使用 python 获取文本为 csv 格式

Question

I am able to get the data from pdf to text. But now i need to get the data in csv format with table structure.

I tried it to get the table structure with but it didn't happen.Any inputs? Also, i'm able to generate it through json. Is there a way to get the result into table csv format? any inputs?

Below is the code i have used.

import boto3
import time

# Document
s3BucketName = "textractanalysisexample"
documentName = "sheet_example.pdf"

def startJob(s3BucketName, objectName):
   response = None
   client = boto3.client('textract')
   response = client.start_document_text_detection(
   DocumentLocation={
       'S3Object': {
           'Bucket': s3BucketName,
           'Name': objectName
       }
   })
   
   return response["JobId"]
   
def isJobComplete(jobId):
   # For production use cases, use SNS based notification 
   # Details at: https://docs.aws.amazon.com/textract/latest/dg/api-async.html
   time.sleep(5)
   client = boto3.client('textract')
   response = client.get_document_text_detection(JobId=jobId)
   status = response["JobStatus"]
   #print("Job status: {}".format(status))

   while(status == "IN_PROGRESS"):
       time.sleep(5)
       response = client.get_document_text_detection(JobId=jobId)
       status = response["JobStatus"]
       #print("Job status: {}".format(status))

   return status
   
def getJobResults(jobId):

   pages = []

   client = boto3.client('textract')
   response = client.get_document_text_detection(JobId=jobId)
   
   pages.append(response)
   print("Resultset page recieved: {}".format(len(pages)))
   nextToken = None
   if('NextToken' in response):
       nextToken = response['NextToken']

   while(nextToken):

       response = client.get_document_text_detection(JobId=jobId, NextToken=nextToken)

       pages.append(response)
       #print("Resultset page recieved: {}".format(len(pages)))
       nextToken = None
       if('NextToken' in response):
           nextToken = response['NextToken']

   return pages

def lambda_handler(event, context):
   
   jobId = startJob(s3BucketName, documentName)
   #print("Started job with id: {}".format(jobId))
   if(isJobComplete(jobId)):
       response = getJobResults(jobId)
   
   # Print detected text
   for resultPage in response:
       for item in resultPage["Blocks"]:
           if item["BlockType"] == "LINE":
               print (item["Text"]) ```
     

Answer 1

You can import CSV to write to a csv file like so:

import csv

with open('my_pdf.txt', 'r') as in_file:
    stripped = (line.strip() for line in in_file)
    lines = (line.split(",") for line in stripped if line)
    with open('my_pdf.csv', 'w') as out_file:
        writer = csv.writer(out_file)
        writer.writerow(('title', 'intro'))
        writer.writerows(lines)

You can just put in the rows you need, and this splits your data into comma separated values. You can see more information for CSV writer (and csv python in general) here (Python Docs) .