markdown-crawler/dist/cjs/cli.js

A powerful web crawler that extracts content from web pages and converts them to clean Markdown format, with support for code blocks and GitHub Flavored Markdown

#!/usr/bin/env node
"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    var desc = Object.getOwnPropertyDescriptor(m, k);
    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
      desc = { enumerable: true, get: function() { return m[k]; } };
    }
    Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
    Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
    o["default"] = v;
});
var __importStar = (this && this.__importStar) || (function () {
    var ownKeys = function(o) {
        ownKeys = Object.getOwnPropertyNames || function (o) {
            var ar = [];
            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
            return ar;
        };
        return ownKeys(o);
    };
    return function (mod) {
        if (mod && mod.__esModule) return mod;
        var result = {};
        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
        __setModuleDefault(result, mod);
        return result;
    };
})();
var __importDefault = (this && this.__importDefault) || function (mod) {
    return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
const commander_1 = require("commander");
const crawler_js_1 = require("./crawler.js");
const yaml = __importStar(require("yaml")); // Changed import style
const fs_1 = __importDefault(require("fs"));
const path_1 = __importDefault(require("path"));
const program = new commander_1.Command();
program
    .name('md-crawler')
    .description('Crawl web pages and convert to YAML format Markdown. Will recursively crawl all pages in subdirectories.')
    .argument('<url>', 'URL to crawl. For URLs containing spaces, wrap them in double quotes: "http://example.com/my page"')
    .argument('<output>', 'Output YAML file name. Will be saved in the current working directory.')
    .action(async (url, output) => {
    try {
        console.log('Starting web crawl...');
        const additionalGlobalUrls = [url.endsWith('/') ? `${url}**/*` : `${url.substring(0, url.lastIndexOf('/'))}/**/*`];
        const results = await (0, crawler_js_1.crawl)(url, additionalGlobalUrls);
        console.log('Converting format...');
        // 创建YAML文档，确保Markdown内容保持正确格式
        const yamlData = results.map(({ title, url, markdown }) => {
            // 使用YAML的块字符串格式(|)，并保持原始格式
            return {
                url,
                title,
                content: markdown
            };
        });
        // 使用yaml.stringify并设置正确的选项
        const yamlString = yaml.stringify(yamlData, {
            indent: 2,
            lineWidth: 0, // 禁用行宽限制，避免长行被折断
            doubleQuotedAsJSON: false, // 避免过度转义
            doubleQuotedMinMultiLineLength: Infinity, // 避免多行字符串使用双引号
            defaultStringType: 'BLOCK_LITERAL' // 使用块字符串格式(|)
        });
        // 后处理YAML字符串，移除内容中不必要的反斜杠
        // const processedYamlString = yamlString
        //   // 保留YAML结构，但移除内容中的反斜杠+换行符组合
        //   .replace(/(\s*content: \|[\r\n]+)([^]*?)(?=\n\s*-|\n\s*$)/g, (match, prefix, content) => {
        //     // 只处理content部分，保留前缀
        //     const processedContent = content
        //       // 移除反斜杠+换行符组合，但保留实际换行
        //       .replace(/\\(\r?\n\s*)/g, '$1')
        //       // 修复URL中的反斜杠
        //       .replace(/\\\&/g, '&')
        //       // 移除链接中的反斜杠
        //       .replace(/\\\[/g, '[')
        //       .replace(/\\\]/g, ']')
        //       .replace(/\\\(/g, '(')
        //       .replace(/\\\)/g, ')')
        //       // 保留Markdown代码块中的反斜杠
        //       .replace(/```([^`]*?)```/g, (codeMatch) => codeMatch.replace(/\\\\/g, '\\\\'));
        //     return prefix + processedContent;
        //   });
        // Check and ensure file path ends with .yaml
        const outputWithExt = output.endsWith('.yaml') ? output : `${output}.yaml`;
        const outputPath = path_1.default.resolve(process.cwd(), outputWithExt);
        fs_1.default.writeFileSync(outputPath, yamlString);
        console.log(`Success! Results saved to: ${outputPath}`);
    }
    catch (error) {
        console.error('Error occurred:', error);
        process.exit(1);
    }
});
program.parse();