Pure javascript cross-platform module to extract texts from PDFs.
2024 refresh library of pdf-parse
- pdf2json buggy, no support anymore, memory leak, throws non-catchable fatal errors
- j-pdfjson fork of pdf2json
- pdf-parser buggy, no tests
- pdfreader using pdf2json
- pdf-extract not cross-platform using xpdf
npm install pdf-parse-new
const fs = require('fs');
const pdf = require('pdf-parse-new');
let dataBuffer = fs.readFileSync('path to PDF file...');
pdf(dataBuffer).then(function(data) {
// number of pages
console.log(data.numpages);
// number of rendered pages
console.log(data.numrender);
// PDF info
console.log(data.info);
// PDF metadata
console.log(data.metadata);
// PDF.js version
// check https://mozilla.github.io/pdf.js/getting_started/
console.log(data.version);
// PDF text
console.log(data.text);
});
You can use crawler-request which uses the pdf-parse
const fs = require('fs');
const pdf = require('pdf-parse-new');
let dataBuffer = fs.readFileSync('path to PDF file...');
pdf(dataBuffer).then(function(data) {
// use data
})
.catch(function(error){
// handle exceptions
})
- v1.0.9 and above break pagerender callback changelog
- If you need another format like json, you can change page render behaviour with a callback
- Check out https://mozilla.github.io/pdf.js/
// default render callback
function render_page(pageData) {
// check documents https://mozilla.github.io/pdf.js/
let render_options = {
// replaces all occurrences of whitespace with standard spaces (0x20). The default value is `false`.
normalizeWhitespace: false,
// do not attempt to combine same line TextItem's. The default value is `false`.
disableCombineTextItems: false,
}
return pageData.getTextContent(render_options)
.then(function(textContent) {
let lastY, text = '';
for (let item of textContent.items) {
if (lastY == item.transform[5] || !lastY){
text += item.str;
}
else{
text += '\n' + item.str;
}
lastY = item.transform[5];
}
return text;
});
}
let options = {
pagerender: render_page
}
let dataBuffer = fs.readFileSync('path to PDF file...');
pdf(dataBuffer,options).then(function(data) {
//use new format
});
const DEFAULT_OPTIONS = {
// internal page parser callback
// you can set this option, if you need another format except raw text
pagerender: render_page,
// max page number to parse
max: 0,
// pdf.js verbosity Level
verbosityLevel: 0, // errors: 0, warnings: 1, infos: 5
}
If you need another format except raw text.
Max number of page to parse. If the value is less than or equal to 0, parser renders all pages.
pdf.js version is v4.5.136 mozilla.github.io/pdf.js
-
mocha
ornpm test
- Check test folder and quickstart.js for extra usages.
If you find a bug or a mistake, you can help by submitting an issue Here
GitLab calls it merge request instead of pull request.
MIT licensed and all it's dependencies are MIT or BSD licensed.