Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug] Fixing /crawl limit #143

Merged
merged 3 commits into from
May 22, 2024
Merged

[Bug] Fixing /crawl limit #143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bc6b929
[Bug] Fixing /crawl limit
rafaelsideguide May 10, 2024
f4a3469
Merge branch 'main' into bug/crawl-limit
rafaelsideguide May 22, 2024
4dfc371
Update index.test.ts
rafaelsideguide May 22, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion apps/api/src/__tests__/e2e_withAuth/index.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -266,7 +266,7 @@ describe("E2E Tests for API Routes", () => {
urls.forEach((url: string) => {
expect(url.startsWith("https://wwww.mendable.ai/blog/")).toBeFalsy();
});
}, 60000); // 60 seconds
}, 90000); // 90 seconds

it("should return a successful response with a valid API key and limit to 3", async () => {
const crawlResponse = await request(TEST_URL)
Expand Down
8 changes: 4 additions & 4 deletions apps/api/src/scraper/WebScraper/crawler.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ export class WebCrawler {
initialUrl,
includes,
excludes,
maxCrawledLinks,
maxCrawledLinks = 10000,
limit = 10000,
generateImgAltText = false,
maxCrawledDepth = 10,
Expand Down Expand Up @@ -152,7 +152,7 @@ export class WebCrawler {
inProgress?: (progress: Progress) => void,
): Promise<{ url: string, html: string }[]> {
const queue = async.queue(async (task: string, callback) => {
if (this.crawledUrls.size >= this.maxCrawledLinks) {
if (this.crawledUrls.size >= Math.min(this.maxCrawledLinks, this.limit)) {
if (callback && typeof callback === "function") {
callback();
}
Expand All @@ -176,14 +176,14 @@ export class WebCrawler {
if (inProgress && newUrls.length > 0) {
inProgress({
current: this.crawledUrls.size,
total: this.maxCrawledLinks,
total: Math.min(this.maxCrawledLinks, this.limit),
status: "SCRAPING",
currentDocumentUrl: newUrls[newUrls.length - 1].url,
});
} else if (inProgress) {
inProgress({
current: this.crawledUrls.size,
total: this.maxCrawledLinks,
total: Math.min(this.maxCrawledLinks, this.limit),
status: "SCRAPING",
currentDocumentUrl: task,
});
Expand Down
Loading