resume-parser-mcp/dist/parser/extractFileText/extractTextFromPdf.js

To install dependencies:

"use strict";
var __importDefault = (this && this.__importDefault) || function (mod) {
    return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.extractTextFromPdf = extractTextFromPdf;
const fs = require('fs');
const fsPromises = fs.promises;
const pdf_parse_1 = __importDefault(require("pdf-parse")); // 导入pdf-parse库
const logger_1 = require("../../utils/logger");
async function extractTextFromPdf(filePath) {
    const logger = (0, logger_1.useLogger)();
    try {
        const dataBuffer = await fsPromises.readFile(filePath);
        const data = await (0, pdf_parse_1.default)(dataBuffer);
        return data.text;
    }
    catch (error) {
        logger.error('PDF文本提取失败:', error?.message);
        throw new Error(`无法提取PDF文本: ${error?.message}`);
    }
}