2025-1-8

目录

• pdf解析json方案
  • nodejs
• ui
• 按钮获取当前位置坐标

pdf解析json方案

nodejs

const fs = require("fs");
const pdf = require("pdf-parse");

// PDF 转 JSON 函数
async function pdfToJson(pdfPath) {
  try {
    const dataBuffer = fs.readFileSync(pdfPath); // 读取 PDF 文件
    const data = await pdf(dataBuffer);
    console.log(data);
    // 将 PDF 的文本内容存入 JSON
    const result = {
      metadata: {
        title: data.info.Title || "Unknown Title",
        author: data.info.Author || "Unknown Author",
        pages: data.numpages,
      },
      content: data.text.split("\n"), // 按行分割文本
    };

    return result;
  } catch (error) {
    console.error("Error processing PDF:", error);
    return null;
  }
}

// 示例：读取一个 PDF 文件并转换为 JSON
const pdfPath = "./1.pdf"; // 替换为你的 PDF 文件路径
pdfToJson(pdfPath).then(json => {
  if (json) {
    fs.writeFileSync("output.json", JSON.stringify(json, null, 2), "utf-8");
    console.log("PDF 转换为 JSON 成功，已保存为 output.json");
  }
});

输出为

console

{
  numpages: 40,
  numrender: 40,
  info: {
    PDFFormatVersion: '1.3',
    IsAcroFormPresent: false,
    IsXFAPresent: false,
    Creator: 'PFU ScanSnap Home 2.8.0 #iX1600(W)',
    Producer: 'PFU PDF Library 2.0.0',
    CreationDate: "D:20230805110835+08'00'",
    ModDate: "D:20230805110835+08'00'"
  },
  metadata: Metadata {
    _metadata: [Object: null prototype] {
      'pdf:producer': 'PFU PDF Library 2.0.0',
      'dc:format': 'application/pdf',
      'xmpmm:documentid': 'uuid:b19f17c8-ff22-4e80-bd5a-5bb350fb186f',
      'xmpmm:instanceid': 'uuid:5cd8fa62-f842-4511-bbef-bc897585a608',
      'xmp:creatortool': 'PFU ScanSnap Home 2.8.0 #iX1600(W)',
      'xmp:createdate': '2023-08-05T11:08:35+08:00',
      'xmp:modifydate': '2023-08-05T11:08:35+08:00',
      'xmp:metadatadate': '2023-08-05T11:08:35+08:00'
    }
  },
  text: '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n' +
    '\n',
  version: '1.10.100'
}

output.json

{
  "metadata": {
    "title": "Unknown Title",
    "author": "Unknown Author",
    "pages": 40
  },
  "content": [
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    ""
  ]
}

问题

• 为什么 data.text 是空字符串？

text 中没有有效内容，可能是以下原因：

1. PDF 是扫描件（图片型 PDF）

图片型 PDF 没有嵌入文本，pdf-parse 无法直接提取文本。 需要 OCR（光学字符识别）技术来提取文字。例如，使用 Tesseract.js 进行文本识别。

2. 字体编码问题

某些 PDF 使用自定义字体编码，可能导致文本解析失败。可以尝试其他库（例如 pdf.js）。

3. PDF 格式问题

某些 PDF 格式可能使用复杂结构（例如嵌套对象或加密），导致解析失败。

解决

const fs = require("fs");
const pdf = require("pdf-parse");
const { spawn } = require("child_process");
const Tesseract = require("tesseract.js");

async function convertPDFToImages(pdfPath, outputDir) {
  return new Promise((resolve, reject) => {
    const pdfToPpm = spawn("pdftoppm", [
      "-png",
      pdfPath,
      `${outputDir}/output`,
    ]);

    pdfToPpm.on("close", code => {
      if (code === 0) {
        resolve("PDF successfully converted to images");
      } else {
        reject(new Error("Failed to convert PDF to images"));
      }
    });
  });
}

async function ocrImage(imagePath) {
  return Tesseract.recognize(imagePath, "chi_sim")
    .then(({ data: { text } }) => text)
    .catch(err => {
      console.error("OCR failed:", err);
    });
}

async function processPDFWithOCR(pdfPath) {
  const outputDir = "./images";

  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir);
  }

  console.log("Converting PDF to images...");
  await convertPDFToImages(pdfPath, outputDir);

  const images = fs
    .readdirSync(outputDir)
    .filter(file => file.endsWith(".png"));
  console.log("Extracting text from images using OCR...");

  for (const image of images) {
    const imagePath = `${outputDir}/${image}`;
    const text = await ocrImage(imagePath);
    console.log(`Text from ${image}:\n`, text);
  }
}

// 替换为你的 PDF 文件路径
const pdfPath = "./1.pdf";

processPDFWithOCR(pdfPath)
  .then(() => console.log("OCR process completed"))
  .catch(err => console.error("Error:", err));

ui

• rainbow border

.rainbow-border {
  border: 8px solid;
  border-image: linear-gradient(
    35deg,
    rgb(211, 103, 193) 10%,
    rgb(222, 223, 64) 25%,
    rgb(98, 203, 92) 50%,
    rgb(0, 187, 203) 75%,
    rgb(171, 121, 214) 90%
  );
  color: white;
  text-align: center;
  border-image-slice: 1;
}

按钮获取当前位置坐标