cea-core/lib/src/crawler/capcha.js

basic cea api

import fs from 'fs';
import fetch from 'node-fetch';
import * as tesseract from 'tesseract.js';
const { createWorker } = tesseract;
const tessdataPath = '/tmp/eng.traineddata.gz';
async function downloadTessdata() {
    process.env.TESSDATA_PREFIX = '/tmp';
    if (!fs.existsSync('/tmp')) {
        fs.mkdirSync('/tmp');
    }
    else {
        if (fs.existsSync(tessdataPath)) {
            return;
        }
    }
    console.log(await download('https://beetcb.gitee.io/filetransfer/tmp/eng.traineddata.gz', tessdataPath));
}
async function download(url, filename) {
    const stream = fs.createWriteStream(filename);
    const res = await fetch(url);
    const result = await new Promise((resolve, reject) => {
        var _a, _b;
        (_a = res.body) === null || _a === void 0 ? void 0 : _a.pipe(stream);
        (_b = res.body) === null || _b === void 0 ? void 0 : _b.on('error', (e) => reject(e));
        stream.on('close', () => resolve(`Downloaded tess data as ${filename}`));
    }).catch((err) => console.error(err));
    return result;
}
async function ocr(captchaUrl) {
    await downloadTessdata();
    const worker = createWorker({
        langPath: '/tmp',
        cachePath: '/tmp',
    });
    await worker.load();
    await worker.loadLanguage('eng');
    await worker.initialize('eng');
    await worker.setParameters({
        tessedit_char_whitelist: 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890',
    });
    const { data: { text }, } = await worker.recognize(captchaUrl);
    await worker.terminate();
    return text;
}
export default ocr;
//# sourceMappingURL=capcha.js.map