> For the complete documentation index, see [llms.txt](https://docs.apryse.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.apryse.com/web/get-started/samples/textextracttest.md).
# Text Extraction
Sample JavaScript code for using WebViewer, Apryse Web SDK to read a PDF (parse and extract text).
Sample JavaScript code for using Apryse SDK to read a PDF (parse and extract text). If you'd like to search text on PDF pages, see our code sample for [text search](/web/get-started/samples/textsearchtest.md). Learn more about our full [PDF Data Extraction SDK Capabilities](https://apryse.com/capabilities/extraction).
To start your free trial, [get stated with WebViewer](/web/get-started/readme.md).
This sample works with [Full-API for WebViewer](/web/full-api/full-api-overview.md).
//---------------------------------------------------------------------------------------
// Copyright (c) 2001-2023 by Apryse Software Inc. All Rights Reserved.
// Consult legal.txt regarding legal and license information.
//---------------------------------------------------------------------------------------
(exports => {
const PDFNet = exports.Core.PDFNet;
exports.runTextExtractTest = async () => {
// A utility method used to dump all text content in the console window.
const dumpAllText = async reader => {
let element;
let bbox;
let arr;
while ((element = await reader.next()) !== null) {
switch (await element.getType()) {
case PDFNet.Element.Type.e_text_begin:
console.log('--> Text Block Begin');
break;
case PDFNet.Element.Type.e_text_end:
console.log('--> Text Block End');
break;
case PDFNet.Element.Type.e_text:
bbox = await element.getBBox();
console.log('--> BBox: ' + bbox.x1 + ', ' + bbox.y1 + ', ' + bbox.x2 + ', ' + bbox.y2 + '\n');
arr = await element.getTextString();
console.log(arr);
break;
case PDFNet.Element.Type.e_text_new_line:
break;
case PDFNet.Element.Type.e_form:
reader.formBegin();
await dumpAllText(reader);
reader.end();
break;
}
}
};
// helper method for ReadTextFromRect
const rectTextSearch = async (reader, pos, srchStr) => {
let element;
let arr;
while ((element = await reader.next()) !== null) {
let bbox;
switch (await element.getType()) {
case PDFNet.Element.Type.e_text:
bbox = await element.getBBox();
if (await bbox.intersectRect(bbox, pos)) {
arr = await element.getTextString();
srchStr += arr + '\n';
}
break;
case PDFNet.Element.Type.e_text_new_line:
break;
case PDFNet.Element.Type.e_form:
reader.formBegin();
srchStr += await rectTextSearch(reader, pos, srchStr); // possibly need srchStr = ...
reader.end();
break;
}
}
return srchStr;
};
const readTextFromRect = async (page, pos, reader) => {
let srchStr = '';
reader.beginOnPage(page); // uses default parameters.
srchStr += await rectTextSearch(reader, pos, srchStr);
reader.end();
return srchStr;
};
const printStyle = async s => {
const rgb = await s.getColor();
const rColorVal = await rgb.get(0);
const gColorVal = await rgb.get(1);
const bColorVal = await rgb.get(2);
const fontName = await s.getFontName();
const fontSize = await s.getFontSize();
const serifOutput = (await s.isSerif()) ? ' sans-serif; ' : ' ';
const returnString =
'style="font-family:' + fontName + ';font-size:' + fontSize + ';' + serifOutput + 'color: #' + rColorVal.toString(16) + ', ' + gColorVal.toString(16) + ', ' + bColorVal.toString(16) + ')"';
return returnString;
};
const main = async () => {
console.log('Beginning Test');
// Relative path to the folder containing test files.
const inputURL = '../TestFiles/';
const inputFilename = 'newsletter.pdf'; // addimage.pdf, newsletter.pdf
const example1Basic = false;
const example2XML = false;
const example3Wordlist = false;
const example4Advanced = true;
const example5LowLevel = false;
let doc = null;
try {
await PDFNet.startDeallocateStack();
doc = await PDFNet.PDFDoc.createFromURL(inputURL + inputFilename);
doc.initSecurityHandler();
doc.lock();
const page = await doc.getPage(1);
if (page.id === '0') {
console.log('Page not found.');
return 1;
}
const txt = await PDFNet.TextExtractor.create();
const rect = new PDFNet.Rect(0, 0, 612, 794);
txt.begin(page, rect);
let text;
let line;
let word;
if (example1Basic) {
const wordCount = await txt.getWordCount();
console.log('Word Count: ' + wordCount);
text = await txt.getAsText();
console.log('- GetAsText -------------------------------');
console.log(text);
console.log('-----------------------------------------');
}
if (example2XML) {
text = await txt.getAsXML(
PDFNet.TextExtractor.XMLOutputFlags.e_words_as_elements | PDFNet.TextExtractor.XMLOutputFlags.e_output_bbox | PDFNet.TextExtractor.XMLOutputFlags.e_output_style_info
);
console.log('- GetAsXML --------------------------' + text);
console.log('-----------------------------------------------------------');
}
if (example3Wordlist) {
line = await txt.getFirstLine();
for (; await line.isValid(); line = await line.getNextLine()) {
for (word = await line.getFirstWord(); await word.isValid(); word = await word.getNextWord()) {
text = await word.getString();
console.log(text);
}
}
console.log('-----------------------------------------------------------');
}
if (example4Advanced) {
let b;
let q;
let curFlowID = -1;
let curParaID = -1;
for (line = await txt.getFirstLine(); await line.isValid(); line = await line.getNextLine()) {
if ((await line.getNumWords()) === 0) {
continue;
}
if ((await line.getFlowID()) !== curFlowID) {
if (curFlowID !== -1) {
if (curParaID !== -1) {
curParaID = -1;
console.log('</Para>');
}
console.log('</Flow>');
}
curFlowID = await line.getFlowID();
console.log('<Flow id="' + curFlowID + '">');
}
if ((await line.getParagraphID()) !== curParaID) {
if (curParaID !== -1) {
console.log('</Para>');
}
curParaID = await line.getParagraphID();
console.log('<Para id="' + curParaID + '">');
}
b = await line.getBBox();
const lineStyle = await line.getStyle();
let outputStringLineBox = '<Line box="' + b.x1 + ', ' + b.y1 + ', ' + b.x2 + ', ' + b.y1 + '">';
outputStringLineBox += await printStyle(lineStyle);
const currentLineNum = await line.getCurrentNum();
outputStringLineBox += ' cur_num="' + currentLineNum + '">';
console.log(outputStringLineBox);
// For each word in the line...
let outputStringWord = '';
for (word = await line.getFirstWord(); await word.isValid(); word = await word.getNextWord()) {
// output bounding box for the word
q = await word.getBBox();
const currentNum = await word.getCurrentNum();
outputStringWord += '<Word box="' + q.x1 + ', ' + q.y1 + ', ' + q.x2 + ', ' + q.y2 + '" cur_num="' + currentNum + '"';
const sz = await word.getStringLen();
if (sz === 0) {
continue;
}
// if the word style is different from the parent style, output the new style
const sty = await word.getStyle();
if (!(await sty.compare(lineStyle))) {
console.log(await printStyle(sty));
}
outputStringWord += '>' + (await word.getString()) + '</Word>';
console.log(outputStringWord);
}
console.log('</Line>');
}
if (curFlowID !== -1) {
if (curParaID !== -1) {
curParaID = -1;
console.log('</Para>');
}
console.log('</Flow>\n');
}
}
console.log('done');
await PDFNet.endDeallocateStack();
} catch (err) {
console.log(err);
console.log(err.stack);
}
if (example5LowLevel) {
try {
await PDFNet.startDeallocateStack();
doc = await PDFNet.PDFDoc.createFromURL(inputURL + inputFilename);
doc.initSecurityHandler();
doc.lock();
// Example 1. Extract all text content from the document
const reader = await PDFNet.ElementReader.create();
const itr = await doc.getPageIterator(1);
// Read every page
for (itr; await itr.hasNext(); itr.next()) {
const page = await itr.current();
reader.beginOnPage(page);
await dumpAllText(reader);
reader.end();
}
// Example 2. Extract text content based on the
// selection rectangle.
console.log('----------------------------------------------------');
console.log('Extract text based on the selection rectangle.');
console.log('----------------------------------------------------');
const firstPage = await (await doc.getPageIterator()).current();
let s1 = await readTextFromRect(firstPage, await PDFNet.Rect.init(27, 392, 563, 534), reader);
console.log('Field 1: ' + s1);
s1 = await readTextFromRect(firstPage, await PDFNet.Rect.init(28, 551, 106, 623), reader);
console.log('Field 2: ' + s1);
s1 = await readTextFromRect(firstPage, await PDFNet.Rect.init(208, 550, 387, 621), reader);
console.log('Field 3: ' + s1);
// ...
console.log('Done');
await PDFNet.endDeallocateStack();
} catch (err) {
console.log(err.stack);
}
}
};
// add your own license key as the second parameter, e.g. PDFNet.runWithCleanup(main, 'visitor.claims.wvKey || "YOUR_LICENSE_KEY"')
PDFNet.runWithCleanup(main);
};
})(window);
// eslint-disable-next-line spaced-comment
//# sourceURL=TextExtractTest.js
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.apryse.com/web/get-started/samples/textextracttest.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.