Iyeoluwads/firecrawl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

WebScraper refactor into scrapeURL (#714)

Browse Source 
* feat: use strictNullChecking

* feat: switch logger to Winston

* feat(scrapeURL): first batch

* fix(scrapeURL): error swallow

* fix(scrapeURL): add timeout to EngineResultsTracker

* fix(scrapeURL): report unexpected error to sentry

* chore: remove unused modules

* feat(transfomers/coerce): warn when a format's response is missing

* feat(scrapeURL): feature flag priorities, engine quality sorting, PDF and DOCX support

* (add note)

* feat(scrapeURL): wip readme

* feat(scrapeURL): LLM extract

* feat(scrapeURL): better warnings

* fix(scrapeURL/engines/fire-engine;playwright): fix screenshot

* feat(scrapeURL): add forceEngine internal option

* feat(scrapeURL/engines): scrapingbee

* feat(scrapeURL/transformars): uploadScreenshot

* feat(scrapeURL): more intense tests

* bunch of stuff

* get rid of WebScraper (mostly)

* adapt batch scrape

* add staging deploy workflow

* fix yaml

* fix logger issues

* fix v1 test schema

* feat(scrapeURL/fire-engine/chrome-cdp): remove wait inserts on actions

* scrapeURL: v0 backwards compat

* logger fixes

* feat(scrapeurl): v0 returnOnlyUrls support

* fix(scrapeURL/v0): URL leniency

* fix(batch-scrape): ts non-nullable

* fix(scrapeURL/fire-engine/chromecdp): fix wait action

* fix(logger): remove error debug key

* feat(requests.http): use dotenv expression

* fix(scrapeURL/extractMetadata): extract custom metadata

* fix crawl option conversion

* feat(scrapeURL): Add retry logic to robustFetch

* fix(scrapeURL): crawl stuff

* fix(scrapeURL): LLM extract

* fix(scrapeURL/v0): search fix

* fix(tests/v0): grant larger response size to v0 crawl status

* feat(scrapeURL): basic fetch engine

* feat(scrapeURL): playwright engine

* feat(scrapeURL): add url-specific parameters

* Update readme and examples

* added e2e tests for most parameters. Still a few actions, location and iframes to be done.

* fixed type

* Nick:

* Update scrape.ts

* Update index.ts

* added actions and base64 check

* Nick: skipTls feature flag?

* 403

* todo

* todo

* fixes

* yeet headers from url specific params

* add warning when final engine has feature deficit

* expose engine results tracker for ScrapeEvents implementation

* ingest scrape events

* fixed some tests

* comment

* Update index.test.ts

* fixed rawHtml

* Update index.test.ts

* update comments

* move geolocation to global f-e option, fix removeBase64Images

* Nick:

* trim url-specific params

* Update index.ts

---------

Co-authored-by: Eric Ciarla <ericciarla@yahoo.com>
Co-authored-by: rafaelmmiller <8574157+rafaelmmiller@users.noreply.github.com>
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
This commit is contained in:
Gergő Móricz
2024-11-07 20:57:33 +01:00
committed by GitHub
parent ed5a0d3cf2
commit 8d467c8ca7
142 changed files with 4230 additions and 6334 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/api/src/__tests__/e2e_v1_withAuth/index.test.ts
+13 -13
View File
@@ -1,7 +1,7 @@
import request from "supertest";
import { configDotenv } from "dotenv";
import {
ScrapeRequest,
ScrapeRequestInput,
ScrapeResponseRequestTest,
} from "../../controllers/v1/types";
@@ -44,7 +44,7 @@ describe("E2E Tests for v1 API Routes", () => {
});
it.concurrent("should throw error for blocklisted URL", async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://facebook.com/fake-test",
};
@@ -73,7 +73,7 @@ describe("E2E Tests for v1 API Routes", () => {
it.concurrent(
"should return a successful response with a valid API key",
async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://roastmywebsite.ai",
};
@@ -125,7 +125,7 @@ describe("E2E Tests for v1 API Routes", () => {
it.concurrent(
"should return a successful response with a valid API key",
async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://arxiv.org/abs/2410.04840",
};
@@ -167,7 +167,7 @@ describe("E2E Tests for v1 API Routes", () => {
it.concurrent(
"should return a successful response with a valid API key and includeHtml set to true",
async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://roastmywebsite.ai",
formats: ["markdown", "html"],
};
@@ -194,7 +194,7 @@ describe("E2E Tests for v1 API Routes", () => {
30000
);
it.concurrent('should return a successful response for a valid scrape with PDF file', async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://arxiv.org/pdf/astro-ph/9301001.pdf"
// formats: ["markdown", "html"],
};
@@ -217,7 +217,7 @@ describe("E2E Tests for v1 API Routes", () => {
}, 60000);
it.concurrent('should return a successful response for a valid scrape with PDF file without explicit .pdf extension', async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://arxiv.org/pdf/astro-ph/9301001"
};
const response: ScrapeResponseRequestTest = await request(TEST_URL)
@@ -240,7 +240,7 @@ describe("E2E Tests for v1 API Routes", () => {
}, 60000);
it.concurrent("should return a successful response with a valid API key with removeTags option", async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://www.scrapethissite.com/",
onlyMainContent: false // default is true
};
@@ -261,7 +261,7 @@ describe("E2E Tests for v1 API Routes", () => {
expect(responseWithoutRemoveTags.body.data.markdown).toContain("[FAQ](/faq/)"); // .nav
expect(responseWithoutRemoveTags.body.data.markdown).toContain("Hartley Brody 2023"); // #footer
const scrapeRequestWithRemoveTags: ScrapeRequest = {
const scrapeRequestWithRemoveTags: ScrapeRequestInput = {
url: "https://www.scrapethissite.com/",
excludeTags: ['.nav', '#footer', 'strong'],
onlyMainContent: false // default is true
@@ -407,7 +407,7 @@ describe("E2E Tests for v1 API Routes", () => {
it.concurrent(
"should return a successful response with a valid API key and includeHtml set to true",
async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://roastmywebsite.ai",
formats: ["html","rawHtml"],
};
@@ -438,7 +438,7 @@ describe("E2E Tests for v1 API Routes", () => {
it.concurrent(
"should return a successful response with waitFor",
async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://ycombinator.com/companies",
formats: ["markdown"],
waitFor: 8000
@@ -471,7 +471,7 @@ describe("E2E Tests for v1 API Routes", () => {
it.concurrent(
"should return a successful response with a valid links on page",
async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://roastmywebsite.ai",
formats: ["links"],
};
@@ -672,7 +672,7 @@ describe("POST /v1/crawl", () => {
});
it.concurrent("should throw error for blocklisted URL", async () => {
const scrapeRequest: ScrapeRequest = {
const scrapeRequest: ScrapeRequestInput = {
url: "https://facebook.com/fake-test",
};