將資料表匯出至 CSV 檔案

設定您的環境。如需詳細資訊，請參閱先決條件。

將下列範例程式碼儲存至名為 textract_python_table_parser.py 的檔案。在函數 中get_table_csv_results，profile-name將 取代為可擔任角色的設定檔名稱，並將 region取代為您要執行程式碼的區域。

import webbrowser, os
import json
import boto3
import io
from io import BytesIO
import sys
from pprint import pprint


def get_rows_columns_map(table_result, blocks_map):
    rows = {}
    scores = []
    for relationship in table_result['Relationships']:
        if relationship['Type'] == 'CHILD':
            for child_id in relationship['Ids']:
                cell = blocks_map[child_id]
                if cell['BlockType'] == 'CELL':
                    row_index = cell['RowIndex']
                    col_index = cell['ColumnIndex']
                    if row_index not in rows:
                        # create new row
                        rows[row_index] = {}
                    
                    # get confidence score
                    scores.append(str(cell['Confidence']))
                        
                    # get the text value
                    rows[row_index][col_index] = get_text(cell, blocks_map)
    return rows, scores


def get_text(result, blocks_map):
    text = ''
    if 'Relationships' in result:
        for relationship in result['Relationships']:
            if relationship['Type'] == 'CHILD':
                for child_id in relationship['Ids']:
                    word = blocks_map[child_id]
                    if word['BlockType'] == 'WORD':
                        if "," in word['Text'] and word['Text'].replace(",", "").isnumeric():
                            text += '"' + word['Text'] + '"' + ' '
                        else:
                            text += word['Text'] + ' '
                    if word['BlockType'] == 'SELECTION_ELEMENT':
                        if word['SelectionStatus'] =='SELECTED':
                            text +=  'X '
    return text


def get_table_csv_results(file_name):

    with open(file_name, 'rb') as file:
        img_test = file.read()
        bytes_test = bytearray(img_test)
        print('Image loaded', file_name)

    # process using image bytes
    # get the results
    session = boto3.Session(profile_name='profile-name')
    client = session.client('textract', region_name='region')
    response = client.analyze_document(Document={'Bytes': bytes_test}, FeatureTypes=['TABLES'])

    # Get the text blocks
    blocks=response['Blocks']
    pprint(blocks)

    blocks_map = {}
    table_blocks = []
    for block in blocks:
        blocks_map[block['Id']] = block
        if block['BlockType'] == "TABLE":
            table_blocks.append(block)

    if len(table_blocks) <= 0:
        return "<b> NO Table FOUND </b>"

    csv = ''
    for index, table in enumerate(table_blocks):
        csv += generate_table_csv(table, blocks_map, index +1)
        csv += '\n\n'

    return csv

def generate_table_csv(table_result, blocks_map, table_index):
    rows, scores = get_rows_columns_map(table_result, blocks_map)

    table_id = 'Table_' + str(table_index)
    
    # get cells.
    csv = 'Table: {0}\n\n'.format(table_id)

    for row_index, cols in rows.items():
        for col_index, text in cols.items():
            col_indices = len(cols.items())
            csv += '{}'.format(text) + ","
        csv += '\n'
        
    csv += '\n\n Confidence Scores % (Table Cell) \n'
    cols_count = 0
    for score in scores:
        cols_count += 1
        csv += score + ","
        if cols_count == col_indices:
            csv += '\n'
            cols_count = 0

    csv += '\n\n\n'
    return csv

def main(file_name):
    table_csv = get_table_csv_results(file_name)

    output_file = 'output.csv'

    # replace content
    with open(output_file, "wt") as fout:
        fout.write(table_csv)

    # show the results
    print('CSV OUTPUT FILE: ', output_file)


if __name__ == "__main__":
    file_name = sys.argv[1]
    main(file_name)

在命令提示字元中，輸入下列命令。file 以您要分析的文件映像檔案名稱取代 。

python textract_python_table_parser.py file

設定您的環境。如需詳細資訊，請參閱先決條件。

請確定您已遵循 中的指示，請參閱 為非同步操作設定 Amazon Textract。該頁面上記錄的程序可讓您傳送和接收有關非同步任務完成狀態的訊息。

在下列程式碼範例中，將 的值取代roleArn為您在步驟 2 中建立的角色指派的 Arn。將 的值取代bucket為包含 文件的 S3 儲存貯體名稱。將 的值取代document為 S3 儲存貯體中的文件名稱。將 的值取代region_name為您儲存貯體區域的名稱。

將下列範例程式碼儲存至名為 start_doc_analysis_for_table_extraction.py 的檔案。

import boto3
import time

class DocumentProcessor:

    jobId = ''
    region_name = ''

    roleArn = ''
    bucket = ''
    document = ''

    sqsQueueUrl = ''
    snsTopicArn = ''
    processType = ''

    def __init__(self, role, bucket, document, region):
        self.roleArn = role
        self.bucket = bucket
        self.document = document
        self.region_name = region

        self.textract = boto3.client('textract', region_name=self.region_name)
        self.sqs = boto3.client('sqs')
        self.sns = boto3.client('sns')

    def ProcessDocument(self):

        jobFound = False

        response = self.textract.start_document_analysis(DocumentLocation={'S3Object': {'Bucket': self.bucket, 'Name': self.document}},
                FeatureTypes=["TABLES", "FORMS"], NotificationChannel={'RoleArn': self.roleArn, 'SNSTopicArn': self.snsTopicArn})
        print('Processing type: Analysis')

        print('Start Job Id: ' + response['JobId'])

        print('Done!')

    def CreateTopicandQueue(self):

        millis = str(int(round(time.time() * 1000)))

        # Create SNS topic
        snsTopicName = "AmazonTextractTopic" + millis

        topicResponse = self.sns.create_topic(Name=snsTopicName)
        self.snsTopicArn = topicResponse['TopicArn']

        # create SQS queue
        sqsQueueName = "AmazonTextractQueue" + millis
        self.sqs.create_queue(QueueName=sqsQueueName)
        self.sqsQueueUrl = self.sqs.get_queue_url(QueueName=sqsQueueName)['QueueUrl']

        attribs = self.sqs.get_queue_attributes(QueueUrl=self.sqsQueueUrl,
                                                AttributeNames=['QueueArn'])['Attributes']

        sqsQueueArn = attribs['QueueArn']

        # Subscribe SQS queue to SNS topic
        self.sns.subscribe(TopicArn=self.snsTopicArn, Protocol='sqs', Endpoint=sqsQueueArn)

        # Authorize SNS to write SQS queue
        policy = """{{
      "Version":"2012-10-17",
      "Statement":[
        {{
          "Sid":"MyPolicy",
          "Effect":"Allow",
          "Principal" : {{"AWS" : "*"}},
          "Action":"SQS:SendMessage",
          "Resource": "{}",
          "Condition":{{
            "ArnEquals":{{
              "aws:SourceArn": "{}"
            }}
          }}
        }}
      ]
    }}""".format(sqsQueueArn, self.snsTopicArn)

        response = self.sqs.set_queue_attributes(
            QueueUrl=self.sqsQueueUrl,
            Attributes={
                'Policy': policy
            })

def main():
    roleArn = 'role-arn'
    bucket = 'bucket-name'
    document = 'document-name'
    region_name = 'region-name'

    analyzer = DocumentProcessor(roleArn, bucket, document, region_name)
    analyzer.CreateTopicandQueue()
    analyzer.ProcessDocument()

if __name__ == "__main__":
    main()

執行程式碼。程式碼將列印 JobId。向下複製此 JobId。

等待您的任務完成處理，完成後，請將下列程式碼複製到名為 get_doc_analysis_for_table_extraction.py 的檔案。將 的值取代jobId為您先前複製的任務 ID。將 的值取代region_name為與您的 Textract 角色相關聯的區域名稱。將 的值取代file_name為您要提供輸出 CSV 的名稱。

import boto3
from pprint import pprint

jobId = ''
region_name = ''
file_name = ''

textract = boto3.client('textract', region_name=region_name)

# Display information about a block
def DisplayBlockInfo(block):
    print("Block Id: " + block['Id'])
    print("Type: " + block['BlockType'])
    if 'EntityTypes' in block:
        print('EntityTypes: {}'.format(block['EntityTypes']))

    if 'Text' in block:
        print("Text: " + block['Text'])

    if block['BlockType'] != 'PAGE':
        print("Confidence: " + "{:.2f}".format(block['Confidence']) + "%")

def GetResults(jobId, file_name):
    maxResults = 1000
    paginationToken = None
    finished = False

    while finished == False:

        response = None

        if paginationToken == None:
            response = textract.get_document_analysis(JobId=jobId, MaxResults=maxResults)
        else:
            response = textract.get_document_analysis(JobId=jobId, MaxResults=maxResults,
                                                           NextToken=paginationToken)

        blocks = response['Blocks']
        table_csv = get_table_csv_results(blocks)
        output_file = file_name + ".csv"
        # replace content
        with open(output_file, "at") as fout:
            fout.write(table_csv)
        # show the results
        print('Detected Document Text')
        print('Pages: {}'.format(response['DocumentMetadata']['Pages']))
        print('OUTPUT TO CSV FILE: ', output_file)

        # Display block information
        for block in blocks:
            DisplayBlockInfo(block)
            print()
            print()

        if 'NextToken' in response:
            paginationToken = response['NextToken']
        else:
            finished = True


def get_rows_columns_map(table_result, blocks_map):
    rows = {}
    for relationship in table_result['Relationships']:
        if relationship['Type'] == 'CHILD':
            for child_id in relationship['Ids']:
                try:
                    cell = blocks_map[child_id]
                    if cell['BlockType'] == 'CELL':
                        row_index = cell['RowIndex']
                        col_index = cell['ColumnIndex']
                        if row_index not in rows:
                            # create new row
                            rows[row_index] = {}

                        # get the text value
                        rows[row_index][col_index] = get_text(cell, blocks_map)
                except KeyError:
                    print("Error extracting Table data - {}:".format(KeyError))
                    pass
    return rows


def get_text(result, blocks_map):
    text = ''
    if 'Relationships' in result:
        for relationship in result['Relationships']:
            if relationship['Type'] == 'CHILD':
                for child_id in relationship['Ids']:
                    try:
                        word = blocks_map[child_id]
                        if word['BlockType'] == 'WORD':
                            text += word['Text'] + ' '
                        if word['BlockType'] == 'SELECTION_ELEMENT':
                            if word['SelectionStatus'] == 'SELECTED':
                                text += 'X '
                    except KeyError:
                        print("Error extracting Table data - {}:".format(KeyError))

    return text


def get_table_csv_results(blocks):

    pprint(blocks)

    blocks_map = {}
    table_blocks = []
    for block in blocks:
        blocks_map[block['Id']] = block
        if block['BlockType'] == "TABLE":
            table_blocks.append(block)

    if len(table_blocks) <= 0:
        return "<b> NO Table FOUND </b>"

    csv = ''
    for index, table in enumerate(table_blocks):
        csv += generate_table_csv(table, blocks_map, index + 1)
        csv += '\n\n'
        # In order to generate separate CSV file for every table, uncomment code below
        #inner_csv = ''
        #inner_csv += generate_table_csv(table, blocks_map, index + 1)
        #inner_csv += '\n\n'
        #output_file = file_name + "___" + str(index) + ".csv"
        # replace content
        #with open(output_file, "at") as fout:
        #    fout.write(inner_csv)

    return csv


def generate_table_csv(table_result, blocks_map, table_index):
    rows = get_rows_columns_map(table_result, blocks_map)

    table_id = 'Table_' + str(table_index)

    # get cells.
    csv = 'Table: {0}\n\n'.format(table_id)

    for row_index, cols in rows.items():

        for col_index, text in cols.items():
            csv += '{}'.format(text) + ","
        csv += '\n'

    csv += '\n\n\n'
    return csv

response_blocks = GetResults(jobId, file_name)

執行程式碼。

取得結果後，請務必刪除相關聯的 SNS 和 SQS 資源，否則可能會產生這些資源的費用。