PDF Find Text

// `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.
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 = "";

// Search string.
const SearchString = '[4-9][0-9].[0-9][0-9]'; // Regular expression to find numbers in format dd.dd and between 40.00 to 99.99

// Enable regular expressions (Regex)
const RegexSearch = 'True';

// Prepare URL for PDF text search API call.
// See documentation: https://developer.pdf.co
var query = `https://api.pdf.co/v1/pdf/find`;
let reqOptions = {
    uri: query,
    headers: { "x-api-key": API_KEY },
    formData: {
        password: Password,
        pages: Pages,
        url: SourceFileUrl,
        searchString: SearchString,
        regexSearch: RegexSearch
    }
};

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

    // Parse JSON response
    let data = JSON.parse(body);
    for (let index = 0; index < data.body.length; index++) {
        const element = data.body[index];
        console.log("Found text " + element["text"] + " at coordinates " + element["left"] + ", " + element["top"]);
    }

});

import os
import requests # pip install requests

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

# Base URL for PDF.co Web API requests
BASE_URL = "https://api.pdf.co/v1"

# Source PDF file
SourceFile = ".\\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 = ""

# Search string.
SearchString = "\d{1,}\.\d\d" # Regular expression to find numbers like '100.00'
                              # Note: do not use `+` char in regex, but use `{1,}` instead.
                              # `+` char is valid for URL and will not be escaped, and it will become a space char on the server side.

# Enable regular expressions (Regex)
RegexSearch = True


def main(args = None):
    uploadedFileUrl = uploadFile(SourceFile)
    if (uploadedFileUrl != None):
        searchTextInPDF(uploadedFileUrl)


def searchTextInPDF(uploadedFileUrl):
    """Search Text using PDF.co Web API"""

    # Prepare requests params as JSON
    # See documentation: https://developer.pdf.co
    parameters = {}
    parameters["password"] = Password
    parameters["pages"] = Pages
    parameters["url"] = uploadedFileUrl
    parameters["searchString"] = SearchString
    parameters["regexSearch"] = RegexSearch

    # Prepare URL for 'PDF Text Search' API request
    url = "{}/pdf/find".format(BASE_URL)

    # Execute request and get response as JSON
    response = requests.post(url, data=parameters, headers={ "x-api-key": API_KEY })
    if (response.status_code == 200):
        json = response.json()

        if json["error"] == False:
            # Display found information
            for item in json["body"]:
                print(f"Found text {item['text']} at coordinates {item['left']}, {item['top']}")
        else:
            # Show service reported error
            print(json["message"])
    else:
        print(f"Request error: {response.status_code} {response.reason}")


def uploadFile(fileName):
    """Uploads file to the cloud"""

    # 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.

    # Prepare URL for 'Get Presigned URL' API request
    url = "{}/file/upload/get-presigned-url?contenttype=application/octet-stream&name={}".format(
        BASE_URL, os.path.basename(fileName))

    # Execute request and get response as JSON
    response = requests.get(url, headers={ "x-api-key": API_KEY })
    if (response.status_code == 200):
        json = response.json()

        if json["error"] == False:
            # URL to use for file upload
            uploadUrl = json["presignedUrl"]
            # URL for future reference
            uploadedFileUrl = json["url"]

            # 2. UPLOAD FILE TO CLOUD.
            with open(fileName, 'rb') as file:
                requests.put(uploadUrl, data=file, headers={ "x-api-key": API_KEY, "content-type": "application/octet-stream" })

            return uploadedFileUrl
        else:
            # Show service reported error
            print(json["message"])
    else:
        print(f"Request error: {response.status_code} {response.reason}")

    return None


if __name__ == '__main__':
    main()

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

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

        // Source PDF file
        const string SourceFile = @".\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 = "";

        // Search string.
        const string SearchString = @"\d{1,}\.\d\d"; // Regular expression to find numbers like '100.00'
                                                     // Note: do not use `+` char in regex, but use `{1,}` instead.
                                                     // `+` char is valid for URL and will not be escaped, and it will become a space char on the server side.

        // Enable regular expressions (Regex)
        const bool RegexSearch = true;


        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);

            // 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
            // * If you already have a direct file URL, skip to the step 3.

            // Prepare URL for `Get Presigned URL` API call
            string query = Uri.EscapeUriString(string.Format(
                "https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
                Path.GetFileName(SourceFile)));

            try
            {
                // Execute request
                string response = webClient.DownloadString(query);

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

                if (json["error"].ToObject<bool>() == false)
                {
                    // Get URL to use for the file upload
                    string uploadUrl = json["presignedUrl"].ToString();
                    string uploadedFileUrl = json["url"].ToString();

                    // 2. UPLOAD THE FILE TO CLOUD.
                    webClient.Headers.Add("content-type", "application/octet-stream");
                    webClient.UploadFile(uploadUrl, "PUT", SourceFile); // You can use UploadData() instead if your file is byte[] or Stream

                    // 3. MAKE UPLOADED PDF FILE SEARCHABLE

                    // URL for `PDF Text Search` API call
                    // See documentation: https://developer.pdf.co
                    string url = "https://api.pdf.co/v1/pdf/find";

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

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

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

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

                    if (json["error"].ToObject<bool>() == false)
                    {
                        foreach (JToken item in json["body"])
                        {
                            Console.WriteLine($"Found text \"{item["text"]}\" at coordinates {item["left"]}, {item["top"]}");
                        }
                    }
                    else
                    {
                        Console.WriteLine(json["message"].ToString());
                    }
                }
                else
                {
                    Console.WriteLine(json["message"].ToString());
                }
            }
            catch (WebException ex)
            {
                Console.WriteLine(ex.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.
    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 = "";

    // Search string.
  final static String SearchString = "\\d{1,}\\.\\d\\d"; // Regular expression to find numbers like '100.00'
    // Note: do not use `+` char in regex, but use `{1,}` instead.
    // `+` char is valid for URL and will not be escaped, and it will become a space char on the server side.

    // Enable regular expressions (Regex)
    final static boolean RegexSearch = true;

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

        // Prepare URL for PDF text search API call.
        // See documentation: https://developer.pdf.co
        String query = "https://api.pdf.co/v1/pdf/find";

        // 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\", \"searchString\": \"%s\", \"regexSearch\": \"%s\"}",
                Password,
                Pages,
                SourceFileURL,
                SearchString,
                RegexSearch);

        // 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)
            {
                // Display found items in console
                for (JsonElement element : json.get("body").getAsJsonArray())
                {
                    JsonObject item = (JsonObject) element;
                    System.out.println("Found text " + item.get("text") + " at coordinates " + item.get("left") + ", "+ item.get("top"));
                }
            }
            else
            {
                // Display service reported error
                System.out.println(json.get("message").getAsString());
            }
        }
        else
        {
            // Display request error
            System.out.println(response.code() + " " + response.message());
        }
    }
}