Merge pull request #947 from getmaxun/crawl-fix
fix(core): max depth crawling logic
This commit is contained in:
Karishma Shukla
@@ -706,7 +706,6 @@ export default class Interpreter extends EventEmitter {
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
if (this.options.debugChannel?.setActionType) {
|
||||
this.options.debugChannel.setActionType('crawl');
|
||||
}
|
||||
@@ -728,130 +727,141 @@ export default class Interpreter extends EventEmitter {
|
||||
const parsedBase = new URL(baseUrl);
|
||||
const baseDomain = parsedBase.hostname;
|
||||
|
||||
let discoveredUrls: string[] = [];
|
||||
interface RobotRules {
|
||||
disallowedPaths: string[];
|
||||
allowedPaths: string[];
|
||||
crawlDelay: number | null;
|
||||
}
|
||||
|
||||
if (crawlConfig.useSitemap) {
|
||||
this.log('Fetching sitemap URLs...', Level.LOG);
|
||||
let robotRules: RobotRules = {
|
||||
disallowedPaths: [],
|
||||
allowedPaths: [],
|
||||
crawlDelay: null
|
||||
};
|
||||
|
||||
if (crawlConfig.respectRobots) {
|
||||
this.log('Fetching robots.txt...', Level.LOG);
|
||||
try {
|
||||
const sitemapUrl = `${parsedBase.protocol}//${parsedBase.host}/sitemap.xml`;
|
||||
const robotsUrl = `${parsedBase.protocol}//${parsedBase.host}/robots.txt`;
|
||||
|
||||
const sitemapUrls = await page.evaluate((url) => {
|
||||
return new Promise<string[]>((resolve) => {
|
||||
const robotsContent = await page.evaluate((url) => {
|
||||
return new Promise<string>((resolve) => {
|
||||
const xhr = new XMLHttpRequest();
|
||||
xhr.open('GET', url, true);
|
||||
xhr.onload = function() {
|
||||
if (xhr.status === 200) {
|
||||
const text = xhr.responseText;
|
||||
const locMatches = text.match(/<loc>(.*?)<\/loc>/g) || [];
|
||||
const urls = locMatches.map(match => match.replace(/<\/?loc>/g, ''));
|
||||
resolve(urls);
|
||||
resolve(xhr.responseText);
|
||||
} else {
|
||||
resolve([]);
|
||||
resolve('');
|
||||
}
|
||||
};
|
||||
xhr.onerror = function() {
|
||||
resolve([]);
|
||||
resolve('');
|
||||
};
|
||||
xhr.send();
|
||||
});
|
||||
}, sitemapUrl);
|
||||
}, robotsUrl);
|
||||
|
||||
if (sitemapUrls.length > 0) {
|
||||
const nestedSitemaps = sitemapUrls.filter(url =>
|
||||
url.endsWith('/sitemap') || url.endsWith('sitemap.xml') || url.includes('/sitemap/')
|
||||
);
|
||||
const regularUrls = sitemapUrls.filter(url =>
|
||||
!url.endsWith('/sitemap') && !url.endsWith('sitemap.xml') && !url.includes('/sitemap/')
|
||||
);
|
||||
if (robotsContent) {
|
||||
const lines = robotsContent.split('\n');
|
||||
let isRelevantUserAgent = false;
|
||||
let foundSpecificUserAgent = false;
|
||||
|
||||
discoveredUrls.push(...regularUrls);
|
||||
this.log(`Found ${regularUrls.length} regular URLs from main sitemap`, Level.LOG);
|
||||
for (const line of lines) {
|
||||
const trimmedLine = line.trim().toLowerCase();
|
||||
|
||||
for (const nestedUrl of nestedSitemaps.slice(0, 10)) {
|
||||
try {
|
||||
this.log(`Fetching nested sitemap: ${nestedUrl}`, Level.LOG);
|
||||
const nestedUrls = await page.evaluate((url) => {
|
||||
return new Promise<string[]>((resolve) => {
|
||||
const xhr = new XMLHttpRequest();
|
||||
xhr.open('GET', url, true);
|
||||
xhr.onload = function() {
|
||||
if (xhr.status === 200) {
|
||||
const text = xhr.responseText;
|
||||
const locMatches = text.match(/<loc>(.*?)<\/loc>/g) || [];
|
||||
const urls = locMatches.map(match => match.replace(/<\/?loc>/g, ''));
|
||||
resolve(urls);
|
||||
if (trimmedLine.startsWith('#') || trimmedLine === '') {
|
||||
continue;
|
||||
}
|
||||
|
||||
const colonIndex = line.indexOf(':');
|
||||
if (colonIndex === -1) continue;
|
||||
|
||||
const directive = line.substring(0, colonIndex).trim().toLowerCase();
|
||||
const value = line.substring(colonIndex + 1).trim();
|
||||
|
||||
if (directive === 'user-agent') {
|
||||
const agent = value.toLowerCase();
|
||||
if (agent === '*' && !foundSpecificUserAgent) {
|
||||
isRelevantUserAgent = true;
|
||||
} else if (agent.includes('bot') || agent.includes('crawler') || agent.includes('spider')) {
|
||||
isRelevantUserAgent = true;
|
||||
foundSpecificUserAgent = true;
|
||||
} else {
|
||||
resolve([]);
|
||||
if (!foundSpecificUserAgent) {
|
||||
isRelevantUserAgent = false;
|
||||
}
|
||||
}
|
||||
} else if (isRelevantUserAgent) {
|
||||
if (directive === 'disallow' && value) {
|
||||
robotRules.disallowedPaths.push(value);
|
||||
} else if (directive === 'allow' && value) {
|
||||
robotRules.allowedPaths.push(value);
|
||||
} else if (directive === 'crawl-delay' && value) {
|
||||
const delay = parseFloat(value);
|
||||
if (!isNaN(delay) && delay > 0) {
|
||||
robotRules.crawlDelay = delay * 1000;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
this.log(`Robots.txt parsed: ${robotRules.disallowedPaths.length} disallowed paths, ${robotRules.allowedPaths.length} allowed paths, crawl-delay: ${robotRules.crawlDelay || 'none'}`, Level.LOG);
|
||||
} else {
|
||||
this.log('No robots.txt found or not accessible, proceeding without restrictions', Level.WARN);
|
||||
}
|
||||
} catch (error) {
|
||||
this.log(`Failed to fetch robots.txt: ${error.message}, proceeding without restrictions`, Level.WARN);
|
||||
}
|
||||
}
|
||||
|
||||
const isUrlAllowedByRobots = (url: string): boolean => {
|
||||
if (!crawlConfig.respectRobots) return true;
|
||||
|
||||
try {
|
||||
const urlObj = new URL(url);
|
||||
const pathname = urlObj.pathname;
|
||||
|
||||
for (const allowedPath of robotRules.allowedPaths) {
|
||||
if (allowedPath === pathname || pathname.startsWith(allowedPath)) {
|
||||
return true;
|
||||
}
|
||||
if (allowedPath.includes('*')) {
|
||||
const regex = new RegExp('^' + allowedPath.replace(/\*/g, '.*').replace(/\?/g, '.') + '$');
|
||||
if (regex.test(pathname)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for (const disallowedPath of robotRules.disallowedPaths) {
|
||||
if (disallowedPath === '/') {
|
||||
return false;
|
||||
}
|
||||
if (pathname.startsWith(disallowedPath)) {
|
||||
return false;
|
||||
}
|
||||
if (disallowedPath.includes('*')) {
|
||||
const regex = new RegExp('^' + disallowedPath.replace(/\*/g, '.*').replace(/\?/g, '.') + '$');
|
||||
if (regex.test(pathname)) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
if (disallowedPath.endsWith('$')) {
|
||||
const pattern = disallowedPath.slice(0, -1);
|
||||
if (pathname === pattern || pathname.endsWith(pattern)) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return true;
|
||||
} catch (error) {
|
||||
return true;
|
||||
}
|
||||
};
|
||||
xhr.onerror = function() {
|
||||
resolve([]);
|
||||
};
|
||||
xhr.send();
|
||||
});
|
||||
}, nestedUrl);
|
||||
|
||||
if (nestedUrls.length > 0) {
|
||||
discoveredUrls.push(...nestedUrls);
|
||||
this.log(`Found ${nestedUrls.length} URLs from nested sitemap ${nestedUrl}`, Level.LOG);
|
||||
}
|
||||
} catch (error) {
|
||||
this.log(`Failed to fetch nested sitemap ${nestedUrl}: ${error.message}`, Level.WARN);
|
||||
}
|
||||
}
|
||||
|
||||
this.log(`Total URLs from all sitemaps: ${discoveredUrls.length}`, Level.LOG);
|
||||
} else {
|
||||
this.log('No URLs found in sitemap or sitemap not available', Level.WARN);
|
||||
}
|
||||
} catch (error) {
|
||||
this.log(`Sitemap fetch failed: ${error.message}`, Level.WARN);
|
||||
}
|
||||
}
|
||||
|
||||
if (crawlConfig.followLinks) {
|
||||
this.log('Extracting links from current page...', Level.LOG);
|
||||
try {
|
||||
await page.waitForLoadState('load', { timeout: 15000 }).catch(() => {});
|
||||
|
||||
await page.waitForLoadState('networkidle', { timeout: 10000 }).catch(() => {
|
||||
this.log('Network did not become idle, continuing anyway', Level.WARN);
|
||||
});
|
||||
|
||||
await new Promise(resolve => setTimeout(resolve, 5000));
|
||||
|
||||
const anchorCount = await page.evaluate(() => {
|
||||
return document.querySelectorAll('a').length;
|
||||
});
|
||||
this.log(`Page has ${anchorCount} total anchor tags`, Level.LOG);
|
||||
|
||||
const pageLinks = await page.evaluate(() => {
|
||||
const links: string[] = [];
|
||||
const allAnchors = document.querySelectorAll('a');
|
||||
console.log('Total anchors found:', allAnchors.length);
|
||||
|
||||
for (let i = 0; i < allAnchors.length; i++) {
|
||||
const anchor = allAnchors[i] as HTMLAnchorElement;
|
||||
const href = anchor.getAttribute('href');
|
||||
const fullHref = anchor.href;
|
||||
|
||||
if (fullHref && (fullHref.startsWith('http://') || fullHref.startsWith('https://'))) {
|
||||
links.push(fullHref);
|
||||
}
|
||||
}
|
||||
|
||||
console.log('Links extracted:', links.length);
|
||||
return links;
|
||||
});
|
||||
|
||||
discoveredUrls.push(...pageLinks);
|
||||
this.log(`Found ${pageLinks.length} links from page`, Level.LOG);
|
||||
} catch (error) {
|
||||
this.log(`Link extraction failed: ${error.message}`, Level.WARN);
|
||||
}
|
||||
}
|
||||
|
||||
const filteredUrls = discoveredUrls.filter(url => {
|
||||
const isUrlAllowedByConfig = (url: string): boolean => {
|
||||
try {
|
||||
const urlObj = new URL(url);
|
||||
|
||||
@@ -865,16 +875,24 @@ export default class Interpreter extends EventEmitter {
|
||||
|
||||
if (crawlConfig.includePaths && crawlConfig.includePaths.length > 0) {
|
||||
const matches = crawlConfig.includePaths.some(pattern => {
|
||||
try {
|
||||
const regex = new RegExp(pattern);
|
||||
return regex.test(url);
|
||||
} catch {
|
||||
return url.includes(pattern);
|
||||
}
|
||||
});
|
||||
if (!matches) return false;
|
||||
}
|
||||
|
||||
if (crawlConfig.excludePaths && crawlConfig.excludePaths.length > 0) {
|
||||
const matches = crawlConfig.excludePaths.some(pattern => {
|
||||
try {
|
||||
const regex = new RegExp(pattern);
|
||||
return regex.test(url);
|
||||
} catch {
|
||||
return url.includes(pattern);
|
||||
}
|
||||
});
|
||||
if (matches) return false;
|
||||
}
|
||||
@@ -883,50 +901,42 @@ export default class Interpreter extends EventEmitter {
|
||||
} catch (error) {
|
||||
return false;
|
||||
}
|
||||
});
|
||||
};
|
||||
|
||||
const uniqueUrls = Array.from(new Set(filteredUrls.map(url => {
|
||||
const normalizeUrl = (url: string): string => {
|
||||
return url.replace(/#.*$/, '').replace(/\/$/, '');
|
||||
})));
|
||||
};
|
||||
|
||||
const basePathname = parsedBase.pathname;
|
||||
const prioritizedUrls = uniqueUrls.sort((a, b) => {
|
||||
const extractLinksFromPage = async (): Promise<string[]> => {
|
||||
try {
|
||||
const aUrl = new URL(a);
|
||||
const bUrl = new URL(b);
|
||||
const aMatchesBase = aUrl.pathname.startsWith(basePathname);
|
||||
const bMatchesBase = bUrl.pathname.startsWith(basePathname);
|
||||
await page.waitForLoadState('load', { timeout: 15000 }).catch(() => {});
|
||||
await page.waitForLoadState('networkidle', { timeout: 10000 }).catch(() => {});
|
||||
await new Promise(resolve => setTimeout(resolve, 1000));
|
||||
|
||||
if (aMatchesBase && !bMatchesBase) return -1;
|
||||
if (!aMatchesBase && bMatchesBase) return 1;
|
||||
const pageLinks = await page.evaluate(() => {
|
||||
const links: string[] = [];
|
||||
const allAnchors = document.querySelectorAll('a');
|
||||
|
||||
return 0;
|
||||
} catch (error) {
|
||||
return 0;
|
||||
for (let i = 0; i < allAnchors.length; i++) {
|
||||
const anchor = allAnchors[i] as HTMLAnchorElement;
|
||||
const fullHref = anchor.href;
|
||||
|
||||
if (fullHref && (fullHref.startsWith('http://') || fullHref.startsWith('https://'))) {
|
||||
links.push(fullHref);
|
||||
}
|
||||
}
|
||||
|
||||
return links;
|
||||
});
|
||||
|
||||
const finalUrls = prioritizedUrls.slice(0, crawlConfig.limit);
|
||||
|
||||
this.log(`Crawl discovered ${finalUrls.length} URLs (from ${discoveredUrls.length} total)`, Level.LOG);
|
||||
|
||||
this.log(`Starting to scrape content from ${finalUrls.length} discovered URLs...`, Level.LOG);
|
||||
const crawlResults = [];
|
||||
|
||||
for (let i = 0; i < finalUrls.length; i++) {
|
||||
const url = finalUrls[i];
|
||||
try {
|
||||
this.log(`[${i + 1}/${finalUrls.length}] Scraping: ${url}`, Level.LOG);
|
||||
|
||||
await page.goto(url, {
|
||||
waitUntil: 'domcontentloaded',
|
||||
timeout: 30000
|
||||
}).catch(() => {
|
||||
this.log(`Failed to navigate to ${url}, skipping...`, Level.WARN);
|
||||
});
|
||||
|
||||
await page.waitForLoadState('load', { timeout: 10000 }).catch(() => {});
|
||||
return pageLinks;
|
||||
} catch (error) {
|
||||
this.log(`Link extraction failed: ${error.message}`, Level.WARN);
|
||||
return [];
|
||||
}
|
||||
};
|
||||
|
||||
const scrapePageContent = async (url: string) => {
|
||||
const pageData = await page.evaluate(() => {
|
||||
const getMeta = (name: string) => {
|
||||
const meta = document.querySelector(`meta[name="${name}"], meta[property="${name}"]`);
|
||||
@@ -973,32 +983,197 @@ export default class Interpreter extends EventEmitter {
|
||||
};
|
||||
});
|
||||
|
||||
crawlResults.push({
|
||||
return {
|
||||
metadata: {
|
||||
...pageData.metadata,
|
||||
url: url,
|
||||
sourceURL: url
|
||||
},
|
||||
} as Record<string, any>,
|
||||
html: pageData.html,
|
||||
text: pageData.text,
|
||||
links: pageData.links,
|
||||
wordCount: pageData.wordCount,
|
||||
scrapedAt: new Date().toISOString()
|
||||
};
|
||||
};
|
||||
|
||||
const visitedUrls = new Set<string>();
|
||||
const crawlResults: any[] = [];
|
||||
|
||||
interface CrawlQueueItem {
|
||||
url: string;
|
||||
depth: number;
|
||||
}
|
||||
|
||||
const crawlQueue: CrawlQueueItem[] = [];
|
||||
|
||||
const normalizedBaseUrl = normalizeUrl(baseUrl);
|
||||
visitedUrls.add(normalizedBaseUrl);
|
||||
crawlQueue.push({ url: baseUrl, depth: 0 });
|
||||
|
||||
this.log(`Starting breadth-first crawl with maxDepth: ${crawlConfig.maxDepth}, limit: ${crawlConfig.limit}`, Level.LOG);
|
||||
|
||||
if (crawlConfig.useSitemap) {
|
||||
this.log('Fetching sitemap URLs...', Level.LOG);
|
||||
try {
|
||||
const sitemapUrl = `${parsedBase.protocol}//${parsedBase.host}/sitemap.xml`;
|
||||
|
||||
const sitemapUrls = await page.evaluate((url) => {
|
||||
return new Promise<string[]>((resolve) => {
|
||||
const xhr = new XMLHttpRequest();
|
||||
xhr.open('GET', url, true);
|
||||
xhr.onload = function() {
|
||||
if (xhr.status === 200) {
|
||||
const text = xhr.responseText;
|
||||
const locMatches = text.match(/<loc>(.*?)<\/loc>/g) || [];
|
||||
const urls = locMatches.map(match => match.replace(/<\/?loc>/g, ''));
|
||||
resolve(urls);
|
||||
} else {
|
||||
resolve([]);
|
||||
}
|
||||
};
|
||||
xhr.onerror = function() {
|
||||
resolve([]);
|
||||
};
|
||||
xhr.send();
|
||||
});
|
||||
}, sitemapUrl);
|
||||
|
||||
if (sitemapUrls.length > 0) {
|
||||
const nestedSitemaps = sitemapUrls.filter(url =>
|
||||
url.endsWith('/sitemap') || url.endsWith('sitemap.xml') || url.includes('/sitemap/')
|
||||
);
|
||||
const regularUrls = sitemapUrls.filter(url =>
|
||||
!url.endsWith('/sitemap') && !url.endsWith('sitemap.xml') && !url.includes('/sitemap/')
|
||||
);
|
||||
|
||||
for (const sitemapPageUrl of regularUrls) {
|
||||
const normalized = normalizeUrl(sitemapPageUrl);
|
||||
if (!visitedUrls.has(normalized) && isUrlAllowedByConfig(sitemapPageUrl) && isUrlAllowedByRobots(sitemapPageUrl)) {
|
||||
visitedUrls.add(normalized);
|
||||
crawlQueue.push({ url: sitemapPageUrl, depth: 1 });
|
||||
}
|
||||
}
|
||||
|
||||
this.log(`Found ${regularUrls.length} regular URLs from main sitemap`, Level.LOG);
|
||||
|
||||
for (const nestedUrl of nestedSitemaps.slice(0, 10)) {
|
||||
try {
|
||||
this.log(`Fetching nested sitemap: ${nestedUrl}`, Level.LOG);
|
||||
const nestedUrls = await page.evaluate((url) => {
|
||||
return new Promise<string[]>((resolve) => {
|
||||
const xhr = new XMLHttpRequest();
|
||||
xhr.open('GET', url, true);
|
||||
xhr.onload = function() {
|
||||
if (xhr.status === 200) {
|
||||
const text = xhr.responseText;
|
||||
const locMatches = text.match(/<loc>(.*?)<\/loc>/g) || [];
|
||||
const urls = locMatches.map(match => match.replace(/<\/?loc>/g, ''));
|
||||
resolve(urls);
|
||||
} else {
|
||||
resolve([]);
|
||||
}
|
||||
};
|
||||
xhr.onerror = function() {
|
||||
resolve([]);
|
||||
};
|
||||
xhr.send();
|
||||
});
|
||||
}, nestedUrl);
|
||||
|
||||
for (const nestedPageUrl of nestedUrls) {
|
||||
const normalized = normalizeUrl(nestedPageUrl);
|
||||
if (!visitedUrls.has(normalized) && isUrlAllowedByConfig(nestedPageUrl) && isUrlAllowedByRobots(nestedPageUrl)) {
|
||||
visitedUrls.add(normalized);
|
||||
crawlQueue.push({ url: nestedPageUrl, depth: 1 });
|
||||
}
|
||||
}
|
||||
|
||||
this.log(`Found ${nestedUrls.length} URLs from nested sitemap ${nestedUrl}`, Level.LOG);
|
||||
} catch (error) {
|
||||
this.log(`Failed to fetch nested sitemap ${nestedUrl}: ${error.message}`, Level.WARN);
|
||||
}
|
||||
}
|
||||
|
||||
this.log(`Total URLs queued from sitemaps: ${crawlQueue.length - 1}`, Level.LOG);
|
||||
} else {
|
||||
this.log('No URLs found in sitemap or sitemap not available', Level.WARN);
|
||||
}
|
||||
} catch (error) {
|
||||
this.log(`Sitemap fetch failed: ${error.message}`, Level.WARN);
|
||||
}
|
||||
}
|
||||
|
||||
let processedCount = 0;
|
||||
|
||||
while (crawlQueue.length > 0 && crawlResults.length < crawlConfig.limit) {
|
||||
if (this.isAborted) {
|
||||
this.log('Workflow aborted during crawl', Level.WARN);
|
||||
break;
|
||||
}
|
||||
|
||||
const { url, depth } = crawlQueue.shift()!;
|
||||
processedCount++;
|
||||
|
||||
this.log(`[${crawlResults.length + 1}/${crawlConfig.limit}] Crawling (depth ${depth}): ${url}`, Level.LOG);
|
||||
|
||||
try {
|
||||
if (robotRules.crawlDelay && crawlResults.length > 0) {
|
||||
this.log(`Applying crawl delay: ${robotRules.crawlDelay}ms`, Level.LOG);
|
||||
await new Promise(resolve => setTimeout(resolve, robotRules.crawlDelay!));
|
||||
}
|
||||
|
||||
await page.goto(url, {
|
||||
waitUntil: 'domcontentloaded',
|
||||
timeout: 30000
|
||||
}).catch((err) => {
|
||||
throw new Error(`Navigation failed: ${err.message}`);
|
||||
});
|
||||
|
||||
this.log(`✓ Scraped ${url} (${pageData.wordCount} words)`, Level.LOG);
|
||||
await page.waitForLoadState('load', { timeout: 10000 }).catch(() => {});
|
||||
|
||||
const pageResult = await scrapePageContent(url);
|
||||
pageResult.metadata.depth = depth;
|
||||
crawlResults.push(pageResult);
|
||||
|
||||
this.log(`✓ Scraped ${url} (${pageResult.wordCount} words, depth ${depth})`, Level.LOG);
|
||||
|
||||
if (crawlConfig.followLinks && depth < crawlConfig.maxDepth) {
|
||||
const newLinks = await extractLinksFromPage();
|
||||
let addedCount = 0;
|
||||
|
||||
for (const link of newLinks) {
|
||||
const normalized = normalizeUrl(link);
|
||||
|
||||
if (!visitedUrls.has(normalized) &&
|
||||
isUrlAllowedByConfig(link) &&
|
||||
isUrlAllowedByRobots(link)) {
|
||||
visitedUrls.add(normalized);
|
||||
crawlQueue.push({ url: link, depth: depth + 1 });
|
||||
addedCount++;
|
||||
}
|
||||
}
|
||||
|
||||
if (addedCount > 0) {
|
||||
this.log(`Added ${addedCount} new URLs to queue at depth ${depth + 1}`, Level.LOG);
|
||||
}
|
||||
}
|
||||
|
||||
} catch (error) {
|
||||
this.log(`Failed to scrape ${url}: ${error.message}`, Level.WARN);
|
||||
this.log(`Failed to crawl ${url}: ${error.message}`, Level.WARN);
|
||||
crawlResults.push({
|
||||
metadata: {
|
||||
url: url,
|
||||
sourceURL: url,
|
||||
depth: depth
|
||||
},
|
||||
error: error.message,
|
||||
scrapedAt: new Date().toISOString()
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
this.log(`Successfully scraped ${crawlResults.length} pages`, Level.LOG);
|
||||
this.log(`Crawl completed: ${crawlResults.length} pages scraped (${processedCount} URLs processed, ${visitedUrls.size} URLs discovered)`, Level.LOG);
|
||||
|
||||
const actionType = "crawl";
|
||||
const actionName = "Crawl Results";
|
||||
@@ -1031,8 +1206,6 @@ export default class Interpreter extends EventEmitter {
|
||||
provider?: 'duckduckgo';
|
||||
filters?: {
|
||||
timeRange?: 'day' | 'week' | 'month' | 'year';
|
||||
location?: string;
|
||||
lang?: string;
|
||||
};
|
||||
mode: 'discover' | 'scrape';
|
||||
}) => {
|
||||
|
||||
Reference in New Issue
Block a user