我想知道是否可以仅使用 Javascript 来获取 PDF 文件中的文本？ 如果是的话，有人可以告诉我怎么做吗？
我知道有一些服务器端 java、c# 等库，但我不想使用服务器。 谢谢
由于pdf.js多年来一直在发展，我想给出一个新的答案。也就是说，它可以在本地完成，而不涉及任何服务器或外部服务。新的 pdf.js 有一个函数：page.getTextContent()。您可以从中获取文本内容。我已经使用以下代码成功完成了。
.then( function(){...})PDFJS.getDocument( data ).then( function(pdf) {pdf.getPage(i).then( function(page){page.getTextContent().then( function(textContent){最终得到的是一个字符串数组
textContent.bidiTexts[]输入参数
dataFileReader注意： 根据其他一些用户的说法，该库已更新并导致代码损坏。根据下面async5的评论，您需要将
textContent.bidiTextstextContent.items function Pdf2TextClass(){
var self = this;
this.complete = 0;
/**
*
* @param data ArrayBuffer of the pdf file content
* @param callbackPageDone To inform the progress each time
* when a page is finished. The callback function's input parameters are:
* 1) number of pages done;
* 2) total number of pages in file.
* @param callbackAllDone The input parameter of callback function is
* the result of extracted text from pdf file.
*
*/
this.pdfToText = function(data, callbackPageDone, callbackAllDone){
console.assert( data instanceof ArrayBuffer || typeof data == 'string' );
PDFJS.getDocument( data ).then( function(pdf) {
var div = document.getElementById('viewer');
var total = pdf.numPages;
callbackPageDone( 0, total );
var layers = {};
for (i = 1; i <= total; i++){
pdf.getPage(i).then( function(page){
var n = page.pageNumber;
page.getTextContent().then( function(textContent){
if( null != textContent.bidiTexts ){
var page_text = "";
var last_block = null;
for( var k = 0; k < textContent.bidiTexts.length; k++ ){
var block = textContent.bidiTexts[k];
if( last_block != null && last_block.str[last_block.str.length-1] != ' '){
if( block.x < last_block.x )
page_text += "\r\n";
else if ( last_block.y != block.y && ( last_block.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null ))
page_text += ' ';
}
page_text += block.str;
last_block = block;
}
textContent != null && console.log("page " + n + " finished."); //" content: \n" + page_text);
layers[n] = page_text + "\n\n";
}
++ self.complete;
callbackPageDone( self.complete, total );
if (self.complete == total){
window.setTimeout(function(){
var full_text = "";
var num_pages = Object.keys(layers).length;
for( var j = 1; j <= num_pages; j++)
full_text += layers[j] ;
callbackAllDone(full_text);
}, 1000);
}
}); // end of page.getTextContent().then
}); // end of page.then
} // of for
});
}; // end of pdfToText()
}; // end of class
我无法让 gm2008 的示例工作（pdf.js 上的内部数据结构显然已经改变），所以我编写了自己的完全基于承诺的解决方案，不使用任何 DOM 元素、查询选择器或画布，使用更新的pdf.js 来自 mozilla
的示例它占用了上传的文件路径，因为我将它与 node-webkit 一起使用。 您需要确保已下载 cmps 并指向某处，并且需要 pdf.js 和 pdf.worker.js 才能使其正常工作。
/**
* Extract text from PDFs with PDF.js
* Uses the demo pdf.js from https://mozilla.github.io/pdf.js/getting_started/
*/
this.pdfToText = function(data) {
PDFJS.workerSrc = 'js/vendor/pdf.worker.js';
PDFJS.cMapUrl = 'js/vendor/pdfjs/cmaps/';
PDFJS.cMapPacked = true;
return PDFJS.getDocument(data).then(function(pdf) {
var pages = [];
for (var i = 0; i < pdf.numPages; i++) {
pages.push(i);
}
return Promise.all(pages.map(function(pageNumber) {
return pdf.getPage(pageNumber + 1).then(function(page) {
return page.getTextContent().then(function(textContent) {
return textContent.items.map(function(item) {
return item.str;
}).join(' ');
});
});
})).then(function(pages) {
return pages.join("\r\n");
});
});
}
用途：
self.pdfToText(files[0].path).then(function(result) {
console.log("PDF done!", result);
})
仅留下完整的工作示例。
<html>
<head>
<script src="https://npmcdn.com/pdfjs-dist/build/pdf.js"></script>
</head>
<body>
<input id="pdffile" name="pdffile" type="file" />
<button id="btn" onclick="convert()">Process</button>
<div id="result"></div>
</body>
</html>
<script>
function convert() {
var fr=new FileReader();
var pdff = new Pdf2TextClass();
fr.onload=function(){
pdff.pdfToText(fr.result, null, (text) => { document.getElementById('result').innerText += text; });
}
fr.readAsDataURL(document.getElementById('pdffile').files[0])
}
function Pdf2TextClass() {
var self = this;
this.complete = 0;
this.pdfToText = function (data, callbackPageDone, callbackAllDone) {
console.assert(data instanceof ArrayBuffer || typeof data == 'string');
var loadingTask = pdfjsLib.getDocument(data);
loadingTask.promise.then(function (pdf) {
var total = pdf._pdfInfo.numPages;
//callbackPageDone( 0, total );
var layers = {};
for (i = 1; i <= total; i++) {
pdf.getPage(i).then(function (page) {
var n = page.pageNumber;
page.getTextContent().then(function (textContent) {
//console.log(textContent.items[0]);0
if (null != textContent.items) {
var page_text = "";
var last_block = null;
for (var k = 0; k < textContent.items.length; k++) {
var block = textContent.items[k];
if (last_block != null && last_block.str[last_block.str.length - 1] != ' ') {
if (block.x < last_block.x)
page_text += "\r\n";
else if (last_block.y != block.y && (last_block.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null))
page_text += ' ';
}
page_text += block.str;
last_block = block;
}
textContent != null && console.log("page " + n + " finished."); //" content: \n" + page_text);
layers[n] = page_text + "\n\n";
}
++self.complete;
//callbackPageDone( self.complete, total );
if (self.complete == total) {
window.setTimeout(function () {
var full_text = "";
var num_pages = Object.keys(layers).length;
for (var j = 1; j <= num_pages; j++)
full_text += layers[j];
callbackAllDone(full_text);
}, 1000);
}
}); // end of page.getTextContent().then
}); // end of page.then
} // of for
});
}; // end of pdfToText()
}; // end of class
</script>这里有一些 JavaScript 代码，可以使用来自 http://hublog.hubmed.org/archives/001948.html 的 Pdf.js 执行您想要的操作：
var input = document.getElementById("input");
var processor = document.getElementById("processor");
var output = document.getElementById("output");
// listen for messages from the processor
window.addEventListener("message", function(event){
if (event.source != processor.contentWindow) return;
switch (event.data){
// "ready" = the processor is ready, so fetch the PDF file
case "ready":
var xhr = new XMLHttpRequest;
xhr.open('GET', input.getAttribute("src"), true);
xhr.responseType = "arraybuffer";
xhr.onload = function(event) {
processor.contentWindow.postMessage(this.response, "*");
};
xhr.send();
break;
// anything else = the processor has returned the text of the PDF
default:
output.textContent = event.data.replace(/\s+/g, " ");
break;
}
}, true);
...这是一个例子：
注意：此代码假设您使用的是nodejs。这意味着您正在解析本地文件而不是网页中的文件，因为最初的问题没有明确询问如何解析网页上的 pdf。
@gm2008 的答案是一个很好的起点（请阅读它及其评论以获取更多信息），但需要一些更新（08/19）并且有一些未使用的代码。我也喜欢更完整的例子。还可以进行更多的重构和调整（例如使用
await和以前一样，它使用 Mozilla 的 PDFjs 库。 npmjs 包位于 https://www.npmjs.com/package/pdfjs-dist。
根据我的经验，这在查找放置空间的位置方面效果不佳，但这是另一个问题。
[编辑：我相信对
.transform// This file is called myPDFfileToText.js and is in the root folder
let PDFJS = require('pdfjs-dist');
let pathToPDF = 'path/to/myPDFfileToText.pdf';
let toText = Pdf2TextObj();
let onPageDone = function() {}; // don't want to do anything between pages
let onFinish = function(fullText) { console.log(fullText) };
toText.pdfToText(pathToPDF, onPageDone, onFinish);
function Pdf2TextObj() {
let self = this;
this.complete = 0;
/**
*
* @param path Path to the pdf file.
* @param callbackPageDone To inform the progress each time
* when a page is finished. The callback function's input parameters are:
* 1) number of pages done.
* 2) total number of pages in file.
* 3) the `page` object itself or null.
* @param callbackAllDone Called after all text has been collected. Input parameters:
* 1) full text of parsed pdf.
*
*/
this.pdfToText = function(path, callbackPageDone, callbackAllDone) {
// console.assert(typeof path == 'string');
PDFJS.getDocument(path).promise.then(function(pdf) {
let total = pdf.numPages;
callbackPageDone(0, total, null);
let pages = {};
// For some (pdf?) reason these don't all come in consecutive
// order. That's why they're stored as an object and then
// processed one final time at the end.
for (let pagei = 1; pagei <= total; pagei++) {
pdf.getPage(pagei).then(function(page) {
let pageNumber = page.pageNumber;
page.getTextContent().then(function(textContent) {
if (null != textContent.items) {
let page_text = "";
let last_item = null;
for (let itemsi = 0; itemsi < textContent.items.length; itemsi++) {
let item = textContent.items[itemsi];
// I think to add whitespace properly would be more complex and
// would require two loops.
if (last_item != null && last_item.str[last_item.str.length - 1] != ' ') {
let itemX = item.transform[5]
let lastItemX = last_item.transform[5]
let itemY = item.transform[4]
let lastItemY = last_item.transform[4]
if (itemX < lastItemX)
page_text += "\r\n";
else if (itemY != lastItemY && (last_item.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null))
page_text += ' ';
} // ends if may need to add whitespace
page_text += item.str;
last_item = item;
} // ends for every item of text
textContent != null && console.log("page " + pageNumber + " finished.") // " content: \n" + page_text);
pages[pageNumber] = page_text + "\n\n";
} // ends if has items
++self.complete;
callbackPageDone(self.complete, total, page);
// If all done, put pages in order and combine all
// text, then pass that to the callback
if (self.complete == total) {
// Using `setTimeout()` isn't a stable way of making sure
// the process has finished. Watch out for missed pages.
// A future version might do this with promises.
setTimeout(function() {
let full_text = "";
let num_pages = Object.keys(pages).length;
for (let pageNum = 1; pageNum <= num_pages; pageNum++)
full_text += pages[pageNum];
callbackAllDone(full_text);
}, 1000);
}
}); // ends page.getTextContent().then
}); // ends page.then
} // ends for every page
});
}; // Ends pdfToText()
return self;
}; // Ends object factory
在终端中运行：
node myPDFfileToText.js更新于 02/2021
<script src="https://npmcdn.com/pdfjs-dist/build/pdf.js"></script>
<script>
function Pdf2TextClass(){
var self = this;
this.complete = 0;
this.pdfToText = function(data, callbackPageDone, callbackAllDone){
console.assert( data instanceof ArrayBuffer || typeof data == 'string' );
var loadingTask = pdfjsLib.getDocument(data);
loadingTask.promise.then(function(pdf) {
var total = pdf._pdfInfo.numPages;
//callbackPageDone( 0, total );
var layers = {};
for (i = 1; i <= total; i++){
pdf.getPage(i).then( function(page){
var n = page.pageNumber;
page.getTextContent().then( function(textContent){
//console.log(textContent.items[0]);0
if( null != textContent.items ){
var page_text = "";
var last_block = null;
for( var k = 0; k < textContent.items.length; k++ ){
var block = textContent.items[k];
if( last_block != null && last_block.str[last_block.str.length-1] != ' '){
if( block.x < last_block.x )
page_text += "\r\n";
else if ( last_block.y != block.y && ( last_block.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null ))
page_text += ' ';
}
page_text += block.str;
last_block = block;
}
textContent != null && console.log("page " + n + " finished."); //" content: \n" + page_text);
layers[n] = page_text + "\n\n";
}
++ self.complete;
//callbackPageDone( self.complete, total );
if (self.complete == total){
window.setTimeout(function(){
var full_text = "";
var num_pages = Object.keys(layers).length;
for( var j = 1; j <= num_pages; j++)
full_text += layers[j] ;
console.log(full_text);
}, 1000);
}
}); // end of page.getTextContent().then
}); // end of page.then
} // of for
});
}; // end of pdfToText()
}; // end of class
var pdff = new Pdf2TextClass();
pdff.pdfToText('PDF_URL');
</script>
@SchizoDuckie 的解决方案，更短：
import { getDocument as loadPdf } from 'pdfjs-dist';
...
async function pdfToTxt(file: File): Promise<string> {
const pdf = await loadPdf(await file.arrayBuffer()).promise;
return Promise.all([...Array(pdf.numPages).keys()]
.map(async num => (await (await pdf.getPage(num + 1)).getTextContent())
.items.map(item => (<any>item).str).join(' ')))
.then(pages => pages.join('\n'));
}
npm install pdf-parse
所需文件：
/node_modules/pdf-parse/lib/pdf.js/v2.0.550/build/pdf.js
加载：
pdf.worker.js
用途：
var pdf = await pdfjsLib.getDocument({ data: new Uint8Array(buffer) }).promise;
var numPages = pdf.numPages;
var texts = [];
for (let i = 1; i <= numPages; i++) {
let page = await pdf.getPage(i);
let textContent = await page.getTextContent();
let textItems = textContent.items;
let pageText = textItems.map(item => item.str).join(" ").replace(/\s+/g," ");
texts.push(pageText);
}
console.log(texts);
缓冲区可以来自：
var file = $("input[type=file]");
file.onchange = function () {
var file = this.files[0];
var reader = new FileReader();
reader.onload = async () => {
var buffer = reader.result;
// use buffer
}
if (file && file.type == "application/pdf") {
reader.readAsArrayBuffer(file);
}
}
对于所有真正想在节点服务器上使用它的人：
/**
* Created by velten on 25.04.16.
*/
"use strict";
let pdfUrl = "http://example.com/example.pdf";
let request = require('request');
var pdfParser = require('pdf2json');
let pdfPipe = request({url: pdfUrl, encoding:null}).pipe(pdfParser);
pdfPipe.on("pdfParser_dataError", err => console.error(err) );
pdfPipe.on("pdfParser_dataReady", pdf => {
//optionally:
//let pdf = pdfParser.getMergedTextBlocksIfNeeded();
let count1 = 0;
//get text on a particular page
for (let page of pdf.formImage.Pages) {
count1 += page.Texts.length;
}
console.log(count1);
pdfParser.destroy();
});
这是可能的，但是：
因此，如果您有一些空闲时间，您可以学习 pdf 格式并自己编写这样的库，或者当然您也可以使用服务器端库。