Find Text in Table with AI

var https = require("https");
var path = require("path");
var fs = require("fs");

// `request` module is required for file upload.
// Use "npm install request" command to install.
var request = require("request");

// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const API_KEY = "***********************************";

// Direct URL of source PDF file.
// You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/    
const SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.pdf";

// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const Pages = "";

// PDF document password. Leave empty for unprotected documents.
const Password = "";

// Prepare URL for PDF Table Search API call.
// See documentation: https://apidocs.pdf.co
var query = `https://api.pdf.co/v1/pdf/find/table`;
let reqOptions = {
    uri: query,
    headers: { "x-api-key": API_KEY },
    formData: {
        password: Password,
        pages: Pages,
        url: SourceFileUrl
    }
};

// Send request
request.post(reqOptions, function (error, resp, body) {
    if (error) {
        return console.error("Error: ", error);
    }

    var jsonBody = JSON.parse(body);

    // Loop through all found tables, and get json data
    if (jsonBody.body.tables && jsonBody.body.tables.length > 0) {
        for (var i = 0; i < jsonBody.body.tables.length; i++) {
            getJSONFromCoordinates(SourceFileUrl, jsonBody.body.tables[i].PageIndex, jsonBody.body.tables[i].rect, `table_${i + 1}.json`);
        }
    }

});

/**
* Get JSON from specific co-ordinates
*/
function getJSONFromCoordinates(fileUrl, pageIndex, rect, outputFileName) {

    // Prepare request to `PDF To JSON` API endpoint
    var jsonQueryPath = `https://api.pdf.co/v1/pdf/convert/to/json`;

    // Json Request 
    let jsonReqOptions = {
        uri: jsonQueryPath,
        headers: { "x-api-key": API_KEY },
        formData: {
            pages: pageIndex,
            url: fileUrl,
            rect: rect
        }
    };

    // Send request
    request.post(jsonReqOptions, function (error, resp, body) {
        if (error) {
            return console.error("Error: ", error);
        }

        var outputJsonUrl = JSON.parse(body).url;

        // Download JSON file
        var file = fs.createWriteStream(outputFileName);
        https.get(outputJsonUrl, (response2) => {
            response2.pipe(file)
                .on("close", () => {
                    console.log(`Generated JSON file saved as "${outputFileName}" file.`);
                });
        });

    });
}

import requests
  import os

  # The authentication key (API Key).
  # Get your own by registering at https://app.pdf.co
  API_KEY = "***************************************"

  # Direct URL of source PDF file.
  SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.pdf"

  # Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
  Pages = ""

  # PDF document password. Leave empty for unprotected documents.
  Password = ""

  # Prepare URL for PDF Table Search API call.
  query = "https://api.pdf.co/v1/pdf/find/table"
  reqOptions = {
      'password': Password,
      'pages': Pages,
      'url': SourceFileUrl
  }
  headers = {
      'x-api-key': API_KEY
  }


  def getJSONFromCoordinates(fileUrl, pageIndex, rect, outputFileName):
      # Prepare request to `PDF To JSON` API endpoint
      jsonQueryPath = "https://api.pdf.co/v1/pdf/convert/to/json"

      # Json Request
      jsonReqOptions = {
          'pages': pageIndex,
          'url': fileUrl,
          'rect': rect
      }

      # Send request
      response = requests.post(jsonQueryPath, headers=headers, data=jsonReqOptions)
      if response.status_code == 200:
          outputJsonUrl = response.json()['url']

          # Download JSON file
          res = requests.get(outputJsonUrl)
          with open(outputFileName, 'wb') as outfile:
              outfile.write(res.content)
          print(f'Generated JSON file saved as "{outputFileName}" file.')
      else:
          print(f"Request error: {response.status_code} {response.reason}")


  # Send request
  response = requests.post(query, headers=headers, data=reqOptions)
  if response.status_code == 200:
      jsonBody = response.json()

      # Loop through all found tables, and get json data
      if 'tables' in jsonBody['body'] and len(jsonBody['body']['tables']) > 0:
          for i, table in enumerate(jsonBody['body']['tables']):
              getJSONFromCoordinates(SourceFileUrl, table['PageIndex'], table['rect'], f"table_{i + 1}.json")
  else:
      print(f"Request error: {response.status_code} {response.reason}")

using Newtonsoft.Json;
  using Newtonsoft.Json.Linq;
  using System;
  using System.Collections.Generic;
  using System.Net;

  namespace PDFcoApiExample
  {
      class Program
      {
          // The authentication key (API Key).
          // Get your own by registering at https://app.pdf.co
          const String API_KEY = "*****************************************";
          
          // Direct URL of source PDF file.
          // You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/
          const string SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.pdf";
          
          // Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
          const string Pages = "";
          
          // PDF document password. Leave empty for unprotected documents.
          const string Password = "";
          
          static void Main(string[] args)
          {
              // Create standard .NET web client instance
              WebClient webClient = new WebClient();

              // Set API Key
              webClient.Headers.Add("x-api-key", API_KEY);

              // URL for PDF Table Search API call.
              // See documentation: https://apidocs.pdf.co
              string url = "https://api.pdf.co/v1/pdf/find/table";

              // Prepare requests params as JSON
              Dictionary<string, object> parameters = new Dictionary<string, object>();
              parameters.Add("password", Password);
              parameters.Add("pages", Pages);
              parameters.Add("url", SourceFileUrl);

              // Convert dictionary of params to JSON
              string jsonPayload = JsonConvert.SerializeObject(parameters);

              try
              {
                  // Execute POST request with JSON payload
                  string response = webClient.UploadString(url, jsonPayload);

                  // Parse JSON response
                  JObject json = JObject.Parse(response);

                  if (json["status"].ToString() != "error")
                  {
                      Console.WriteLine(response);
                  }
                  else
                  {
                      Console.WriteLine(json["message"].ToString());
                  }
              }
              catch (WebException e)
              {
                  Console.WriteLine(e.ToString());
              }

              webClient.Dispose();


              Console.WriteLine();
              Console.WriteLine("Press any key...");
              Console.ReadKey();
          }
      }
  }

package com.company;

  import com.google.gson.JsonElement;
  import com.google.gson.JsonObject;
  import com.google.gson.JsonParser;
  import okhttp3.*;

  import java.io.*;
  import java.net.*;

  public class Main
  {
      // The authentication key (API Key).
      // Get your own by registering at https://app.pdf.co
      final static String API_KEY = "***********************************";

      // Direct URL of source PDF file.
      // You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/    
      final static String SourceFileURL = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.pdf";

      // Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
      final static String Pages = "";

      // PDF document password. Leave empty for unprotected documents.
      final static String Password = "";

      public static void main(String[] args) throws IOException
      {
          // Create HTTP client instance
          OkHttpClient webClient = new OkHttpClient();

          // Prepare URL for PDF Table Search API call.
          // See documentation: https://apidocs.pdf.co
          String query = "https://api.pdf.co/v1/pdf/find/table";

          // Make correctly escaped (encoded) URL
          URL url = null;
          try
          {
              url = new URI(null, query, null).toURL();
          }
          catch (URISyntaxException e)
          {
              e.printStackTrace();
          }

          // Create JSON payload
          String jsonPayload = String.format("{\"password\": \"%s\", \"pages\": \"%s\", \"url\": \"%s\"}",
                  Password,
                  Pages,
                  SourceFileURL);

          // Prepare request body
          RequestBody body = RequestBody.create(MediaType.parse("application/json"), jsonPayload);
          
          // Prepare request
          Request request = new Request.Builder()
              .url(url)
              .addHeader("x-api-key", API_KEY) // (!) Set API Key
              .addHeader("Content-Type", "application/json")
              .post(body)
              .build();
          
          // Execute request
          Response response = webClient.newCall(request).execute();

          if (response.code() == 200)
          {
              // Parse JSON response
              JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();

              boolean error = json.get("error").getAsBoolean();
              if (!error)
              {
                  System.out.println(response.body().string());
              }
              else
              {
                  // Display service reported error
                  System.out.println(json.get("message").getAsString());
              }
          }
          else
          {
              // Display request error
              System.out.println(response.code() + " " + response.message());
          }
      }
  }