web-fetcher-plugin

"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;
    };
})();
Object.defineProperty(exports, "__esModule", { value: true });
exports.parseHtml = parseHtml;
exports.extractElementsBySelector = extractElementsBySelector;
exports.searchInHtml = searchInHtml;
const cheerio = __importStar(require("cheerio"));
async function parseHtml(html) {
    const $ = cheerio.load(html);
    // Extract title
    const title = $("title").text() || $('meta[property="og:title"]').attr("content") || "";
    // Extract description
    const description = $('meta[name="description"]').attr("content") ||
        $('meta[property="og:description"]').attr("content") ||
        "";
    // Extract og:image
    const ogImage = $('meta[property="og:image"]').attr("content") || "";
    // Extract all headings
    const headings = [];
    $("h1, h2, h3, h4, h5, h6").each((_, elem) => {
        const text = $(elem).text().trim();
        if (text) {
            headings.push(text);
        }
    });
    // Extract all paragraphs
    const paragraphs = [];
    $("p").each((_, elem) => {
        const text = $(elem).text().trim();
        if (text) {
            paragraphs.push(text);
        }
    });
    // Extract all links
    const links = [];
    $("a").each((_, elem) => {
        const href = $(elem).attr("href") || "";
        const text = $(elem).text().trim();
        if (href && text) {
            links.push({ href, text });
        }
    });
    // Extract all meta tags
    const metadata = {};
    $("meta").each((_, elem) => {
        const name = $(elem).attr("name") || $(elem).attr("property");
        const content = $(elem).attr("content");
        if (name && content) {
            metadata[name] = content;
        }
    });
    return {
        title,
        description,
        ogImage,
        headings,
        paragraphs,
        links,
        metadata,
    };
}
function extractElementsBySelector(html, selector) {
    const $ = cheerio.load(html);
    const results = [];
    try {
        $(selector).each((_, elem) => {
            const tag = elem.name || "unknown";
            const content = $(elem).html() || "";
            const attributes = {};
            if (elem.attribs) {
                Object.keys(elem.attribs).forEach((key) => {
                    attributes[key] = elem.attribs[key];
                });
            }
            results.push({
                tag,
                content: content.substring(0, 500), // Limit content length
                attributes,
            });
        });
    }
    catch (error) {
        console.error("Error extracting elements:", error);
    }
    return results;
}
function searchInHtml(html, keywords) {
    const $ = cheerio.load(html);
    const text = $.root().text();
    return keywords.map((keyword) => {
        const regex = new RegExp(keyword, "gi");
        const matches = (text.match(regex) || []).length;
        // Extract context around matches
        const context = [];
        const lowerKeyword = keyword.toLowerCase();
        const sentences = text.split(/[.!?]+/);
        for (const sentence of sentences) {
            if (sentence.toLowerCase().includes(lowerKeyword) && context.length < 3) {
                context.push(sentence.trim().substring(0, 200));
            }
        }
        return {
            keyword,
            matches,
            context,
        };
    });
}
//# sourceMappingURL=parser.js.map