Fork of pdf-parse
npm install @serguun42/pdf-parseFork of pdf-parse
npm install @serguun42/pdf-parse
``js
const fs = require("fs");
const PdfParse = require("@serguun42/pdf-parse");
let dataBuffer = fs.readFileSync("path/to/file.pdf");
PdfParse(dataBuffer).then((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
`js
const fs = require("fs");
const PdfParse = require("@serguun42/pdf-parse");
const dataBuffer = fs.readFileSync("path/to/file.pdf");
PdfParse(dataBuffer)
.then((data) => {
// use data
})
.catch((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/
`jsfalse
// 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 .
disableCombineTextItems: false
};
return pageData.getTextContent(render_options).then((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
};
const dataBuffer = fs.readFileSync("path/to/file.pdf");
PdfParse(dataBuffer, options).then((data) => {
// use new format
});
`
`js
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,
};
``
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.
Removed
MIT licensed and all it's dependencies are MIT or BSD licensed.
This fork is also under MIT license.