Spaces:
Paused
Paused
File size: 18,049 Bytes
0e759d2 |
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 |
import "dotenv/config";
process.env.ENV = "test";
import { scrapeURL } from ".";
import { scrapeOptions } from "../../controllers/v1/types";
import { Engine } from "./engines";
const testEngines: (Engine | undefined)[] = [
undefined,
"fire-engine;chrome-cdp",
"fire-engine;playwright",
"fire-engine;tlsclient",
"scrapingbee",
"scrapingbeeLoad",
"fetch",
];
const testEnginesScreenshot: (Engine | undefined)[] = [
undefined,
"fire-engine;chrome-cdp",
"fire-engine;playwright",
"scrapingbee",
"scrapingbeeLoad",
];
describe("Standalone scrapeURL tests", () => {
describe.each(testEngines)("Engine %s", (forceEngine: Engine | undefined) => {
it("Basic scrape", async () => {
const out = await scrapeURL(
"test:scrape-basic",
"https://www.roastmywebsite.ai/",
scrapeOptions.parse({}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).not.toHaveProperty("content");
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document).not.toHaveProperty("html");
expect(out.document.markdown).toContain("_Roast_");
expect(out.document.metadata.error).toBeUndefined();
expect(out.document.metadata.title).toBe("Roast My Website");
expect(out.document.metadata.description).toBe(
"Welcome to Roast My Website, the ultimate tool for putting your website through the wringer! This repository harnesses the power of Firecrawl to scrape and capture screenshots of websites, and then unleashes the latest LLM vision models to mercilessly roast them. 🌶️",
);
expect(out.document.metadata.keywords).toBe(
"Roast My Website,Roast,Website,GitHub,Firecrawl",
);
expect(out.document.metadata.robots).toBe("follow, index");
expect(out.document.metadata.ogTitle).toBe("Roast My Website");
expect(out.document.metadata.ogDescription).toBe(
"Welcome to Roast My Website, the ultimate tool for putting your website through the wringer! This repository harnesses the power of Firecrawl to scrape and capture screenshots of websites, and then unleashes the latest LLM vision models to mercilessly roast them. 🌶️",
);
expect(out.document.metadata.ogUrl).toBe(
"https://www.roastmywebsite.ai",
);
expect(out.document.metadata.ogImage).toBe(
"https://www.roastmywebsite.ai/og.png",
);
expect(out.document.metadata.ogLocaleAlternate).toStrictEqual([]);
expect(out.document.metadata.ogSiteName).toBe("Roast My Website");
expect(out.document.metadata.sourceURL).toBe(
"https://www.roastmywebsite.ai/",
);
expect(out.document.metadata.statusCode).toBe(200);
}
}, 30000);
it("Scrape with formats markdown and html", async () => {
const out = await scrapeURL(
"test:scrape-formats-markdown-html",
"https://roastmywebsite.ai",
scrapeOptions.parse({
formats: ["markdown", "html"],
}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("html");
expect(out.document).toHaveProperty("metadata");
expect(out.document.markdown).toContain("_Roast_");
expect(out.document.html).toContain("<h1");
expect(out.document.metadata.statusCode).toBe(200);
expect(out.document.metadata.error).toBeUndefined();
}
}, 30000);
it("Scrape with onlyMainContent disabled", async () => {
const out = await scrapeURL(
"test:scrape-onlyMainContent-false",
"https://www.scrapethissite.com/",
scrapeOptions.parse({
onlyMainContent: false,
}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document).not.toHaveProperty("html");
expect(out.document.markdown).toContain("[FAQ](/faq/)"); // .nav
expect(out.document.markdown).toContain("Hartley Brody 2023"); // #footer
}
}, 30000);
it("Scrape with excludeTags", async () => {
const out = await scrapeURL(
"test:scrape-excludeTags",
"https://www.scrapethissite.com/",
scrapeOptions.parse({
onlyMainContent: false,
excludeTags: [".nav", "#footer", "strong"],
}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document).not.toHaveProperty("html");
expect(out.document.markdown).not.toContain("Hartley Brody 2023");
expect(out.document.markdown).not.toContain("[FAQ](/faq/)");
}
}, 30000);
it("Scrape of a page with 400 status code", async () => {
const out = await scrapeURL(
"test:scrape-400",
"https://httpstat.us/400",
scrapeOptions.parse({}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.statusCode).toBe(400);
}
}, 30000);
it("Scrape of a page with 401 status code", async () => {
const out = await scrapeURL(
"test:scrape-401",
"https://httpstat.us/401",
scrapeOptions.parse({}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.statusCode).toBe(401);
}
}, 30000);
it("Scrape of a page with 403 status code", async () => {
const out = await scrapeURL(
"test:scrape-403",
"https://httpstat.us/403",
scrapeOptions.parse({}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.statusCode).toBe(403);
}
}, 30000);
it("Scrape of a page with 404 status code", async () => {
const out = await scrapeURL(
"test:scrape-404",
"https://httpstat.us/404",
scrapeOptions.parse({}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.statusCode).toBe(404);
}
}, 30000);
it("Scrape of a page with 405 status code", async () => {
const out = await scrapeURL(
"test:scrape-405",
"https://httpstat.us/405",
scrapeOptions.parse({}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.statusCode).toBe(405);
}
}, 30000);
it("Scrape of a page with 500 status code", async () => {
const out = await scrapeURL(
"test:scrape-500",
"https://httpstat.us/500",
scrapeOptions.parse({}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.statusCode).toBe(500);
}
}, 30000);
it("Scrape a redirected page", async () => {
const out = await scrapeURL(
"test:scrape-redirect",
"https://scrapethissite.com/",
scrapeOptions.parse({}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document.markdown).toContain("Explore Sandbox");
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.sourceURL).toBe(
"https://scrapethissite.com/",
);
expect(out.document.metadata.url).toBe(
"https://www.scrapethissite.com/",
);
expect(out.document.metadata.statusCode).toBe(200);
expect(out.document.metadata.error).toBeUndefined();
}
}, 30000);
});
describe.each(testEnginesScreenshot)(
"Screenshot on engine %s",
(forceEngine: Engine | undefined) => {
it("Scrape with screenshot", async () => {
const out = await scrapeURL(
"test:scrape-screenshot",
"https://www.scrapethissite.com/",
scrapeOptions.parse({
formats: ["screenshot"],
}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("screenshot");
expect(typeof out.document.screenshot).toBe("string");
expect(
out.document.screenshot!.startsWith(
"https://service.firecrawl.dev/storage/v1/object/public/media/",
),
);
// TODO: attempt to fetch screenshot
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.statusCode).toBe(200);
expect(out.document.metadata.error).toBeUndefined();
}
}, 30000);
it("Scrape with full-page screenshot", async () => {
const out = await scrapeURL(
"test:scrape-screenshot-fullPage",
"https://www.scrapethissite.com/",
scrapeOptions.parse({
formats: ["screenshot@fullPage"],
}),
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("screenshot");
expect(typeof out.document.screenshot).toBe("string");
expect(
out.document.screenshot!.startsWith(
"https://service.firecrawl.dev/storage/v1/object/public/media/",
),
);
// TODO: attempt to fetch screenshot
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.statusCode).toBe(200);
expect(out.document.metadata.error).toBeUndefined();
}
}, 30000);
},
);
it("Scrape of a PDF file", async () => {
const out = await scrapeURL(
"test:scrape-pdf",
"https://arxiv.org/pdf/astro-ph/9301001.pdf",
scrapeOptions.parse({}),
{ teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("metadata");
expect(out.document.markdown).toContain("Broad Line Radio Galaxy");
expect(out.document.metadata.statusCode).toBe(200);
expect(out.document.metadata.error).toBeUndefined();
}
}, 60000);
it("Scrape a DOCX file", async () => {
const out = await scrapeURL(
"test:scrape-docx",
"https://nvca.org/wp-content/uploads/2019/06/NVCA-Model-Document-Stock-Purchase-Agreement.docx",
scrapeOptions.parse({}),
{ teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("metadata");
expect(out.document.markdown).toContain(
"SERIES A PREFERRED STOCK PURCHASE AGREEMENT",
);
expect(out.document.metadata.statusCode).toBe(200);
expect(out.document.metadata.error).toBeUndefined();
}
}, 60000);
it("LLM extract with prompt and schema", async () => {
const out = await scrapeURL(
"test:llm-extract-prompt-schema",
"https://firecrawl.dev",
scrapeOptions.parse({
formats: ["extract"],
extract: {
prompt:
"Based on the information on the page, find what the company's mission is and whether it supports SSO, and whether it is open source",
schema: {
type: "object",
properties: {
company_mission: { type: "string" },
supports_sso: { type: "boolean" },
is_open_source: { type: "boolean" },
},
required: ["company_mission", "supports_sso", "is_open_source"],
additionalProperties: false,
},
},
}),
{ teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("extract");
expect(out.document.extract).toHaveProperty("company_mission");
expect(out.document.extract).toHaveProperty("supports_sso");
expect(out.document.extract).toHaveProperty("is_open_source");
expect(typeof out.document.extract.company_mission).toBe("string");
expect(out.document.extract.supports_sso).toBe(false);
expect(out.document.extract.is_open_source).toBe(true);
}
}, 120000);
it("LLM extract with schema only", async () => {
const out = await scrapeURL(
"test:llm-extract-schema",
"https://firecrawl.dev",
scrapeOptions.parse({
formats: ["extract"],
extract: {
schema: {
type: "object",
properties: {
company_mission: { type: "string" },
supports_sso: { type: "boolean" },
is_open_source: { type: "boolean" },
},
required: ["company_mission", "supports_sso", "is_open_source"],
additionalProperties: false,
},
},
}),
{ teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("extract");
expect(out.document.extract).toHaveProperty("company_mission");
expect(out.document.extract).toHaveProperty("supports_sso");
expect(out.document.extract).toHaveProperty("is_open_source");
expect(typeof out.document.extract.company_mission).toBe("string");
expect(out.document.extract.supports_sso).toBe(false);
expect(out.document.extract.is_open_source).toBe(true);
}
}, 120000);
test.concurrent.each(new Array(100).fill(0).map((_, i) => i))(
"Concurrent scrape #%i",
async (i) => {
const url = "https://www.scrapethissite.com/?i=" + i;
const id = "test:concurrent:" + url;
const out = await scrapeURL(id, url, scrapeOptions.parse({}), { teamId: "test" });
const replacer = (key: string, value: any) => {
if (value instanceof Error) {
return {
...value,
message: value.message,
name: value.name,
cause: value.cause,
stack: value.stack,
};
} else {
return value;
}
};
// verify that log collection works properly while concurrency is happening
// expect(out.logs.length).toBeGreaterThan(0);
const weirdLogs = out.logs.filter((x) => x.scrapeId !== id);
if (weirdLogs.length > 0) {
console.warn(JSON.stringify(weirdLogs, replacer));
}
expect(weirdLogs.length).toBe(0);
if (!out.success) console.error(JSON.stringify(out, replacer));
expect(out.success).toBe(true);
if (out.success) {
expect(out.document.warning).toBeUndefined();
expect(out.document).toHaveProperty("markdown");
expect(out.document).toHaveProperty("metadata");
expect(out.document.metadata.error).toBeUndefined();
expect(out.document.metadata.statusCode).toBe(200);
}
},
30000,
);
});
|