var pdfParser = require('pdf-parser')
var fs = require('fs')
var PDF_PATH = __dirname + '/pdfs'
var results = []
var failed = []
fs.readdir(PDF_PATH, function(err, files){
if(err){
return console.log(err)
}
for(const file of files){
let the_ent = {
'name': '',
'other data': []
}
pdfParser.pdf2json(PDF_PATH + '/' + file, function(error, pdf){
if(error != null){
console.log(error)
}else if(pdf['pages'] == undefined){
failed.push(file)
console.log(file +' failed')
}else{
//populate 'results' array
}
console.log(/*pdf_data*/)
results.push(/*pdf_data*/)
})
}
console.log(results)
console.log(failed)
results = JSON.stringify(results)
//fs.writeFileSync() write results to json
})
我不知道今天早上我怎么了,我不知道如何异步编写它;显然,脚本执行后立即触发底部的日志/写文件。
我已经尝试包装异步函数并等待readdir / pdf解析而不是使用回调-显然不正确。我只是想解析文件夹中的每个pdf-将我想要的内容推送到一些数组,然后在循环完成zzz后将它们记录下来。
包装最小的异步tasks into Promises,然后使用async / await组合它们:
// the Promise wrapper:
const parsePdf = file => new Promise((res, rej) => pdfParser.pdf2json(file, (err, r) => err ? rej(err) : res(r));
(async function () { // start an asynchronous context
const PDF_PATH = __dirname + '/pdfs';
const results = [], failed = []; // prefer const over let
// reading files in a promising way is already provided natively:
const files = await fs.promises.readdir(PDF_PATH);
for(const file of files){ // this is in series, in parallel would probably be faster
let the_ent = {
name: '',
'other data': [], // avoid whitespaces!
};
const pdf = await parsePdf(PDF_PATH + '/' +file);
if(pdf.pages === undefined) { // prefer equality (===) over comparison (==)
failed.push(file);
console.log(file + ' failed');
} else {
// populate 'results' array
}
}
console.log(results, failed);
})();
您可能也可以处理文件in parallel。
您可以使用util.promisify
来实现同步功能:
const readdir = util.promisify(fs.readdir);
const reader = util.promisify(pdfParser.pdf2json);
最小演示:
const fs = require('fs');
const util = require('util');
var pdfParser = require('pdf-parser');
const readdir = util.promisify(fs.readdir);
const reader = util.promisify(pdfParser.pdf2json);
var PDF_PATH = __dirname + '/pdfs';
(async () => {
async function processFiles() {
let results = [];
let files = await readdir(PDF_PATH);
for (const file of files) {
let pdf = await reader(PDF_PATH + '/' + file);
results.push(pdf);
}
return results;
}
const result = await processFiles();
console.info(result);
})();