Spaces:
Sleeping
Sleeping
File size: 2,418 Bytes
9a43362 d9ba1d6 9a43362 d9ba1d6 c1e1733 d9ba1d6 9a43362 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /**
* URL Parser & Orchestrator
* Routes URLs to platform-specific scrapers
*/
import { detectPlatform, type PlatformType } from '../scraper/detector';
import { scrapeInstagram } from '../scraper/instagram';
import { scrapeTwitter } from '../scraper/twitter';
import { scrapeTikTok } from '../scraper/tiktok';
import { scrapeThreads } from '../scraper/threads';
import { scrapeWeb } from '../scraper/web';
import type { ScrapingResult } from '../scraper/apify';
export interface URLParseResult extends ScrapingResult {
platform?: PlatformType;
}
/**
* Parse URL and extract content
* Automatically routes to correct scraper based on platform
*/
export async function parseURL(url: string): Promise<URLParseResult> {
try {
// Detect platform
const detection = detectPlatform(url);
if (detection.platform === 'unknown') {
return {
success: false,
platform: 'unknown',
error: 'Could not identify URL type. Please provide a valid URL.',
};
}
// Route to appropriate scraper
let result: ScrapingResult;
switch (detection.platform) {
case 'instagram':
result = await scrapeInstagram(url);
break;
case 'twitter':
result = await scrapeTwitter(url);
break;
case 'tiktok':
result = await scrapeTikTok(url);
break;
case 'threads':
result = await scrapeThreads(url);
break;
case 'web':
result = await scrapeWeb(url);
break;
default:
result = await scrapeWeb(url);
}
return {
...result,
platform: detection.platform,
};
} catch (error) {
console.warn('[url parser] scraping failed or no API key, falling back to raw url:', error);
// Since scraping failed, pass the raw URL to the LLM to guess the context
return {
success: true,
platform: 'unknown',
content: url, // Fix: matched 'content' property instead of 'extractedText' for proper mapping
title: 'Failed to scrape - falling back to URL guess',
};
}
}
/**
* Check if URL is parseable
*/
export function isParseableURL(url: string): boolean {
const detection = detectPlatform(url);
return detection.platform !== 'unknown';
}
/**
* Get platform type for URL
*/
export function getPlatformType(url: string): PlatformType {
const detection = detectPlatform(url);
return detection.platform;
}
|