Convert PDF To HTML From URL (Node.js) - AWS Lambda
PDF to HTML sample in AWS Lambda demonstrating ‘Convert PDF To HTML From URL (Node.js)’
app.js
var https = require("https");
// 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-html/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 = "";
// Set to `true` to get simplified HTML without CSS. Default is the rich HTML keeping the document design.
const PlainHtml = false;
// Set to `true` if your document has the column layout like a newspaper.
const ColumnLayout = false;
// Prepare request to `PDF To HTML` API endpoint
var queryPath = `/v1/pdf/convert/to/html?name=result.html&password=${Password}&pages=${Pages}` +
`&simple=${PlainHtml}&columns=${ColumnLayout}&url=${SourceFileUrl}`;
// JSON payload for api request
var jsonPayload = JSON.stringify({
name: path.basename(DestinationFile), password: Password, pages: Pages, simple: PlainHtml, columns: ColumnLayout, url: SourceFileUrl
});
var reqOptions = {
host: "api.pdf.co",
method: "POST",
path: queryPath,
headers: {
"x-api-key": API_KEY,
"Content-Type": "application/json",
"Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
}
};
exports.handler = async (event) => {
let dataString = '';
const promise_response = await new Promise((resolve, reject) => {
// Send request
var postRequest = https.request(reqOptions, (response) => {
response.on('data', chunk => {
dataString += chunk;
});
response.on('end', () => {
resolve({
statusCode: 200,
body: JSON.stringify(JSON.parse(dataString), null, 4)
});
});
}).on("error", (e) => {
reject({
statusCode: 500,
body: 'Something went wrong!'
});
});
// Write request data
postRequest.write(jsonPayload);
postRequest.end();
});
return promise_response;
};
PDF.co Web API: the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.
Download Source Code (.zip)
return to the previous page explore PDF to HTML endpoint
Copyright © 2016 - 2024 PDF.co