Parse Documents by Template and Extract Data using a REST API in Python.

ParseByTemplate_Python

Parse Documents by Template and Extract Data
1. Programmatically upload a PDF file on the cloud
2. Parse Documents by Template Object using a REST API in Python
3. Parse Documents by Template File using a REST API in Python

ParseByTemplate_Python_Configurations.py

client_id = "da0c487d-c1c0-45ae-b7bf-43eaf53c5ad5"
client_secret = "479db2b01dcb93a3d4d20efb16dea971"

configuration = groupdocs_parser_cloud.Configuration(client_id, client_secret)
configuration.api_base_url = "https://api.groupdocs.cloud"
my_storage = ""

ParseByTemplate_Python_PassTemplateFile.py

# api initialization
parseApi = groupdocs_parser_cloud.ParseApi.from_config(configuration)

# define parse options
options = groupdocs_parser_cloud.ParseOptions()
options.file_info = groupdocs_parser_cloud.FileInfo()
options.file_info.file_path = "companies.pdf"
options.template_path = "template.json"

# parse request
request = groupdocs_parser_cloud.ParseRequest(options)
result = parseApi.parse(request)

# show results
for data in result.fields_data:
    if data.page_area.page_text_area is not None:
        print("Field name: " + data.name + ". Text :" + data.page_area.page_text_area.text)

    if data.page_area.page_table_area is not None:
        print("Table name: " + data.name)
        for cell in data.page_area.page_table_area.page_table_area_cells:
            print("Table cell. Row " + str(cell.row_index) + " column " + str(cell.column_index) + ". Text: " + cell.page_area.page_text_area.text);

ParseByTemplate_Python_PassTemplateObject.py

# api initialization
parseApi = groupdocs_parser_cloud.ParseApi.from_config(configuration)

# define parse options
options = groupdocs_parser_cloud.ParseOptions()
options.file_info = groupdocs_parser_cloud.FileInfo()
options.file_info.file_path = "companies.pdf"

# Get Template Object
options.template = GetTemplate()  

# parse request
request = groupdocs_parser_cloud.ParseRequest(options)
result = parseApi.parse(request)

# Show Results
for data in result.fields_data:
    if data.page_area.page_text_area is not None:
        print("Field name: " + data.name + ". Text :" + data.page_area.page_text_area.text)

    if data.page_area.page_table_area is not None:
        print("Table name: " + data.name)
        for cell in data.page_area.page_table_area.page_table_area_cells:
            print("Table cell. Row " + str(cell.row_index) + " column " + str(cell.column_index) + ". Text: " + cell.page_area.page_text_area.text);

ParseByTemplate_Python_Template.json

{
  "Fields": [
    {
      "FieldName": "Address",
      "FieldPosition": {
        "FieldPositionType": "Regex",
        "Regex": "Companyaddress:"
      }
    },
    {
      "FieldName": "CompanyAddress",
      "FieldPosition": {
        "FieldPositionType": "Linked",
        "LinkedFieldName": "ADDRESS",
        "IsRightLinked": true,
        "SearchArea": {
          "Height": 10.0,
          "Width": 100.0
        },
        "AutoScale": true
      }
    },
    {
      "FieldName": "Company",
      "FieldPosition": {
        "FieldPositionType": "Regex",
        "Regex": "Companyname:"
      }
    },
    {
      "FieldName": "CompanyName",
      "FieldPosition": {
        "FieldPositionType": "Linked",
        "LinkedFieldName": "Company",
        "IsRightLinked": true,
        "SearchArea": {
          "Height": 10.0,
          "Width": 100.0
        },
        "AutoScale": true
      }
    }
  ],
  "Tables": [
    {
      "TableName": "Companies",
      "DetectorParameters": {
        "Rectangle": {
          "Position": {
            "X": 77.0,
            "Y": 279.0
          },
          "Size": {
            "Height": 41.0,
            "Width": 480.0
          }
        }
      }
    }
  ]
}

ParseByTemplate_Python_TemplateObject.py

def GetTemplate():
        field1 = groupdocs_parser_cloud.Field()
        field1.field_name = "Address"
        fieldPosition1 = groupdocs_parser_cloud.FieldPosition()
        fieldPosition1.field_position_type = "Regex"
        fieldPosition1.regex = "Company address:"
        field1.field_position = fieldPosition1

        field2 = groupdocs_parser_cloud.Field()
        field2.field_name = "CompanyAddress"
        fieldPosition2 = groupdocs_parser_cloud.FieldPosition()
        fieldPosition2.field_position_type = "Linked"
        fieldPosition2.linked_field_name = "ADDRESS"
        fieldPosition2.is_right_linked = True
        size2 = groupdocs_parser_cloud.Size()
        size2.width = 100
        size2.height = 10
        fieldPosition2.search_area = size2
        fieldPosition2.auto_scale = True
        field2.field_position = fieldPosition2
        
        field3 = groupdocs_parser_cloud.Field()
        field3.field_name = "Company"
        fieldPosition3 = groupdocs_parser_cloud.FieldPosition()
        fieldPosition3.field_position_type = "Regex"
        fieldPosition3.regex = "Company name:"
        field3.field_position = fieldPosition3
        
        field4 = groupdocs_parser_cloud.Field()
        field4.field_name = "CompanyName"
        fieldPosition4 = groupdocs_parser_cloud.FieldPosition()
        fieldPosition4.field_position_type = "Linked"
        fieldPosition4.linked_field_name = "Company"
        fieldPosition4.is_right_linked = True
        size4 = groupdocs_parser_cloud.Size()
        size4.width = 100
        size4.height = 10
        fieldPosition4.search_area = size4
        fieldPosition4.auto_scale = True
        field4.field_position = fieldPosition4
        
        table = groupdocs_parser_cloud.Table()
        table.table_name = "Companies"
        detectorparams = groupdocs_parser_cloud.DetectorParameters()
        rect = groupdocs_parser_cloud.Rectangle()
        size = groupdocs_parser_cloud.Size()
        size.height = 60
        size.width = 480
        position = groupdocs_parser_cloud.Point()
        position.x = 77
        position.y = 279
        rect.size = size
        rect.position = position
        detectorparams.rectangle = rect
        table.detector_parameters = detectorparams
        
        fields = [field1, field2, field3, field4]
        tables = [table]
        
        template = groupdocs_parser_cloud.Template()
        template.fields = fields
        template.tables = tables
        return template

ParseByTemplate_Python_Upload.py

# Create instance of the API
file_api = groupdocs_parser_cloud.FileApi.from_config(configuration)

# upload sample files
request = groupdocs_parser_cloud.UploadFileRequest("companies.pdf", "C:\\Files\\companies.pdf", my_storage)
response = file_api.upload_file(request)