pdf.js/examples/node/getinfo.mjs
Jonas Jenwald 59c4041a49 Update the examples/-folder to account for outputting of JavaScript modules (PR 17055 follow-up)
This patch also changes most examples to use "top level await", since that's now supported and slightly simplifies the code.
2023-10-28 10:26:25 +02:00

77 lines
2.4 KiB
JavaScript

/* Any copyright is dedicated to the Public Domain.
* http://creativecommons.org/publicdomain/zero/1.0/ */
//
// Basic node example that prints document metadata and text content.
//
// Run `gulp dist-install` to generate 'pdfjs-dist' npm package files.
import { getDocument } from "pdfjs-dist/legacy/build/pdf.mjs";
// Loading file from file system into typed array
const pdfPath =
process.argv[2] || "../../web/compressed.tracemonkey-pldi-09.pdf";
// Will be using promises to load document, pages and misc data instead of
// callback.
const loadingTask = getDocument(pdfPath);
loadingTask.promise
.then(function (doc) {
const numPages = doc.numPages;
console.log("# Document Loaded");
console.log("Number of Pages: " + numPages);
console.log();
let lastPromise; // will be used to chain promises
lastPromise = doc.getMetadata().then(function (data) {
console.log("# Metadata Is Loaded");
console.log("## Info");
console.log(JSON.stringify(data.info, null, 2));
console.log();
if (data.metadata) {
console.log("## Metadata");
console.log(JSON.stringify(data.metadata.getAll(), null, 2));
console.log();
}
});
const loadPage = function (pageNum) {
return doc.getPage(pageNum).then(function (page) {
console.log("# Page " + pageNum);
const viewport = page.getViewport({ scale: 1.0 });
console.log("Size: " + viewport.width + "x" + viewport.height);
console.log();
return page
.getTextContent()
.then(function (content) {
// Content contains lots of information about the text layout and
// styles, but we need only strings at the moment
const strings = content.items.map(function (item) {
return item.str;
});
console.log("## Text Content");
console.log(strings.join(" "));
// Release page resources.
page.cleanup();
})
.then(function () {
console.log();
});
});
};
// Loading of the first page will wait on metadata and subsequent loadings
// will wait on the previous pages.
for (let i = 1; i <= numPages; i++) {
lastPromise = lastPromise.then(loadPage.bind(null, i));
}
return lastPromise;
})
.then(
function () {
console.log("# End of Document");
},
function (err) {
console.error("Error: " + err);
}
);