Press n or j to go to the next uncovered block, b, p or k for the previous block.
| 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 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 | 12x 12x 12x 5x 12x 3x 12x 11x 11x 11x 1x 19x 19x 19x 19x 15x 5x 19x 19x 4x 15x 1x 14x 1x 13x 13x 1x 19x 19x 19x 19x 2x 2x 2x 2x 2x 2x 2x 2x 1x 1x 1x 2x 18x 9x 9x 9x 9x 9x 9x 9x 9x 9x 9x 9x 14x 14x 14x 14x 14x 14x 14x 11x 10x 10x 9x 9x 9x 9x 9x 6x 6x 6x 6x 6x 5x 4x 9x 9x 9x 4x 9x 8x 8x 8x 5x 3x 10x 3x 3x 1x 4x 3x 5x 53x 53x 1x 52x 52x 52x 52x 52x 52x 52x 52x 2x 52x 52x 3x 52x 52x 52x 3x 49x 3x 49x 49x 49x 49x 49x 49x 49x 49x 49x 5x 5x 5x 1x 49x 49x 49x 49x 49x 49x 49x 49x 49x 49x 49x 49x 49x 2x 49x 2x 49x 49x 49x 2x 49x 49x 49x 49x 49x 49x 49x 49x 49x 49x 49x 44x 49x 49x 2x 47x 47x 47x 47x 3x 1x 2x 2x 44x 40x 4x 2x 2x 1x 47x 47x 5x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 1x 5x 5x 5x 5x 5x 2x 2x 47x 2x 47x 2x 47x 1x 47x 2x 3x 2x 47x 6x | import { BaseHandler } from './base-handler.js';
import { BatchCrawlOptions, CrawlResultItem, AdvancedCrawlConfig, CrawlEndpointResponse } from '../types.js';
import * as fs from 'fs/promises';
import * as path from 'path';
import * as os from 'os';
export class CrawlHandlers extends BaseHandler {
async batchCrawl(options: BatchCrawlOptions) {
try {
// Build crawler config if needed
const crawler_config: Record<string, unknown> = {};
// Handle remove_images by using exclude_tags
if (options.remove_images) {
crawler_config.exclude_tags = ['img', 'picture', 'svg'];
}
if (options.bypass_cache) {
crawler_config.cache_mode = 'BYPASS';
}
const response = await this.axiosClient.post('/crawl', {
urls: options.urls,
max_concurrent: options.max_concurrent,
crawler_config: Object.keys(crawler_config).length > 0 ? crawler_config : undefined,
});
const results = response.data.results || [];
return {
content: [
{
type: 'text',
text: `Batch crawl completed. Processed ${results.length} URLs:\n\n${results
.map(
(r: CrawlResultItem, i: number) => `${i + 1}. ${options.urls[i]}: ${r.success ? 'Success' : 'Failed'}`,
)
.join('\n')}`,
},
],
};
} catch (error) {
throw this.formatError(error, 'batch crawl');
}
}
async smartCrawl(options: { url: string; max_depth?: number; follow_links?: boolean; bypass_cache?: boolean }) {
try {
// First, try to detect the content type from URL or HEAD request
let contentType = '';
try {
const headResponse = await this.axiosClient.head(options.url);
contentType = headResponse.headers['content-type'] || '';
} catch {
// If HEAD request fails, continue anyway - we'll detect from the crawl response
console.debug('HEAD request failed, will detect content type from response');
}
let detectedType = 'html';
if (options.url.includes('sitemap') || options.url.endsWith('.xml')) {
detectedType = 'sitemap';
} else if (options.url.includes('rss') || options.url.includes('feed')) {
detectedType = 'rss';
} else if (contentType.includes('text/plain') || options.url.endsWith('.txt')) {
detectedType = 'text';
} else Iif (contentType.includes('application/xml') || contentType.includes('text/xml')) {
detectedType = 'xml';
} else if (contentType.includes('application/json')) {
detectedType = 'json';
}
// Crawl without the unsupported 'strategy' parameter
const response = await this.axiosClient.post('/crawl', {
urls: [options.url],
crawler_config: {
cache_mode: options.bypass_cache ? 'BYPASS' : 'ENABLED',
},
browser_config: {
headless: true,
browser_type: 'chromium',
},
});
const results = response.data.results || [];
const result = results[0] || {};
// Handle follow_links for sitemaps and RSS feeds
if (options.follow_links && (detectedType === 'sitemap' || detectedType === 'rss' || detectedType === 'xml')) {
// Extract URLs from the content
const urlPattern = /<loc>(.*?)<\/loc>|<link[^>]*>(.*?)<\/link>|href=["']([^"']+)["']/gi;
const content = result.markdown || result.html || '';
const foundUrls: string[] = [];
let match;
while ((match = urlPattern.exec(content)) !== null) {
const url = match[1] || match[2] || match[3];
Eif (url && url.startsWith('http')) {
foundUrls.push(url);
}
}
if (foundUrls.length > 0) {
// Limit to first 10 URLs to avoid overwhelming the system
const urlsToFollow = foundUrls.slice(0, Math.min(10, options.max_depth || 10));
// Crawl the found URLs
await this.axiosClient.post('/crawl', {
urls: urlsToFollow,
max_concurrent: 3,
bypass_cache: options.bypass_cache,
});
return {
content: [
{
type: 'text',
text: `Smart crawl detected content type: ${detectedType}\n\nMain content:\n${result.markdown?.raw_markdown || result.html || 'No content extracted'}\n\n---\nFollowed ${urlsToFollow.length} links:\n${urlsToFollow.map((url, i) => `${i + 1}. ${url}`).join('\n')}`,
},
...(result.metadata
? [
{
type: 'text',
text: `\n\n---\nMetadata:\n${JSON.stringify(result.metadata, null, 2)}`,
},
]
: []),
],
};
}
}
return {
content: [
{
type: 'text',
text: `Smart crawl detected content type: ${detectedType}\n\n${result.markdown?.raw_markdown || result.html || 'No content extracted'}`,
},
...(result.metadata
? [
{
type: 'text',
text: `\n\n---\nMetadata:\n${JSON.stringify(result.metadata, null, 2)}`,
},
]
: []),
],
};
} catch (error) {
throw this.formatError(error, 'smart crawl');
}
}
async crawlRecursive(options: {
url: string;
max_depth?: number;
max_pages?: number;
include_pattern?: string;
exclude_pattern?: string;
}) {
try {
const startUrl = new URL(options.url);
const visited = new Set<string>();
const toVisit: Array<{ url: string; depth: number }> = [{ url: options.url, depth: 0 }];
const results: Array<{ url: string; content: string; internal_links_found: number; depth: number }> = [];
let maxDepthReached = 0;
const includeRegex = options.include_pattern ? new RegExp(options.include_pattern) : null;
const excludeRegex = options.exclude_pattern ? new RegExp(options.exclude_pattern) : null;
const maxDepth = options.max_depth !== undefined ? options.max_depth : 3;
const maxPages = options.max_pages || 50;
while (toVisit.length > 0 && results.length < maxPages) {
const current = toVisit.shift();
Iif (!current || visited.has(current.url) || current.depth > maxDepth) {
continue;
}
visited.add(current.url);
try {
// Check URL patterns
Iif (excludeRegex && excludeRegex.test(current.url)) continue;
Iif (includeRegex && !includeRegex.test(current.url)) continue;
// Crawl the page using the crawl endpoint to get links
const response = await this.axiosClient.post('/crawl', {
urls: [current.url],
crawler_config: {
cache_mode: 'BYPASS',
},
});
const crawlResults = response.data.results || [response.data];
const result: CrawlResultItem = crawlResults[0];
if (result && result.success) {
const markdownContent = result.markdown?.fit_markdown || result.markdown?.raw_markdown || '';
const internalLinksCount = result.links?.internal?.length || 0;
maxDepthReached = Math.max(maxDepthReached, current.depth);
results.push({
url: current.url,
content: markdownContent,
internal_links_found: internalLinksCount,
depth: current.depth,
});
// Add internal links to crawl queue
if (current.depth < maxDepth && result.links?.internal) {
for (const linkObj of result.links.internal) {
const linkUrl = linkObj.href || linkObj;
try {
const absoluteUrl = new URL(linkUrl, current.url).toString();
if (!visited.has(absoluteUrl) && new URL(absoluteUrl).hostname === startUrl.hostname) {
toVisit.push({ url: absoluteUrl, depth: current.depth + 1 });
}
} catch (e) {
// Skip invalid URLs
console.debug('Invalid URL:', e);
}
}
}
}
} catch (error) {
// Log but continue crawling other pages
console.error(`Failed to crawl ${current.url}:`, error instanceof Error ? error.message : error);
}
}
// Prepare the output text
let outputText = `Recursive crawl completed:\n\nPages crawled: ${results.length}\nStarting URL: ${options.url}\n`;
if (results.length > 0) {
outputText += `Max depth reached: ${maxDepthReached} (limit: ${maxDepth})\n\nNote: Only internal links (same domain) are followed during recursive crawling.\n\nPages found:\n${results.map((r) => `- [Depth ${r.depth}] ${r.url}\n Content: ${r.content.length} chars\n Internal links found: ${r.internal_links_found}`).join('\n')}`;
} else {
outputText += `\nNo pages could be crawled. This might be due to:\n- The starting URL returned an error\n- No internal links were found\n- All discovered links were filtered out by include/exclude patterns`;
}
return {
content: [
{
type: 'text',
text: outputText,
},
],
};
} catch (error) {
throw this.formatError(error, 'crawl recursively');
}
}
async parseSitemap(options: { url: string; filter_pattern?: string }) {
try {
// Fetch the sitemap directly (not through Crawl4AI server)
const axios = (await import('axios')).default;
const response = await axios.get(options.url, {
timeout: 30000,
headers: {
'User-Agent': 'Mozilla/5.0 (compatible; MCP-Crawl4AI/1.0)',
},
});
const sitemapContent = response.data;
// Parse XML content - simple regex approach for basic sitemaps
const urlMatches = sitemapContent.match(/<loc>(.*?)<\/loc>/g) || [];
const urls = urlMatches.map((match: string) => match.replace(/<\/?loc>/g, ''));
// Apply filter if provided
let filteredUrls = urls;
if (options.filter_pattern) {
const filterRegex = new RegExp(options.filter_pattern);
filteredUrls = urls.filter((url: string) => filterRegex.test(url));
}
return {
content: [
{
type: 'text',
text: `Sitemap parsed successfully:\n\nTotal URLs found: ${urls.length}\nFiltered URLs: ${filteredUrls.length}\n\nURLs:\n${filteredUrls.slice(0, 100).join('\n')}${filteredUrls.length > 100 ? '\n... and ' + (filteredUrls.length - 100) + ' more' : ''}`,
},
],
};
} catch (error) {
throw this.formatError(error, 'parse sitemap');
}
}
async crawl(options: Record<string, unknown>) {
try {
// Ensure options is an object
if (!options || typeof options !== 'object') {
throw new Error('crawl requires options object with at least a url parameter');
}
// Build browser_config
const browser_config: Record<string, unknown> = {
headless: true, // Always true as noted
};
if (options.browser_type) browser_config.browser_type = options.browser_type;
if (options.viewport_width) browser_config.viewport_width = options.viewport_width;
if (options.viewport_height) browser_config.viewport_height = options.viewport_height;
if (options.user_agent) browser_config.user_agent = options.user_agent;
if (options.headers) browser_config.headers = options.headers;
if (options.cookies) browser_config.cookies = options.cookies;
// Handle proxy configuration
if (options.proxy_server) {
browser_config.proxy_config = {
server: options.proxy_server,
username: options.proxy_username,
password: options.proxy_password,
};
}
// Build crawler_config
const crawler_config: Record<string, unknown> = {};
// Content filtering
if (options.word_count_threshold !== undefined)
crawler_config.word_count_threshold = options.word_count_threshold;
if (options.excluded_tags) crawler_config.excluded_tags = options.excluded_tags;
if (options.remove_overlay_elements) crawler_config.remove_overlay_elements = options.remove_overlay_elements;
// JavaScript execution
if (options.js_code !== undefined && options.js_code !== null) {
// If js_code is an array, join it with newlines for the server
crawler_config.js_code = Array.isArray(options.js_code) ? options.js_code.join('\n') : options.js_code;
} else if (options.js_code === null) {
// If js_code is explicitly null, throw a helpful error
throw new Error('js_code parameter is null. Please provide JavaScript code as a string or array of strings.');
}
if (options.wait_for) crawler_config.wait_for = options.wait_for;
if (options.wait_for_timeout) crawler_config.wait_for_timeout = options.wait_for_timeout;
// Dynamic content
if (options.delay_before_scroll) crawler_config.delay_before_scroll = options.delay_before_scroll;
if (options.scroll_delay) crawler_config.scroll_delay = options.scroll_delay;
// Content processing
if (options.process_iframes) crawler_config.process_iframes = options.process_iframes;
if (options.exclude_external_links) crawler_config.exclude_external_links = options.exclude_external_links;
// Export options
if (options.screenshot) crawler_config.screenshot = options.screenshot;
if (options.pdf) crawler_config.pdf = options.pdf;
// Session and cache
if (options.session_id) {
crawler_config.session_id = options.session_id;
// Update session last_used time
const session = this.sessions.get(String(options.session_id));
if (session) {
session.last_used = new Date();
}
}
if (options.cache_mode) crawler_config.cache_mode = String(options.cache_mode).toLowerCase();
// Performance
Iif (options.timeout) crawler_config.timeout = options.timeout;
if (options.verbose) crawler_config.verbose = options.verbose;
// Additional crawler parameters
Iif (options.wait_until) crawler_config.wait_until = options.wait_until;
Iif (options.page_timeout) crawler_config.page_timeout = options.page_timeout;
Iif (options.wait_for_images) crawler_config.wait_for_images = options.wait_for_images;
Iif (options.ignore_body_visibility) crawler_config.ignore_body_visibility = options.ignore_body_visibility;
if (options.scan_full_page) crawler_config.scan_full_page = options.scan_full_page;
if (options.remove_forms) crawler_config.remove_forms = options.remove_forms;
if (options.keep_data_attributes) crawler_config.keep_data_attributes = options.keep_data_attributes;
Iif (options.excluded_selector) crawler_config.excluded_selector = options.excluded_selector;
if (options.only_text) crawler_config.only_text = options.only_text;
// Media handling
if (options.image_description_min_word_threshold !== undefined)
crawler_config.image_description_min_word_threshold = options.image_description_min_word_threshold;
if (options.image_score_threshold !== undefined)
crawler_config.image_score_threshold = options.image_score_threshold;
if (options.exclude_external_images) crawler_config.exclude_external_images = options.exclude_external_images;
if (options.screenshot_wait_for !== undefined) crawler_config.screenshot_wait_for = options.screenshot_wait_for;
// Link filtering
if (options.exclude_social_media_links)
crawler_config.exclude_social_media_links = options.exclude_social_media_links;
if (options.exclude_domains) crawler_config.exclude_domains = options.exclude_domains;
// Page interaction
if (options.js_only) crawler_config.js_only = options.js_only;
if (options.simulate_user) crawler_config.simulate_user = options.simulate_user;
if (options.override_navigator) crawler_config.override_navigator = options.override_navigator;
if (options.magic) crawler_config.magic = options.magic;
// Virtual scroll
if (options.virtual_scroll_config) crawler_config.virtual_scroll_config = options.virtual_scroll_config;
// Cache control
if (options.cache_mode) crawler_config.cache_mode = options.cache_mode;
// Other
if (options.log_console) crawler_config.log_console = options.log_console;
if (options.capture_mhtml) crawler_config.capture_mhtml = options.capture_mhtml;
// Call service with proper configuration
const crawlConfig: AdvancedCrawlConfig = {
url: options.url ? String(options.url) : undefined,
crawler_config,
};
// Only include browser_config if we're not using a session
if (!options.session_id) {
crawlConfig.browser_config = browser_config;
}
const response: CrawlEndpointResponse = await this.service.crawl(crawlConfig);
// Validate response structure
if (!response || !response.results || response.results.length === 0) {
throw new Error('Invalid response from server: no results received');
}
const result: CrawlResultItem = response.results[0];
// Build response content
const content = [];
// Main content - use markdown.raw_markdown as primary content
let mainContent = 'No content extracted';
if (result.extracted_content) {
// Handle extraction results which might be objects or strings
if (typeof result.extracted_content === 'string') {
mainContent = result.extracted_content;
} else Eif (typeof result.extracted_content === 'object') {
mainContent = JSON.stringify(result.extracted_content, null, 2);
}
} else if (result.markdown?.raw_markdown) {
mainContent = result.markdown.raw_markdown;
} else if (result.html) {
mainContent = result.html;
} else if (result.fit_html) {
mainContent = result.fit_html;
}
content.push({
type: 'text',
text: mainContent,
});
// Screenshot if available
if (result.screenshot) {
// Save to local directory if requested
let savedFilePath: string | undefined;
if (options.screenshot_directory && typeof options.screenshot_directory === 'string') {
try {
// Resolve home directory path
let screenshotDir = options.screenshot_directory;
Iif (screenshotDir.startsWith('~')) {
const homedir = os.homedir();
screenshotDir = path.join(homedir, screenshotDir.slice(1));
}
// Check if user provided a file path instead of directory
Iif (screenshotDir.endsWith('.png') || screenshotDir.endsWith('.jpg')) {
console.warn(
`Warning: screenshot_directory should be a directory path, not a file path. Using parent directory.`,
);
screenshotDir = path.dirname(screenshotDir);
}
// Ensure directory exists
await fs.mkdir(screenshotDir, { recursive: true });
// Generate filename from URL and timestamp
const url = new URL(String(options.url));
const hostname = url.hostname.replace(/[^a-z0-9]/gi, '-');
const timestamp = new Date().toISOString().replace(/[:.]/g, '-').slice(0, -5);
const filename = `${hostname}-${timestamp}.png`;
savedFilePath = path.join(screenshotDir, filename);
// Convert base64 to buffer and save
const buffer = Buffer.from(result.screenshot, 'base64');
await fs.writeFile(savedFilePath, buffer);
} catch (saveError) {
// Log error but don't fail the operation
console.error('Failed to save screenshot locally:', saveError);
}
}
// If saved locally and screenshot is large (>800KB), don't return the base64 data
const screenshotSize = Buffer.from(result.screenshot, 'base64').length;
const shouldReturnImage = !savedFilePath || screenshotSize < 800 * 1024; // 800KB threshold
Eif (shouldReturnImage) {
content.push({
type: 'image',
data: result.screenshot,
mimeType: 'image/png',
});
}
if (savedFilePath) {
const sizeInfo = !shouldReturnImage
? ` (${Math.round(screenshotSize / 1024)}KB - too large to display inline)`
: '';
content.push({
type: 'text',
text: `\n---\nScreenshot saved to: ${savedFilePath}${sizeInfo}`,
});
}
}
// PDF if available
if (result.pdf) {
content.push({
type: 'resource',
resource: {
uri: `data:application/pdf;name=${encodeURIComponent(new URL(String(options.url)).hostname)}.pdf;base64,${result.pdf}`,
mimeType: 'application/pdf',
blob: result.pdf,
},
});
}
// Metadata
if (result.metadata) {
content.push({
type: 'text',
text: `\n---\nMetadata: ${JSON.stringify(result.metadata, null, 2)}`,
});
}
// Links
if (result.links && (result.links.internal.length > 0 || result.links.external.length > 0)) {
content.push({
type: 'text',
text: `\n---\nLinks: Internal: ${result.links.internal.length}, External: ${result.links.external.length}`,
});
}
// JS execution results if available
if (result.js_execution_result && result.js_execution_result.results.length > 0) {
const jsResults = result.js_execution_result.results
.map((res: unknown, idx: number) => {
return `Result ${idx + 1}: ${JSON.stringify(res, null, 2)}`;
})
.join('\n');
content.push({
type: 'text',
text: `\n---\nJavaScript Execution Results:\n${jsResults}`,
});
}
return { content };
} catch (error) {
throw this.formatError(error, 'crawl');
}
}
}
|