
# output_csv_file = os.path.basename(__file__).replace('.py','.csv')

# change this path to use your SDE connection files
sde_connection_files = 'c:/gis/sde_connection_files'

with open(output_csv_file,'w',newline='') as csv_file:
    csv_writer = csv.writer(csv_file, delimiter=',')
    column_headers = [
        'Geodatabase', 'Feature Dataset', 'Feature Class', 
        'Spatial Reference', 'Row Count', 'Column Count', 
        'Metadata Title', 'Metadata Description', 'Metadata Summary',
        'Metadata Credits', 'Metadata Access Constraints'
    ]
    
    csv_writer.writerow(column_headers)

    for (folder, dirs, files) in os.walk(sde_connection_files):
        for file in files:
            if(not file.startswith('_') and file.endswith('.sde')):
                geodatabase = file.split('@')[1]

                wksp = os.path.join(folder,file)
                env.workspace = wksp

                datasets = ListDatasets(feature_type='feature')
                datasets = [''] + datasets if datasets is not None else []

                for dataset in datasets:
                    for feature_class in ListFeatureClasses(dataset):
                        desc = Describe(feature_class)
                        spatial_reference = desc.SpatialReference.factoryCode
                        count = GetCount_management(feature_class)[0]
                        column_count = len(ListFields(feature_class))
                        metadata = md.Metadata(feature_class)

                        row = [
                            geodatabase,dataset,feature_class,
                            spatial_reference,count,column_count,
                            metadata.title,metadata.description,
                            metadata.summary,metadata.credits,
                            metadata.accessConstraints    
                        ]

                        print(row)
                        
                        csv_writer.writerow(row)

此脚本对于审核元数据很有用。 该脚本可以在多个 文件地理数据库 上运行，并将创建一个包含以下列的输出 CSV 文件：“上次修改”、“文件地理数据库”、“要素数据集”、“要素类”、“空间参考”、“行数”、“列数”、“元数据标题”、“元数据描述”、“元数据摘要”、“元数据积分”、 “元数据访问限制”。

import csv
import os
import time

from arcpy import Describe
from arcpy import env
from arcpy import GetCount_management
from arcpy import ListDatasets
from arcpy import ListFeatureClasses
from arcpy import ListFields
from arcpy import metadata as md

folder = r'...'
log = open('log.txt', 'w')
output_csv_file = os.path.basename(__file__).replace('.py','.csv')

with open(output_csv_file,'w',newline='') as csv_file:
    csv_writer = csv.writer(csv_file, delimiter=',')
    column_headers = [
        'Last Modified','File Geodatabase', 'Feature Dataset', 'Feature Class', 
        'Spatial Reference', 'Row Count', 'Column Count', 
        'Metadata Title', 'Metadata Description', 'Metadata Summary',
        'Metadata Credits', 'Metadata Access Constraints'
    ]
    
    csv_writer.writerow(column_headers)

    for (folder, dirs, files) in os.walk(folder):
        if(folder.endswith('.gdb')):
            print(folder)

            last_modified = '???'

            try:
                last_modified = time.ctime(max(os.stat(root).st_mtime for root,_,_ in os.walk(folder)))
            except:
                msg = 'Error getting last modified date for {}'.format(folder)
                print(msg)
                log.write('{}\n'.format(msg))
                pass

            fgdb = folder
            env.workspace = fgdb

            datasets = []

            try:
                datasets = ListDatasets(feature_type='feature')
                datasets = [''] + datasets if datasets is not None else []
            except:
                msg = 'Error getting datasets for {}'.format(folder)
                print(msg)
                log.write('{}\n'.format(msg))
                pass

            for dataset in datasets:
                for feature_class in ListFeatureClasses(dataset):
                    desc = Describe(feature_class)
                    spatial_reference = desc.SpatialReference.factoryCode
                    count = GetCount_management(feature_class)[0]
                    column_count = len(ListFields(feature_class))
                
                    metadata = None
                    row = []

                    try:
                        metadata = md.Metadata(feature_class)
                        row = [
                            last_modified,
                            fgdb,dataset,feature_class,
                            spatial_reference,count,column_count,
                            metadata.title,metadata.description,
                            metadata.summary,metadata.credits,
                            metadata.accessConstraints    
                        ]
                    except:
                        row = [
                            last_modified,
                            fgdb,dataset,feature_class,
                            spatial_reference,count,column_count,
                            'error','error','error','error','error'    
                        ]
                        pass

                    csv_writer.writerow(row)

log.close()

有时，当数据从 shapefile 转换为要素类时，或者如果运行地理处理工具时不小心，要素类最终可能会出现冗余字段。 例如，要素类可能有一个名为“OBJECTID”的字段，并且同一要素类中可能还有另一个名为“OBJECTID_1”的字段。 这些字段之一应该是要素类的 OID 字段，但是，有时也不清楚哪个 OBJECTID 字段是正确的字段。 下面的这个脚本不需要知道哪个字段是OID字段，因为如果无法删除该字段，第35行将失败，并且脚本将继续运行。 下面的脚本显示了检查字段名称的两种不同方式，即字段名称可以包含在第 10 行的列表中，或者字段名称可以在第 33 行添加“OBJECTID”前缀。对于此脚本，删除的字段将输出到 CSV 文件。 输出 CSV 文件的名称与 Python 脚本的名称相同 - 请参阅第 12 行。在运行脚本之前，最好注释掉第 35 行，运行脚本，然后检查输出 CSV 文件以查看哪些字段将被删除。 此外，字段一旦删除就无法恢复，因此如有疑问，应首先备份文件地理数据库。

import csv
import os

from arcpy import env
from arcpy import ListDatasets
from arcpy import ListFeatureClasses
from arcpy import ListFields
from arcpy.management import DeleteField

fields_to_delete = ['objectid', 'objectid_1', 'objectid_12', 'shape_le_1', 'shape_leng', 'shape_length', 'shape__length', 'shape__area']
input_folder = r'...'
output_csv_file = os.path.basename(__file__).replace('.py','.csv')

with open(output_csv_file, 'w', newline='') as csv_file:
    csv_writer = csv.writer(csv_file)
    csv_writer.writerow(['File Geodatabase','Feature Dataset', 'Feature Class', 'Field'])

    for (folder, dirs, files) in os.walk(input_folder):
        if(folder.endswith('.gdb')):
            file_geodatabase = folder
            print('Processing {}'.format(file_geodatabase))

            env.workspace = file_geodatabase

            feature_datasets = ListDatasets(feature_type='feature')
            feature_datasets = [''] + feature_datasets if feature_datasets is not None else []

            for feature_dataset in feature_datasets:
                feature_classes = ListFeatureClasses(feature_dataset=feature_dataset)

                for feature_class in feature_classes:
                    for field in ListFields(feature_class):
                        if field.name.lower() in fields_to_delete or field.name.lower().startswith('objectid'):
                            try:
                                DeleteField(feature_class, field.name)
                                csv_writer.writerow([file_geodatabase, feature_dataset, feature_class, field.name])
                            
                            except:
                                pass

在发布地图服务或要素服务之前，最好先重新计算要素类范围。 这是因为要素类范围有时可能是错误的。 有多种情况可能会导致要素类范围错误，包括对数据运行地理处理任务从而更改数据范围，并且导入数据时要素类范围也可能错误，因为初始要素类范围可能是根据导入数据的子集计算的。 查看要素类范围的第一个简单方法是错误的，当单击“缩放到图层”按钮时，地图不会缩放到正确的范围。 图层范围不正确的另一个迹象是图层未正确渲染。 例如，导入大型 GeoJSON 文件时，在重新计算该要素类的范围之前，该文件可能无法在 ArcGIS Pro 中正确渲染。

import os

from arcpy import env
from arcpy import ListDatasets
from arcpy import ListFeatureClasses
from arcpy.management import RecalculateFeatureClassExtent

input_folder = r'...'

for (folder, dirs, files) in os.walk(input_folder):
    if(folder.endswith('.gdb')):
        env.workspace = folder

        feature_datasets = ListDatasets(feature_type='feature')
        feature_datasets = [''] + feature_datasets if feature_datasets is not None else []

        for feature_dataset in feature_datasets:
            feature_classes = ListFeatureClasses(feature_dataset=feature_dataset)

            for feature_class in feature_classes:
                print('{}\t{}\t{}'.format(folder, feature_dataset, feature_class))
                RecalculateFeatureClassExtent(feature_class)

此脚本用于列出目录中的所有 shapefile，以帮助了解您拥有的 shapefile 数量，以便将它们迁移到文件地理数据库或企业级地理数据库中的要素类。 请注意，出于多种原因，通常应避免使用 shapefile。 shapefile 格式是一种非常古老的格式，并且有更好的格式用于共享空间数据。 Shapefile 的压缩性能很差，当数据导出到 shapefile 时，字段名称会被截断为十个字符，这使得很难猜测原始字段名称是什么。 在考虑使用 shapefile 之前，请使用地理数据库要素类、geopackage、geojson 或其他格式。

import csv
import os

# change the input folder here for the directory you want to search
input_folder = r'\\...\...'

# change the file name here to the output file you want
results_file = 'shapefiles.csv'

extns = ['.aih', '.ain', '.atx', '.cpg', '.dbf', '.fbn', '.fbx', '.ixs', '.mxs', '.prj', '.sbn', '.sbx', '.shp', '.shx', '.xml']

with open(results_file, 'w', newline='') as csvfile:
    csvwriter = csv.writer(csvfile)
    column_headers = ['Folder','Shapefile'] + extns
    csvwriter.writerow(column_headers)

    for (folder, dirs, files) in os.walk(input_folder):
        for file in files:
            if(file.endswith('.shp')):
                shapefile_name = file.replace('.shp','')

                line = [folder,shapefile_name]

                for extn in extns:
                    file_path = os.path.join(folder,'{}{}'.format(shapefile_name,extn))
                    file_exists = 'Y' if os.path.exists(file_path) else 'N'
                    line.append(file_exists)
                
                csvwriter.writerow(line)

此脚本列出 MXD（ArcMap 文件）和 APRX（ArcGIS Pro 文件）的图层信息。 结果将输出到 CSV 文件并包含以下列：

请注意，ArcMap 使用 Python 2，ArcGIS Pro 使用 Python 3，因此为了让脚本与 Python 3 配合使用 MXD 文件，我们在下面的脚本中将 MXD 转换为 APRX。 此 APRX 仅在内存中，不会保存到磁盘（但如果需要，可以保存到磁盘）。

要在下面运行此命令，请更改第 5 行和第 7 行，并手动创建一个可以克隆到内存中的空白 APRX（第 7 行）。

import csv
import os

from arcpy.mp import ArcGISProject

directory = r'\\...\...'
blank_aprx = r'\\...\...\temp.aprx'
results_file = os.path.basename(__file__).replace('.py','.csv')

# create a CSV file
with open(results_file, 'w', newline='') as csvfile:
    csvwriter = csv.writer(csvfile)

    # write out the column headers in the CSV file
    csvwriter.writerow(['File Path','Folder','File Name','File Type','Map / Data Frame','Layer Name','Layer Source','Is Broken','Definition Query'])

    # loop through all of the folders and files in the input directory
    for folder, dirs, files in os.walk(directory):
        for file in files:
            file_path = os.path.join(folder,file)
            
            # check if it is an MXD file - we need to convert the MXD to APRX (in-memory) because we cannot use Python 3 with MXDs
            if file.endswith('.mxd'):     
                file_type = 'mxd'
                aprx = ArcGISProject(blank_aprx)
                aprx.importDocument(file_path)

            #  check if it is an APRX file
            elif file.endswith('.aprx'):
                file_type = 'aprx'
                aprx = ArcGISProject(file_path)
            
            else:
                # file is not an MXD or APRX, so skip the loop below
                continue

            # list all layers within the 'maps' (for APRXs), or 'data frames' (for MXDs)
            for map in aprx.listMaps():
                for layer in map.listLayers():
                    # if the layer is not a group layer and has a data source
                    if layer.supports('dataSource'):
                        # check if the layer is broken
                        isBroken = layer.isBroken if layer.supports('isBroken') else 'n/a'
                        # check if the layer has a definition query (the WHERE clause in a normal SQL statement - definition queries use SQL)
                        definitionQuery = layer.definitionQuery if layer.supports('definitionQuery') else 'n/a'
                        line = [file_path, folder, file, file_type, map.name, layer.name, layer.dataSource, isBroken, definitionQuery]

                        # write the results to CSV
                        csvwriter.writerow(line)

            # delete the in-memory aprx
            del aprx

print('Results file: {}'.format(results_file))

此脚本列出所有服务的服务信息并将结果输出到 CSV。 CSV 中的列标题如下所示：

运行脚本之前，更改第 22 行至第 31 行的参数。

import csv
import json
import requests

def getToken(url, params):
    response = requests.post(url, params)
    token = json.loads(response.text)['token']
    return token

def fetchUrl(url):
    params = {
        'f': 'json',
        'token': token
    }

    response = requests.post(url, params)
    data = json.loads(response.text)

    return data

web_adaptor = 'arcgis' # web adaptor or load balancer 
token_url = 'https://{}/portal/sharing/rest/generateToken'.format(map_server)

params = {
    'f': 'json',
    'referer': 'https://.../portal/sharing/rest/generateToken',
    'username': 'portaladmin',
    'password': '**************'
}

token = getToken(token_url, params)

''' 
    ArcGIS Admin URL - we are using the admin URL, not the 
    Services Directory URL because the Services Directory will 
    only list the services that are started/running.  We also
    want to know about the stopped services.
'''
admin_url = 'https://{}/{}/admin/services'.format(map_server,web_adaptor)

params = {
    'f': 'json',
    'token': token
}

response = requests.get(admin_url, params)
data = json.loads(response.text)

folders = data['folders']
foldersToExclude = ['System','Utilities']

for folder in foldersToExclude:
    folders.remove(folder)

services = data['services'] 

with open('map_service_info.csv', 'w', newline='') as csv_file:
    csv_writer = csv.writer(csv_file)

    column_names = ['Map Server', 'Folder', 'Service name', 'Service type', 'URL', 'Published By', 'Path', 'Service Description', 'Copyright Info']
    csv_writer.writerow(column_names)

    for service in services:
        folder = ''
        service_name = service['serviceName']
        service_type = service['type']
        url = '{}/{}.{}'.format(admin_url,service_name,service_type)
       
        service_info = fetchUrl(url)
        service_description = service_info['description']
        user_name = service_info['properties']['userName'] if 'userName' in service_info['properties'] else ''
        copyright_info = service_info['properties']['copyright'] if 'copyright' in service_info['properties'] else ''
        path = service_info['properties']['path'] if 'path' in service_info['properties'] else ''

        row = [map_server, folder, service_name, service_type, url, user_name, path, service_description, copyright_info]
        csv_writer.writerow(row)

    for folder in folders:
        url = '{}/{}'.format(admin_url,folder)
        folder_info = fetchUrl(url)

        for service in folder_info['services']:
            folder = folder_info['folderName']
            service_name = service['serviceName']
            service_type = service['type']
            url = '{}/{}/{}.{}'.format(admin_url, folder, service_name, service_type, url)

            service_info = fetchUrl(url)
            service_description = service_info['description']
            user_name = service_info['properties']['userName'] if 'userName' in service_info['properties'] else ''
            copyright_info = service_info['properties']['copyright'] if 'copyright' in service_info['properties'] else ''
            path = service_info['properties']['path'] if 'path' in service_info['properties'] else ''

            row = [map_server, folder, service_name, service_type, url, user_name, path, service_description, copyright_info]
            csv_writer.writerow(row)