Sample request
CURL
curl --request POST \
--url 'https://api.pdf.co/v1/pdf/convert/to/csv' \
--header 'Content-Type: application/json' \
--header 'x-api-key: YOUR_API_KEY' \
--data '{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"
}'
const response = await fetch("https://api.pdf.co/v1/pdf/convert/to/csv", {
method: "POST",
headers: {
"Content-Type": "application/json",
"x-api-key": "YOUR_API_KEY",
},
body: JSON.stringify({
url: "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf",
}),
});
const result = await response.json();
console.log(result);
import requests
response = requests.post(
"https://api.pdf.co/v1/pdf/convert/to/csv",
headers={"x-api-key": "YOUR_API_KEY"},
json={"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"},
)
print(response.json())
using System;
using System.Net.Http;
using System.Text;
using System.Text.Json;
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("x-api-key", "YOUR_API_KEY");
var payload = JsonSerializer.Serialize(new {
url = "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"
});
using var response = await client.PostAsync(
"https://api.pdf.co/v1/pdf/convert/to/csv",
new StringContent(payload, Encoding.UTF8, "application/json")
);
Console.WriteLine(await response.Content.ReadAsStringAsync());
OkHttpClient client = new OkHttpClient();
String payload = "{\"url\":\"https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf\"}";
Request request = new Request.Builder()
.url("https://api.pdf.co/v1/pdf/convert/to/csv")
.addHeader("x-api-key", "YOUR_API_KEY")
.post(RequestBody.create(MediaType.parse("application/json"), payload))
.build();
try (Response response = client.newCall(request).execute()) {
System.out.println(response.body().string());
}
<?php
$curl = curl_init("https://api.pdf.co/v1/pdf/convert/to/csv");
curl_setopt_array($curl, [
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: YOUR_API_KEY",
],
CURLOPT_POST => true,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POSTFIELDS => json_encode([
"url" => "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf",
]),
]);
echo curl_exec($curl);
curl_close($curl);
?>
{
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.csv",
"credits": 28,
"remainingCredits": 616411,
"duration": 1250,
"url": "https://pdf-temp-files.s3.amazonaws.com/example/sample.csv",
"outputLinkValidTill": "2026-11-04T12:00:00+00:00"
}
{
"error": true,
"status": 400,
"message": "Invalid input url. Please set url to the link accessible without authentication or upload a file to API and use as a input link for other APIs.",
"credits": 0,
"remainingCredits": 616467,
"errorCode": 400
}
{
"status": "error",
"errorCode": 401,
"error": true,
"message": "Please provide your API key as \"x-api-key\" header parameter for GET or POST request or as username (\"curl -u <apikey>\") or as url parameter (not recommended). Get your API key at https://app.pdf.co/account"
}
{
"status": "error",
"errorCode": 402,
"error": true,
"message": "Not enough credits, subscription expired or metered use is not allowed. Please review credits on your account at https://app.pdf.co/subscriptions"
}
{
"status": "error",
"errorCode": 403,
"error": true,
"message": "This API endpoint is not available on your subscription plan."
}
{
"errorCode": 408,
"error": true,
"message": "Timeout error. Input was too large to process in 35 secs, the connection was bad or input file was not available. For links to G Drive, G Docs, Dropbox or similar: they can limit access. To solve put 'cache:' before the link and try again. Also there is PDF.co built-in file storage at https://app.pdf.co/files stable and fast. If you use API directly then try 'async' mode (set 'async' to 'true') so it will create background job. Check the job status with '/job/check?jobId=<jobId>'. For pdf with lot of pages try to specify a page range using 'pages' param (get page count with '/pdf/info' endpoint). If you use Zapier then turn on 'Autoreply' to autoretry.",
"remainingCredits": 616467,
"credits": 0
}
{
"error": true,
"message": "Too many requests. Your current limit is 60 requests per minute. Please try again later"
}
CURL
curl --request POST \
--url 'https://api.pdf.co/v1/pdf/convert/to/csv' \
--header 'Content-Type: application/json' \
--header 'x-api-key: YOUR_API_KEY' \
--data '{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"
}'
const response = await fetch("https://api.pdf.co/v1/pdf/convert/to/csv", {
method: "POST",
headers: {
"Content-Type": "application/json",
"x-api-key": "YOUR_API_KEY",
},
body: JSON.stringify({
url: "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf",
}),
});
const result = await response.json();
console.log(result);
import requests
response = requests.post(
"https://api.pdf.co/v1/pdf/convert/to/csv",
headers={"x-api-key": "YOUR_API_KEY"},
json={"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"},
)
print(response.json())
using System;
using System.Net.Http;
using System.Text;
using System.Text.Json;
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("x-api-key", "YOUR_API_KEY");
var payload = JsonSerializer.Serialize(new {
url = "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"
});
using var response = await client.PostAsync(
"https://api.pdf.co/v1/pdf/convert/to/csv",
new StringContent(payload, Encoding.UTF8, "application/json")
);
Console.WriteLine(await response.Content.ReadAsStringAsync());
OkHttpClient client = new OkHttpClient();
String payload = "{\"url\":\"https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf\"}";
Request request = new Request.Builder()
.url("https://api.pdf.co/v1/pdf/convert/to/csv")
.addHeader("x-api-key", "YOUR_API_KEY")
.post(RequestBody.create(MediaType.parse("application/json"), payload))
.build();
try (Response response = client.newCall(request).execute()) {
System.out.println(response.body().string());
}
<?php
$curl = curl_init("https://api.pdf.co/v1/pdf/convert/to/csv");
curl_setopt_array($curl, [
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: YOUR_API_KEY",
],
CURLOPT_POST => true,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POSTFIELDS => json_encode([
"url" => "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf",
]),
]);
echo curl_exec($curl);
curl_close($curl);
?>
{
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.csv",
"credits": 28,
"remainingCredits": 616411,
"duration": 1250,
"url": "https://pdf-temp-files.s3.amazonaws.com/example/sample.csv",
"outputLinkValidTill": "2026-11-04T12:00:00+00:00"
}
{
"error": true,
"status": 400,
"message": "Invalid input url. Please set url to the link accessible without authentication or upload a file to API and use as a input link for other APIs.",
"credits": 0,
"remainingCredits": 616467,
"errorCode": 400
}
{
"status": "error",
"errorCode": 401,
"error": true,
"message": "Please provide your API key as \"x-api-key\" header parameter for GET or POST request or as username (\"curl -u <apikey>\") or as url parameter (not recommended). Get your API key at https://app.pdf.co/account"
}
{
"status": "error",
"errorCode": 402,
"error": true,
"message": "Not enough credits, subscription expired or metered use is not allowed. Please review credits on your account at https://app.pdf.co/subscriptions"
}
{
"status": "error",
"errorCode": 403,
"error": true,
"message": "This API endpoint is not available on your subscription plan."
}
{
"errorCode": 408,
"error": true,
"message": "Timeout error. Input was too large to process in 35 secs, the connection was bad or input file was not available. For links to G Drive, G Docs, Dropbox or similar: they can limit access. To solve put 'cache:' before the link and try again. Also there is PDF.co built-in file storage at https://app.pdf.co/files stable and fast. If you use API directly then try 'async' mode (set 'async' to 'true') so it will create background job. Check the job status with '/job/check?jobId=<jobId>'. For pdf with lot of pages try to specify a page range using 'pages' param (get page count with '/pdf/info' endpoint). If you use Zapier then turn on 'Autoreply' to autoretry.",
"remainingCredits": 616467,
"credits": 0
}
{
"error": true,
"message": "Too many requests. Your current limit is 60 requests per minute. Please try again later"
}
PDF Conversion
PDF to CSV
Convert PDF and scanned images into CSV representation with layout, columns, rows, and tables.
Sample request
CURL
curl --request POST \
--url 'https://api.pdf.co/v1/pdf/convert/to/csv' \
--header 'Content-Type: application/json' \
--header 'x-api-key: YOUR_API_KEY' \
--data '{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"
}'
const response = await fetch("https://api.pdf.co/v1/pdf/convert/to/csv", {
method: "POST",
headers: {
"Content-Type": "application/json",
"x-api-key": "YOUR_API_KEY",
},
body: JSON.stringify({
url: "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf",
}),
});
const result = await response.json();
console.log(result);
import requests
response = requests.post(
"https://api.pdf.co/v1/pdf/convert/to/csv",
headers={"x-api-key": "YOUR_API_KEY"},
json={"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"},
)
print(response.json())
using System;
using System.Net.Http;
using System.Text;
using System.Text.Json;
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("x-api-key", "YOUR_API_KEY");
var payload = JsonSerializer.Serialize(new {
url = "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"
});
using var response = await client.PostAsync(
"https://api.pdf.co/v1/pdf/convert/to/csv",
new StringContent(payload, Encoding.UTF8, "application/json")
);
Console.WriteLine(await response.Content.ReadAsStringAsync());
OkHttpClient client = new OkHttpClient();
String payload = "{\"url\":\"https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf\"}";
Request request = new Request.Builder()
.url("https://api.pdf.co/v1/pdf/convert/to/csv")
.addHeader("x-api-key", "YOUR_API_KEY")
.post(RequestBody.create(MediaType.parse("application/json"), payload))
.build();
try (Response response = client.newCall(request).execute()) {
System.out.println(response.body().string());
}
<?php
$curl = curl_init("https://api.pdf.co/v1/pdf/convert/to/csv");
curl_setopt_array($curl, [
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: YOUR_API_KEY",
],
CURLOPT_POST => true,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POSTFIELDS => json_encode([
"url" => "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf",
]),
]);
echo curl_exec($curl);
curl_close($curl);
?>
{
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.csv",
"credits": 28,
"remainingCredits": 616411,
"duration": 1250,
"url": "https://pdf-temp-files.s3.amazonaws.com/example/sample.csv",
"outputLinkValidTill": "2026-11-04T12:00:00+00:00"
}
{
"error": true,
"status": 400,
"message": "Invalid input url. Please set url to the link accessible without authentication or upload a file to API and use as a input link for other APIs.",
"credits": 0,
"remainingCredits": 616467,
"errorCode": 400
}
{
"status": "error",
"errorCode": 401,
"error": true,
"message": "Please provide your API key as \"x-api-key\" header parameter for GET or POST request or as username (\"curl -u <apikey>\") or as url parameter (not recommended). Get your API key at https://app.pdf.co/account"
}
{
"status": "error",
"errorCode": 402,
"error": true,
"message": "Not enough credits, subscription expired or metered use is not allowed. Please review credits on your account at https://app.pdf.co/subscriptions"
}
{
"status": "error",
"errorCode": 403,
"error": true,
"message": "This API endpoint is not available on your subscription plan."
}
{
"errorCode": 408,
"error": true,
"message": "Timeout error. Input was too large to process in 35 secs, the connection was bad or input file was not available. For links to G Drive, G Docs, Dropbox or similar: they can limit access. To solve put 'cache:' before the link and try again. Also there is PDF.co built-in file storage at https://app.pdf.co/files stable and fast. If you use API directly then try 'async' mode (set 'async' to 'true') so it will create background job. Check the job status with '/job/check?jobId=<jobId>'. For pdf with lot of pages try to specify a page range using 'pages' param (get page count with '/pdf/info' endpoint). If you use Zapier then turn on 'Autoreply' to autoretry.",
"remainingCredits": 616467,
"credits": 0
}
{
"error": true,
"message": "Too many requests. Your current limit is 60 requests per minute. Please try again later"
}
CURL
curl --request POST \
--url 'https://api.pdf.co/v1/pdf/convert/to/csv' \
--header 'Content-Type: application/json' \
--header 'x-api-key: YOUR_API_KEY' \
--data '{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"
}'
const response = await fetch("https://api.pdf.co/v1/pdf/convert/to/csv", {
method: "POST",
headers: {
"Content-Type": "application/json",
"x-api-key": "YOUR_API_KEY",
},
body: JSON.stringify({
url: "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf",
}),
});
const result = await response.json();
console.log(result);
import requests
response = requests.post(
"https://api.pdf.co/v1/pdf/convert/to/csv",
headers={"x-api-key": "YOUR_API_KEY"},
json={"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"},
)
print(response.json())
using System;
using System.Net.Http;
using System.Text;
using System.Text.Json;
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("x-api-key", "YOUR_API_KEY");
var payload = JsonSerializer.Serialize(new {
url = "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"
});
using var response = await client.PostAsync(
"https://api.pdf.co/v1/pdf/convert/to/csv",
new StringContent(payload, Encoding.UTF8, "application/json")
);
Console.WriteLine(await response.Content.ReadAsStringAsync());
OkHttpClient client = new OkHttpClient();
String payload = "{\"url\":\"https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf\"}";
Request request = new Request.Builder()
.url("https://api.pdf.co/v1/pdf/convert/to/csv")
.addHeader("x-api-key", "YOUR_API_KEY")
.post(RequestBody.create(MediaType.parse("application/json"), payload))
.build();
try (Response response = client.newCall(request).execute()) {
System.out.println(response.body().string());
}
<?php
$curl = curl_init("https://api.pdf.co/v1/pdf/convert/to/csv");
curl_setopt_array($curl, [
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: YOUR_API_KEY",
],
CURLOPT_POST => true,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POSTFIELDS => json_encode([
"url" => "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf",
]),
]);
echo curl_exec($curl);
curl_close($curl);
?>
{
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.csv",
"credits": 28,
"remainingCredits": 616411,
"duration": 1250,
"url": "https://pdf-temp-files.s3.amazonaws.com/example/sample.csv",
"outputLinkValidTill": "2026-11-04T12:00:00+00:00"
}
{
"error": true,
"status": 400,
"message": "Invalid input url. Please set url to the link accessible without authentication or upload a file to API and use as a input link for other APIs.",
"credits": 0,
"remainingCredits": 616467,
"errorCode": 400
}
{
"status": "error",
"errorCode": 401,
"error": true,
"message": "Please provide your API key as \"x-api-key\" header parameter for GET or POST request or as username (\"curl -u <apikey>\") or as url parameter (not recommended). Get your API key at https://app.pdf.co/account"
}
{
"status": "error",
"errorCode": 402,
"error": true,
"message": "Not enough credits, subscription expired or metered use is not allowed. Please review credits on your account at https://app.pdf.co/subscriptions"
}
{
"status": "error",
"errorCode": 403,
"error": true,
"message": "This API endpoint is not available on your subscription plan."
}
{
"errorCode": 408,
"error": true,
"message": "Timeout error. Input was too large to process in 35 secs, the connection was bad or input file was not available. For links to G Drive, G Docs, Dropbox or similar: they can limit access. To solve put 'cache:' before the link and try again. Also there is PDF.co built-in file storage at https://app.pdf.co/files stable and fast. If you use API directly then try 'async' mode (set 'async' to 'true') so it will create background job. Check the job status with '/job/check?jobId=<jobId>'. For pdf with lot of pages try to specify a page range using 'pages' param (get page count with '/pdf/info' endpoint). If you use Zapier then turn on 'Autoreply' to autoretry.",
"remainingCredits": 616467,
"credits": 0
}
{
"error": true,
"message": "Too many requests. Your current limit is 60 requests per minute. Please try again later"
}
Try it live: PDF to CSV → API Tester — send a real request from your browser.
POST /v1/pdf/convert/to/csv
Quick start
A request containing onlyurl is enough to start a conversion.
{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf"
}
To see the request size limits, please refer to the Request Size Limits.
Request body
Attributes are case-sensitive and should be inside JSON for POST request. for example:
{ "url": "https://example.com/file1.pdf" } No query parameters accepted.URL to the source file
url attributeThe callback URL (or Webhook) used to receive the POST data. see Webhooks & Callbacks. This is only applicable when
async is set to true.Specify page indices as comma-separated values or ranges to process (e.g. “0, 1, 2-” or “1, 2, 3-7”). The first-page index is 0. Use ”!” before a number for inverted page numbers (e.g. “!0” for the last page). If not specified, the default configuration processes all pages. The input must be in string format.
Unwrap lines into a single line within table cells in provided PDF documents. This is only applicable when
lineGrouping is set to 1.Defines coordinates for extraction. Use
PDF Edit Add Helperto get or measure PDF coordinates. The format is {x} {y} {width} {height}.Set the language for OCR (text from image) to use for scanned PDF, PNG, and JPG documents input when extracting text. see Language Support. You can also use 2 languages simultaneously like this:
eng+deu (any combination).Set to true to return results inside the response. Otherwise, the endpoint will return a URL to the output file generated.
Controls how lines of text are grouped when extracting data from a PDF. Line grouping within table cells. The available modes are:
1, 2, 3. For more information, see Line Grouping.Show details
Show details
Line Grouping Options
"1": GroupByRows – Each row is checked against the next row to see if they can be grouped together. Rows will only be grouped if all cells in the current row can be grouped with all cells in the next row. Useful when merging related content that spans multiple lines but belongs to the same logical row."2": GroupByColumns – Each cell is checked against the cell below it in the next row to determine if they can be grouped. Cells are grouped within the same column even if others can’t be grouped. Useful for columnar data where content in each column might span multiple lines."3": JoinOrphanedRows – Joins a row with a single cell to the previous row if there is no separator between them. Useful for handling cases with orphaned or misaligned content.
Set
async to true for long processes to run in the background, API will then return a jobId which you can use with the Background Job Check endpoint. Also see Webhooks & CallbacksSet the expiration time for the output link in minutes. After this specified duration, any generated output file(s) will be automatically deleted from PDF.co Temporary Files Storage. The maximum duration for link expiration varies based on your current subscription plan. To store permanent input files (e.g. re-usable images, pdf templates, documents) consider using PDF.co Built-In Files Storage.
See Profiles for more information.Pass
profiles as a string containing serialized JSON, not as a JSON object. The subparameters below are settings inside that string, not separate request-body fields.{
"profiles": "{\"ColumnDetectionMode\":\"ContentGroups\"}"
}
Show Profile subparameters
Show Profile subparameters
You can use profiles to control the convert process and output of the CSV file.
Controls column detection/alignment in PDF table extraction. See Column Detection Mode for more information.
Show details
Show details
Column Detection ModeThis might be case when a document contains a number of overlapping invisible text and vector objects that affect column detection. In this case you may need to fix the wrongly positioned data.Set the options for your column detection via the following
profiles parameters:ColumnDetectionMode - available values:ContentGroupsAndBorders(default, no need to specify)ContentGroupsBordersBorderedTablesContentGroupsAI
{
"profiles": "{\"ColumnDetectionMode\":\"ContentGroups\"}"
}
Specifies how OCR (Optical Character Recognition) should process input content, offering various modes to tailor text extraction based on content type such as images, fonts, and vector graphics. For more information, see OCR Extraction Modes.
Use this parameter to change the OCR resolution from the default 300 dpi. The range is from
72 to 1200 dpi.Use manual rotation to handle PDFs with vertically drawn text. Normally, OCR automatically detects page rotation in PDFs and extracts text accurately. However, in some cases, the PDF might not have an actual rotated page --- Rather, the text itself is drawn vertically. In such scenarios, auto-detection may fail. You can use this parameter to manually set the page rotation. The available angles are:
0, 1, 2, 3.Controls line grouping in PDF text extraction. Modes:
None (no grouping), GroupByRows (merge rows if all cells align), GroupByColumns (merge cells by column), JoinOrphanedRows (merge single-cell rows to above if no separator).Controls whether font colors should be considered when detecting table structure and merging text objects during PDF extraction. Set to true to consider font colors.
Controls how spaces between words are interpreted for column detection in PDF text extraction. It defines the ratio of space width that determines when text should be treated as being in separate columns.
Controls how columns are detected and aligned during table extraction from PDF documents. It affects both table structure detection and text extraction with formatting preservation. Set to true to automatically align columns to the header row. When set to true (default), the row with the most columns is used as the header, and all other rows are aligned to this structure --- ideal for well-structured tables. When set to false, columns are analyzed independently across all rows to build the structure, which works better for inconsistent or irregular tables.
Image preprocessing filters for OCR. Refer to OCRImagePreprocessingFilters for usage examples.Configure this collection using method keys such as
OCRImagePreprocessingFilters.AddGrayscale() inside the serialized profiles string, as shown below.OCRImagePreprocessingFiltersTo set image preprocessing filters, please use:{
"profiles": "{\"ExtractShadowLikeText\":false,\"OCRMode\":\"Auto\",\"OCRImagePreprocessingFilters.AddGrayscale()\":[],\"OCRImagePreprocessingFilters.AddGammaCorrection()\":[1.4]}"
}
The minimum number of characters a page must have to skip OCR. If a page has fewer, OCR will run. For example, if set to 8, OCR is skipped on pages with more than 8 characters.
Controls whether to save vector graphics during PDF to HTML conversion. Set to true to save vector graphics.
Controls how images are saved during PDF to HTML conversion. Modes:
None (no images), OuterFile (save to sub-folder), Embed (embed as Base64 data:URI).Set to true to this parameter makes the converter consider font size differences in document text when detecting and parsing table structures. This can be helpful in cases where tables are formatted using different font sizes to distinguish between headers, data cells, or other structural elements.
Extract text in a specific area by defining the extraction area - set with points in the format [x, y, width, height].
Controls whether to extract invisible text from a PDF document. Set to false to skip over invisible text during extraction. This is particularly useful when dealing with PDFs that contain hidden text layers or when you only want to extract visible content. When this value is set to false, OCRMode must be set to
Auto to properly apply the shadow text filtering effect.Controls the encryption algorithm used for data encryption. See User-Controlled Encryption for more information. The available algorithms are:
AES128, AES192, AES256.Controls the encryption key used for data encryption. See User-Controlled Encryption for more information.
Controls the encryption IV used for data encryption. See User-Controlled Encryption for more information.
Controls the decryption algorithm used for data decryption. See User-Controlled Encryption for more information. The available algorithms are:
AES128, AES192, AES256.Controls the decryption key used for data decryption. See User-Controlled Encryption for more information.
Controls the decryption IV used for data decryption. See User-Controlled Encryption for more information.
Responses
To see the main response codes, please refer to the Response Codes page.
| Parameter | Type | Description |
|---|---|---|
body | string | Stringified CSV content, returned for synchronous requests with inline: true. |
url | string | Temporary CSV output URL for synchronous requests with inline: false (the default). For asynchronous submission, this is a reserved URL; wait for the job to succeed before downloading. |
outputLinkValidTill | string | Timestamp indicating when the output URL expires. Present with URL output. |
jobId | string | Background job ID returned when async: true. |
pageCount | integer | Number of pages processed in the synchronous request. Not included in the asynchronous submission response. |
error | boolean | Indicates whether an error occurred (false means success) |
status | integer or string | Numeric operation status, or "error" for gateway middleware errors with a numeric errorCode. The HTTP 429 response has neither status nor errorCode. In all cases, rely on the HTTP response status. See Response Codes. |
errorCode | integer | Numeric error code in gateway error responses. A conversion-service timeout with status: 445 is returned as HTTP 408 with errorCode: 408. |
message | string | Error details when the request fails. |
name | string | Name of the output file |
credits | integer | Number of credits consumed by the request |
remainingCredits | integer | Number of credits remaining in the account |
duration | integer | Conversion-service request duration in milliseconds, when present. For asynchronous submission, this measures submission handling, not background conversion time. |
Synchronous URL output
Omitinline and async, or set both to false, to return the final CSV URL. The Quick start and primary sample requests use this mode. Omitting async uses its default of false.
Synchronous URL response
{
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.csv",
"credits": 28,
"remainingCredits": 616411,
"duration": 1250,
"url": "https://pdf-temp-files.s3.amazonaws.com/example/sample.csv",
"outputLinkValidTill": "2026-11-04T12:00:00+00:00"
}
Inline CSV output
Setinline: true and async: false to return CSV text in body.
Inline CSV response
{
"body": "\"Your Company Name\",\"\",\"\",\"\",\r\n\"Your Address\",\"\",\"\",\"\",\r\n\"City, State Zip\",\"\",\"\",\"\",\r\n\"\",\"\",\"\",\"Invoice No. 123456\",\r\n\"\",\"\",\"\",\"Invoice Date 01/01/2016\",\r\n\"Client Name\",\"\",\"\",\"\",\r\n\"Address\",\"\",\"\",\"\",\r\n\"City, State Zip\",\"\",\"\",\"\",\r\n\"Notes\",\"\",\"\",\"\",\r\n\"Item\",\"Quantity\",\"Price\",\"Total\",\r\n\"Item 1\",\"1\",\"40.00\",\"40.00\",\r\n\"Item 2\",\"2\",\"30.00\",\"60.00\",\r\n\"Item 3\",\"3\",\"20.00\",\"60.00\",\r\n\"Item 4\",\"4\",\"10.00\",\"40.00\",\r\n\"\",\"\",\"TOTAL\",\"200.00\",\r\n",
"pageCount": 2,
"error": false,
"status": 200,
"name": "result.csv",
"remainingCredits": 616411,
"credits": 56
}
Asynchronous submission
Setasync: true to run conversion in the background. This CSV path returns jobId and a reserved output URL, including when inline: true. Use Background Job Check and download the result only after the job succeeds. The initial response does not include body or pageCount.
Asynchronous request
{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-csv/sample.pdf",
"async": true,
"name": "result.csv"
}
Asynchronous submission response
{
"error": false,
"status": 200,
"name": "result.csv",
"credits": 28,
"remainingCredits": 616439,
"duration": 120,
"url": "https://pdf-temp-files.s3.amazonaws.com/example/result.csv",
"outputLinkValidTill": "2026-11-04T12:00:00+00:00",
"jobId": "EXAMPLE_JOB_ID"
}
Timeout behavior
Synchronous CSV conversion can time out. Useasync: true for long-running requests. The gateway returns HTTP 408 for an upstream request timeout and maps conversion-service timeout code 445 to HTTP 408. A gateway transport timeout has no status field; a conversion-service timeout can retain numeric status: 445 while errorCode is 408. The gateway upstream timeout defaults to 35 seconds and can vary by deployment.
For asynchronous requests, duration measures submission handling. Background Job Check reports the completed job duration separately as jobDuration.
Inconsistent URL Encoding in cURL Output: When using cURL to make API requests, the output JSON may show URL characters encoded as Unicode escape sequences. For example, the ampersand character (
&) may appear as \u0026 in the cURL output. This is normal JSON encoding behavior and does not affect the validity of the URL. The URL will function correctly when used, as JSON parsers automatically decode these escape sequences. If you’re parsing the response programmatically, your JSON parser will handle this conversion automatically.Upload workflow examples
Show upload workflow examples
Show upload workflow examples
These examples upload a local file before converting it to CSV.
- JavaScript/Node.js
- Python
- C#
- Java
- PHP
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 = "*********************************";
// Source PDF file
const SourceFile = "./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 = "";
// Destination CSV file name
const DestinationFile = "./result.csv";
// 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
getPresignedUrl(API_KEY, SourceFile)
.then(([uploadUrl, uploadedFileUrl]) => {
// 2. UPLOAD THE FILE TO CLOUD.
uploadFile(API_KEY, SourceFile, uploadUrl)
.then(() => {
// 3. CONVERT UPLOADED PDF FILE TO CSV
convertPdfToCsv(API_KEY, uploadedFileUrl, Password, Pages, DestinationFile);
})
.catch(e => {
console.log(e);
});
})
.catch(e => {
console.log(e);
});
function getPresignedUrl(apiKey, localFile) {
return new Promise(resolve => {
// Prepare request to `Get Presigned URL` API endpoint
let queryPath = `/v1/file/upload/get-presigned-url?name=${path.basename(SourceFile)}`;
let reqOptions = {
host: "api.pdf.co",
path: encodeURI(queryPath),
headers: { "x-api-key": API_KEY }
};
// Send request
https.get(reqOptions, (response) => {
response.on("data", (d) => {
let data = JSON.parse(d);
if (data.error == false) {
// Return presigned url we received
resolve([data.presignedUrl, data.url]);
}
else {
// Service reported error
console.log("getPresignedUrl(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("getPresignedUrl(): " + e);
});
});
}
function uploadFile(apiKey, localFile, uploadUrl) {
return new Promise(resolve => {
fs.readFile(SourceFile, (err, data) => {
request({
method: "PUT",
url: uploadUrl,
body: data,
}, (err, res, body) => {
if (!err) {
resolve();
}
else {
console.log("uploadFile() request error: " + err);
}
});
});
});
}
function convertPdfToCsv(apiKey, uploadedFileUrl, password, pages, destinationFile) {
// Prepare request to `PDF To CSV` API endpoint
var queryPath = `/v1/pdf/convert/to/csv`;
// JSON payload for api request
var jsonPayload = JSON.stringify({
name: path.basename(destinationFile), password: password, pages: pages, url: uploadedFileUrl, async: true
});
var reqOptions = {
host: "api.pdf.co",
method: "POST",
path: queryPath,
headers: {
"x-api-key": apiKey,
"Content-Type": "application/json",
"Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
}
};
// Send request
var postRequest = https.request(reqOptions, (response) => {
response.on("data", (d) => {
response.setEncoding("utf8");
// Parse JSON response
let data = JSON.parse(d);
console.log(`Job #${data.jobId} has been created!`);
if (data.error == false) {
checkIfJobIsCompleted(data.jobId, data.url, destinationFile);
}
else {
// Service reported error
console.log("convertPdfToCsv(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("convertPdfToCsv(): " + e);
});
// Write request data
postRequest.write(jsonPayload);
postRequest.end();
}
function checkIfJobIsCompleted(jobId, resultFileUrl, destinationFile) {
let queryPath = `/v1/job/check`;
// JSON payload for api request
let jsonPayload = JSON.stringify({
jobid: jobId
});
let reqOptions = {
host: "api.pdf.co",
path: queryPath,
method: "POST",
headers: {
"x-api-key": API_KEY,
"Content-Type": "application/json",
"Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
}
};
// Send request
var postRequest = https.request(reqOptions, (response) => {
response.on("data", (d) => {
response.setEncoding("utf8");
// Parse JSON response
let data = JSON.parse(d);
console.log(`Checking Job #${jobId}, Status: ${data.status}, Time: ${new Date().toLocaleString()}`);
if (data.status == "working") {
// Check again after 3 seconds
setTimeout(function () { checkIfJobIsCompleted(jobId, resultFileUrl, destinationFile); }, 3000);
}
else if (data.status == "success") {
// Download CSV file
var file = fs.createWriteStream(destinationFile);
https.get(resultFileUrl, (response2) => {
response2.pipe(file)
.on("close", () => {
console.log(`Generated CSV file saved as "${destinationFile}" file.`);
});
});
}
else {
console.log(`Operation ended with status: "${data.status}".`);
}
})
});
// Write request data
postRequest.write(jsonPayload);
postRequest.end();
}
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 = ""
# Destination CSV file name
DestinationFile = ".\\result.csv"
def main(args = None):
uploadedFileUrl = uploadFile(SourceFile)
if (uploadedFileUrl != None):
convertPdfToCSV(uploadedFileUrl, DestinationFile)
def convertPdfToCSV(uploadedFileUrl, destinationFile):
"""Converts PDF To CSV using PDF.co Web API"""
# Prepare requests params as JSON
# See documentation: https://developer.pdf.co/
parameters = {}
parameters["name"] = os.path.basename(destinationFile)
parameters["password"] = Password
parameters["pages"] = Pages
parameters["url"] = uploadedFileUrl
# Prepare URL for 'PDF To CSV' API request
url = "{}/pdf/convert/to/csv".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:
# Get URL of result file
resultFileUrl = json["url"]
# Download result file
r = requests.get(resultFileUrl, stream=True)
if (r.status_code == 200):
with open(destinationFile, 'wb') as file:
for chunk in r:
file.write(chunk)
print(f"Result file saved as \"{destinationFile}\" file.")
else:
print(f"Request error: {response.status_code} {response.reason}")
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 = "";
// Destination CSV file name
const string DestinationFile = @".\result.csv";
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["status"].ToString() != "error")
{
// 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
webClient.Headers.Remove("content-type");
// 3. CONVERT UPLOADED PDF FILE TO CSV
// URL for `PDF To CSV` API call
var url = "https://api.pdf.co/v1/pdf/convert/to/csv";
// Prepare requests params as JSON
Dictionary<string, object> parameters = new Dictionary<string, object>();
parameters.Add("name", Path.GetFileName(DestinationFile));
parameters.Add("password", Password);
parameters.Add("pages", Pages);
parameters.Add("url", uploadedFileUrl);
// 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["status"].ToString() != "error")
{
// Get URL of generated CSV file
string resultFileUrl = json["url"].ToString();
// Download CSV file
webClient.DownloadFile(resultFileUrl, DestinationFile);
Console.WriteLine("Generated CSV file saved as \"{0}\" file.", DestinationFile);
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
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.JsonObject;
import com.google.gson.JsonParser;
import okhttp3.*;
import java.io.*;
import java.net.*;
import java.nio.file.Path;
import java.nio.file.Paths;
public class Main
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
final static String API_KEY = "***********************************";
// Source PDF file
final static Path SourceFile = Paths.get(".\\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 = "";
// Destination CSV file name
final static Path DestinationFile = Paths.get(".\\result.csv");
public static void main(String[] args) throws IOException
{
// Create HTTP client instance
OkHttpClient webClient = new OkHttpClient();
// 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 = String.format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=%s",
SourceFile.getFileName());
// Prepare request
Request request = new Request.Builder()
.url(query)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.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();
String status = json.get("status").getAsString();
if (!status.equals("error"))
{
// Get URL to use for the file upload
String uploadUrl = json.get("presignedUrl").getAsString();
// Get URL of uploaded file to use with later API calls
String uploadedFileUrl = json.get("url").getAsString();
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile(webClient, API_KEY, uploadUrl, SourceFile))
{
// 3. CONVERT UPLOADED PDF FILE TO CSV
PdfToCsv(webClient, API_KEY, DestinationFile, Password, Pages, uploadedFileUrl);
}
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static void PdfToCsv(OkHttpClient webClient, String apiKey, Path destinationFile,
String password, String pages, String uploadedFileUrl) throws IOException
{
// Prepare URL for `PDF To CSV` API call
String query = "https://api.pdf.co/v1/pdf/convert/to/csv";
// 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("{\"name\": \"%s\", \"password\": \"%s\", \"pages\": \"%s\", \"url\": \"%s\"}",
destinationFile.getFileName(),
password,
pages,
uploadedFileUrl);
// 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();
String status = json.get("status").getAsString();
if (!status.equals("error"))
{
// Get URL of generated CSV file
String resultFileUrl = json.get("url").getAsString();
// Download CSV file
downloadFile(webClient, resultFileUrl, destinationFile.toFile());
System.out.printf("Generated CSV file saved as \"%s\" file.", destinationFile.toString());
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static boolean uploadFile(OkHttpClient webClient, String apiKey, String url, Path sourceFile) throws IOException
{
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/octet-stream"), sourceFile.toFile());
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", apiKey) // (!) Set API Key
.addHeader("content-type", "application/octet-stream")
.put(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
return (response.code() == 200);
}
public static void downloadFile(OkHttpClient webClient, String url, File destinationFile) throws IOException
{
// Prepare request
Request request = new Request.Builder()
.url(url)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
byte[] fileBytes = response.body().bytes();
// Save downloaded bytes to file
OutputStream output = new FileOutputStream(destinationFile);
output.write(fileBytes);
output.flush();
output.close();
response.close();
}
}
<?php
// Note: For input files larger than 200 KB, we recommend using async mode by setting the "async" parameter to true.
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
$API_KEY = "***********************************";
// 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 = "";
// Destination CSV file name
$DestinationFile = "./result.csv";
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have the direct PDF file link, go to the step 3.
$presignedUrls = getPresignedUrl($API_KEY, $SourceFile);
if ($presignedUrls !== null) {
list($uploadUrl, $uploadedFileUrl) = $presignedUrls;
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile($API_KEY, $SourceFile, $uploadUrl)) {
// 3. CONVERT UPLOADED PDF FILE TO CSV
convertPdfToCsv($API_KEY, $uploadedFileUrl, $Password, $Pages, $DestinationFile);
}
}
function getPresignedUrl($apiKey, $localFile)
{
// Prepare URL for `Get Presigned URL` API call
$url = "https://api.pdf.co/v1/file/upload/get-presigned-url"
. "?contenttype=application/octet-stream"
. "&name=" . urlencode(basename($localFile));
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "getPresignedUrl(): " . $curlError . PHP_EOL;
return null;
}
if ($statusCode != 200) {
// Display request error
echo "getPresignedUrl(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return null;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "getPresignedUrl(): " . $json["message"] . PHP_EOL;
return null;
}
// Return the URL to use for the file upload, and the URL of the uploaded
// file to use with later API calls
return array($json["presignedUrl"], $json["url"]);
}
function uploadFile($apiKey, $localFile, $uploadUrl)
{
$fileHandle = fopen($localFile, "rb");
if ($fileHandle === false) {
echo "uploadFile(): unable to open " . $localFile . PHP_EOL;
return false;
}
// Create request. The presigned URL expects a raw PUT of the file bytes.
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $uploadUrl);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "content-type: application/octet-stream"));
curl_setopt($curl, CURLOPT_PUT, true);
curl_setopt($curl, CURLOPT_INFILE, $fileHandle);
curl_setopt($curl, CURLOPT_INFILESIZE, filesize($localFile));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
fclose($fileHandle);
if ($result === false) {
// Display CURL error
echo "uploadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "uploadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
return true;
}
function convertPdfToCsv($apiKey, $uploadedFileUrl, $password, $pages, $destinationFile)
{
// Prepare URL for `PDF To CSV` API call
$url = "https://api.pdf.co/v1/pdf/convert/to/csv";
// Prepare requests params
$parameters = array();
$parameters["name"] = basename($destinationFile);
$parameters["password"] = $password;
$parameters["pages"] = $pages;
$parameters["url"] = $uploadedFileUrl;
// Create Json payload
$data = json_encode($parameters);
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "Content-Type: application/json"));
curl_setopt($curl, CURLOPT_POST, true);
curl_setopt($curl, CURLOPT_POSTFIELDS, $data);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "convertPdfToCsv(): " . $curlError . PHP_EOL;
return;
}
if ($statusCode != 200) {
// Display request error
echo "convertPdfToCsv(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "convertPdfToCsv(): " . $json["message"] . PHP_EOL;
return;
}
// Get URL of generated CSV file
$resultFileUrl = $json["url"];
// Download CSV file
if (downloadFile($resultFileUrl, $destinationFile)) {
echo "Generated CSV file saved as \"" . $destinationFile . "\" file." . PHP_EOL;
}
}
function downloadFile($url, $destinationFile)
{
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "downloadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "downloadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
// Write the file only after a successful response so failures leave no file behind
if (file_put_contents($destinationFile, $result) === false) {
echo "downloadFile(): unable to create " . $destinationFile . PHP_EOL;
return false;
}
return true;
}
?>
Was this page helpful?