Spaces:
Sleeping
Sleeping
File size: 10,022 Bytes
097eaf0 | 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 | import { Request, Response } from "express";
import { checkTeamCredits } from "../../../src/services/billing/credit_billing";
import { authenticateUser } from "../auth";
import { RateLimiterMode } from "../../../src/types";
import { addScrapeJob } from "../../../src/services/queue-jobs";
import { isUrlBlocked } from "../../../src/scraper/WebScraper/utils/blocklist";
import { validateIdempotencyKey } from "../../../src/services/idempotency/validate";
import { createIdempotencyKey } from "../../../src/services/idempotency/create";
import {
defaultCrawlPageOptions,
defaultCrawlerOptions,
defaultOrigin,
} from "../../../src/lib/default-values";
import { v7 as uuidv7 } from "uuid";
import { logger } from "../../../src/lib/logger";
import {
addCrawlJob,
addCrawlJobs,
crawlToCrawler,
finishCrawlKickoff,
lockURL,
lockURLs,
markCrawlActive,
saveCrawl,
StoredCrawl,
} from "../../../src/lib/crawl-redis";
import { redisEvictConnection } from "../../../src/services/redis";
import { checkAndUpdateURL } from "../../../src/lib/validateUrl";
import * as Sentry from "@sentry/node";
import { getJobPriority } from "../../lib/job-priority";
import { url as urlSchema } from "../v1/types";
import { ZodError } from "zod";
import { UNSUPPORTED_SITE_MESSAGE } from "../../lib/strings";
import { fromV0ScrapeOptions } from "../v2/types";
import { isSelfHosted } from "../../lib/deployment";
import { crawlGroup } from "../../services/worker/nuq";
import { logRequest } from "../../services/logging/log_job";
import { getScrapeZDR } from "../../lib/zdr-helpers";
export async function crawlController(req: Request, res: Response) {
try {
const auth = await authenticateUser(req, res, RateLimiterMode.Crawl);
if (!auth.success) {
return res.status(auth.status).json({ error: auth.error });
}
const { team_id, chunk } = auth;
if (getScrapeZDR(chunk?.flags) === "forced") {
return res.status(400).json({
error:
"Your team has zero data retention enabled. This is not supported on the v0 API. Please update your code to use the v1 API.",
});
}
const id = uuidv7();
await logRequest({
id,
kind: "crawl",
api_version: "v0",
team_id,
origin: req.body.origin ?? "api",
integration: req.body.integration,
target_hint: req.body.url ?? "",
zeroDataRetention: false, // not supported on v0
api_key_id: chunk?.api_key_id ?? null,
});
redisEvictConnection.sadd("teams_using_v0", team_id).catch(error =>
logger.error("Failed to add team to teams_using_v0", {
error,
team_id,
}),
);
redisEvictConnection
.sadd("teams_using_v0:" + team_id, "crawl:" + id)
.catch(error =>
logger.error("Failed to add team to teams_using_v0 (2)", {
error,
team_id,
}),
);
if (req.headers["x-idempotency-key"]) {
const isIdempotencyValid = await validateIdempotencyKey(req);
if (!isIdempotencyValid) {
return res.status(409).json({ error: "Idempotency key already used" });
}
try {
createIdempotencyKey(req);
} catch (error) {
logger.error(error);
return res.status(500).json({ error: error.message });
}
}
const crawlerOptions = {
...defaultCrawlerOptions,
...req.body.crawlerOptions,
};
const pageOptions = { ...defaultCrawlPageOptions, ...req.body.pageOptions };
if (Array.isArray(crawlerOptions.includes)) {
for (const x of crawlerOptions.includes) {
try {
new RegExp(x);
} catch (e) {
return res.status(400).json({ error: e.message });
}
}
}
if (Array.isArray(crawlerOptions.excludes)) {
for (const x of crawlerOptions.excludes) {
try {
new RegExp(x);
} catch (e) {
return res.status(400).json({ error: e.message });
}
}
}
const limitCheck = req.body?.crawlerOptions?.limit ?? 1;
const {
success: creditsCheckSuccess,
message: creditsCheckMessage,
remainingCredits,
} = await checkTeamCredits(chunk, team_id, limitCheck);
if (!creditsCheckSuccess) {
return res.status(402).json({
error: isSelfHosted()
? "Insufficient credits. You may be requesting with a higher limit than the amount of credits you have left. Please check your server configuration."
: "Insufficient credits. You may be requesting with a higher limit than the amount of credits you have left. If not, upgrade your plan at https://firecrawl.dev/pricing or contact us at help@firecrawl.com",
});
}
// TODO: need to do this to v1
crawlerOptions.limit = Math.min(remainingCredits, crawlerOptions.limit);
let url = urlSchema.parse(req.body.url);
if (!url) {
return res.status(400).json({ error: "Url is required" });
}
if (typeof url !== "string") {
return res.status(400).json({ error: "URL must be a string" });
}
try {
url = checkAndUpdateURL(url).url;
} catch (e) {
return res
.status(e instanceof Error && e.message === "Invalid URL" ? 400 : 500)
.json({ error: e.message ?? e });
}
if (
isUrlBlocked(url, auth.chunk?.flags ?? null, {
team_id: auth.chunk?.team_id ?? team_id,
origin: req.body?.origin ?? null,
})
) {
return res.status(403).json({
error: UNSUPPORTED_SITE_MESSAGE,
});
}
// if (mode === "single_urls" && !url.includes(",")) { // NOTE: do we need this?
// try {
// const a = new WebScraperDataProvider();
// await a.setOptions({
// jobId: uuidv7(),
// mode: "single_urls",
// urls: [url],
// crawlerOptions: { ...crawlerOptions, returnOnlyUrls: true },
// pageOptions: pageOptions,
// });
// const docs = await a.getDocuments(false, (progress) => {
// job.updateProgress({
// current: progress.current,
// total: progress.total,
// current_step: "SCRAPING",
// current_url: progress.currentDocumentUrl,
// });
// });
// return res.json({
// success: true,
// documents: docs,
// });
// } catch (error) {
// logger.error(error);
// return res.status(500).json({ error: error.message });
// }
// }
const { scrapeOptions, internalOptions } = fromV0ScrapeOptions(
pageOptions,
undefined,
undefined,
team_id,
);
internalOptions.disableSmartWaitCache = true; // NOTE: smart wait disabled for crawls to ensure contentful scrape, speed does not matter
internalOptions.saveScrapeResultToGCS = process.env
.GCS_FIRE_ENGINE_BUCKET_NAME
? true
: false;
delete (scrapeOptions as any).timeout;
const sc: StoredCrawl = {
originUrl: url,
crawlerOptions,
scrapeOptions,
internalOptions,
team_id,
createdAt: Date.now(),
};
const crawler = crawlToCrawler(id, sc, auth.chunk?.flags ?? null);
try {
sc.robots = await crawler.getRobotsTxt();
} catch (_) {}
await crawlGroup.addGroup(
id,
sc.team_id,
(chunk?.flags?.crawlTtlHours ?? 24) * 60 * 60 * 1000,
);
await saveCrawl(id, sc);
await markCrawlActive(id);
await finishCrawlKickoff(id);
const sitemap = sc.crawlerOptions.ignoreSitemap
? 0
: await crawler.tryGetSitemap(async urls => {
if (urls.length === 0) return;
let jobPriority = await getJobPriority({
team_id,
basePriority: 21,
});
const billing = { endpoint: "crawl" as const, jobId: id };
const jobs = urls.map(url => {
const uuid = uuidv7();
return {
jobId: uuid,
data: {
url,
mode: "single_urls" as const,
crawlerOptions,
scrapeOptions,
internalOptions,
team_id,
origin: req.body.origin ?? defaultOrigin,
integration: req.body.integration,
billing,
crawl_id: id,
sitemapped: true,
zeroDataRetention: false, // not supported on v0
apiKeyId: chunk?.api_key_id ?? null,
},
priority: jobPriority,
};
});
await lockURLs(
id,
sc,
jobs.map(x => x.data.url),
logger,
);
await addCrawlJobs(
id,
jobs.map(x => x.jobId),
logger,
);
for (const job of jobs) {
// add with sentry instrumentation
await addScrapeJob(job.data, job.jobId, job.priority);
}
});
if (sitemap === 0) {
await lockURL(id, sc, url);
// Not needed, first one should be 15.
// const jobPriority = await getJobPriority({team_id, basePriority: 10})
const jobId = uuidv7();
await addScrapeJob(
{
url,
mode: "single_urls",
crawlerOptions,
scrapeOptions,
internalOptions,
team_id,
origin: req.body.origin ?? defaultOrigin,
integration: req.body.integration,
billing: { endpoint: "crawl", jobId: id },
crawl_id: id,
zeroDataRetention: false, // not supported on v0
apiKeyId: chunk?.api_key_id ?? null,
},
jobId,
await getJobPriority({ team_id, basePriority: 15 }),
);
await addCrawlJob(id, jobId, logger);
}
res.json({ jobId: id });
} catch (error) {
Sentry.captureException(error);
logger.error(error);
return res.status(500).json({
error: error instanceof ZodError ? "Invalid URL" : error.message,
});
}
}
|