如何将 boto3 输出添加到新文件中并使用一个脚本将其上传回 AWS s3 存储桶？

Question

The purpose of the code below is to read a pdf file located in s3 bucket and list the values of the pdf in the terminal. My end goal is to load those values into a csv/xlsx and upload it to the same s3 bucket . In other words, this is a file conversion from pdf to xlsx .

Adding item to_excel at the end is not loading the data to excel, any suggestions? the code below is only creating an empty xlsx file on the local directory but I need it to do the following:

1. save the data in xlsx listed in the terminal from reading the pdf located in s3
2. take that xlsx file that has the terminal data and upload it back to s3

import boto3
import time
import pandas as pd

# Textract APIs used - "start_document_text_detection", "get_document_text_detection"
def InvokeTextDetectJob(s3BucketName, objectName):
    response = None
    client = boto3.client('textract')
    response = client.start_document_text_detection(
            DocumentLocation={
                      'S3Object': {
                              `enter code here`      'Bucket': s3BucketName,
                                    'Name': objectName
                                }
           })
    return response["JobId"]

def CheckJobComplete(jobId):
    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 JobResults(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

# S3 Document Data
s3BucketName = "pdfbucket"
documentName = "pdf"

# Function invokes
jobId = InvokeTextDetectJob(s3BucketName, documentName)
print("Started job with id: {}".format(jobId))
if(CheckJobComplete(jobId)):
    response = JobResults(jobId)
    for resultPage in response:
        for item in resultPage["Blocks"]:
            if item["BlockType"] == "LINE":
                print (item["Text"])

with pd.ExcelWriter('output_cp.xlsx') as writer:
    item.to_excel(writer, sheetName='Sheet1')

Answer 1

So after some more research and checking with other people, below is the final product.

The purpose of this code is the following:

1. Read a pdf file stored in an AWS S3 Bucket
2. After reading the file, save the data as text in a new xlsx file

import boto3
import time
import pandas as pd
from xlsxwriter import Workbook

# Textract APIs used - "start_document_text_detection", "get_document_text_detection"


def InvokeTextDetectJob(s3BucketName, objectName):
    response = None
    client = boto3.client('textract')
    response = client.start_document_text_detection(
        DocumentLocation={
            'S3Object': {
                'Bucket': s3BucketName,
                'Name': objectName
            }
        })
    return response["JobId"]


def CheckJobComplete(jobId):
    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 JobResults(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


# S3 Document Data
s3BucketName = "cpaypdf"
documentName = "cp.pdf"

# Function invokes
jobId = InvokeTextDetectJob(s3BucketName, documentName)
print("Started job with id: {}".format(jobId))
if(CheckJobComplete(jobId)):
    response = JobResults(jobId)
    df = pd.DataFrame(
        columns=[
            "Text"
        ]
    )
    for resultPage in response:
        for item in resultPage["Blocks"]:
            if item["BlockType"] == "LINE":
                df = df.append({
                    "Text": item['Text']
                },
                    ignore_index=True
                )
    writer = pd.ExcelWriter("result.xlsx", engine='xlsxwriter')
    df.to_excel(writer, sheet_name='sheetname', index=False)
    writer.save()