Spaces:
Sleeping
Sleeping
File size: 18,105 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 | //! Batch scrape endpoint for Firecrawl API v2.
use serde::{Deserialize, Serialize};
use crate::client::Client;
use crate::scrape::ScrapeOptions;
use crate::types::{CrawlErrorsResponse, Document, JobStatus, WebhookConfig};
use crate::FirecrawlError;
/// Options for batch scraping.
#[serde_with::skip_serializing_none]
#[derive(Deserialize, Serialize, Debug, Default, Clone)]
#[serde(rename_all = "camelCase")]
pub struct BatchScrapeOptions {
/// Scrape options to apply to all URLs.
#[serde(flatten)]
pub options: Option<ScrapeOptions>,
/// Webhook configuration for job notifications.
pub webhook: Option<WebhookConfig>,
/// ID of an existing batch job to append URLs to.
pub append_to_id: Option<String>,
/// Whether to ignore invalid URLs instead of failing.
#[serde(rename = "ignoreInvalidURLs")]
pub ignore_invalid_urls: Option<bool>,
/// Maximum concurrent requests.
pub max_concurrency: Option<u32>,
/// Enable zero data retention mode.
pub zero_data_retention: Option<bool>,
/// Idempotency key for the request.
#[serde(skip)]
pub idempotency_key: Option<String>,
/// Integration identifier for tracking.
pub integration: Option<String>,
/// Poll interval for synchronous batch scrape (milliseconds).
#[serde(skip)]
pub poll_interval: Option<u64>,
}
/// Request body for batch scrape endpoint.
#[derive(Deserialize, Serialize, Debug, Default)]
#[serde(rename_all = "camelCase")]
struct BatchScrapeRequest {
urls: Vec<String>,
#[serde(flatten)]
options: BatchScrapeOptions,
}
/// Response from starting a batch scrape job.
#[derive(Deserialize, Serialize, Debug, Clone)]
#[serde(rename_all = "camelCase")]
pub struct BatchScrapeResponse {
/// Whether the request was successful.
pub success: bool,
/// The batch scrape job ID.
pub id: String,
/// URL to check the batch scrape status.
pub url: String,
/// URLs that were invalid and ignored.
#[serde(rename = "invalidURLs")]
pub invalid_urls: Option<Vec<String>>,
}
/// Status of a batch scrape job.
#[serde_with::skip_serializing_none]
#[derive(Deserialize, Serialize, Debug, Clone)]
#[serde(rename_all = "camelCase")]
pub struct BatchScrapeJob {
/// Current status of the batch scrape job.
pub status: JobStatus,
/// Number of URLs completed.
pub completed: u32,
/// Total number of URLs to scrape.
pub total: u32,
/// Credits used by the batch scrape.
pub credits_used: Option<u32>,
/// Expiry time of the batch data.
pub expires_at: Option<String>,
/// URL for the next page of results.
pub next: Option<String>,
/// Scraped documents.
pub data: Vec<Document>,
}
impl Client {
/// Starts a batch scrape job asynchronously.
///
/// Returns immediately with a job ID that can be used to check status.
///
/// # Arguments
///
/// * `urls` - List of URLs to scrape.
/// * `options` - Optional batch scrape configuration.
///
/// # Returns
///
/// A `BatchScrapeResponse` containing the job ID.
///
/// # Example
///
/// ```no_run
/// use firecrawl::{Client, BatchScrapeOptions};
///
/// #[tokio::main]
/// async fn main() -> Result<(), Box<dyn std::error::Error>> {
/// let client = Client::new("your-api-key")?;
///
/// let urls = vec![
/// "https://example.com".to_string(),
/// "https://example.org".to_string(),
/// ];
///
/// let response = client.start_batch_scrape(urls, None).await?;
/// println!("Batch job started: {}", response.id);
///
/// // Check status later
/// let status = client.get_batch_scrape_status(&response.id).await?;
/// println!("Completed: {}/{}", status.completed, status.total);
///
/// Ok(())
/// }
/// ```
pub async fn start_batch_scrape(
&self,
urls: Vec<String>,
options: impl Into<Option<BatchScrapeOptions>>,
) -> Result<BatchScrapeResponse, FirecrawlError> {
let options = options.into().unwrap_or_default();
let body = BatchScrapeRequest {
urls,
options: options.clone(),
};
let headers = self.prepare_headers(options.idempotency_key.as_ref());
let response = self
.client
.post(self.url("/batch/scrape"))
.headers(headers)
.json(&body)
.send()
.await
.map_err(|e| FirecrawlError::HttpError("Starting batch scrape".to_string(), e))?;
self.handle_response(response, "start batch scrape").await
}
/// Gets the status of a batch scrape job.
///
/// If the job is completed, this will automatically fetch all pages of results.
///
/// # Arguments
///
/// * `id` - The batch scrape job ID.
///
/// # Returns
///
/// A `BatchScrapeJob` containing the current status and any available documents.
///
/// # Example
///
/// ```no_run
/// use firecrawl::Client;
///
/// #[tokio::main]
/// async fn main() -> Result<(), Box<dyn std::error::Error>> {
/// let client = Client::new("your-api-key")?;
///
/// let status = client.get_batch_scrape_status("job-id").await?;
/// println!("Status: {:?}", status.status);
/// println!("Completed: {}/{}", status.completed, status.total);
/// println!("Documents: {}", status.data.len());
///
/// Ok(())
/// }
/// ```
pub async fn get_batch_scrape_status(
&self,
id: impl AsRef<str>,
) -> Result<BatchScrapeJob, FirecrawlError> {
let response = self
.client
.get(self.url(&format!("/batch/scrape/{}", id.as_ref())))
.headers(self.prepare_headers(None))
.send()
.await
.map_err(|e| {
FirecrawlError::HttpError(
format!("Checking batch scrape status {}", id.as_ref()),
e,
)
})?;
let mut status: BatchScrapeJob = self
.handle_response(response, format!("batch scrape status {}", id.as_ref()))
.await?;
// Auto-paginate if completed
if status.status == JobStatus::Completed {
while let Some(next) = status.next.take() {
let next_status = self.get_batch_scrape_status_next(&next).await?;
status.data.extend(next_status.data);
status.next = next_status.next;
}
}
Ok(status)
}
/// Fetches the next page of batch scrape results.
async fn get_batch_scrape_status_next(
&self,
next: &str,
) -> Result<BatchScrapeJob, FirecrawlError> {
let response = self
.client
.get(next)
.headers(self.prepare_headers(None))
.send()
.await
.map_err(|e| {
FirecrawlError::HttpError(format!("Paginating batch scrape at {}", next), e)
})?;
self.handle_response(response, "batch scrape pagination")
.await
}
/// Scrapes multiple URLs and waits for completion.
///
/// This method starts a batch scrape and polls until it completes or fails.
///
/// # Arguments
///
/// * `urls` - List of URLs to scrape.
/// * `options` - Optional batch scrape configuration.
///
/// # Returns
///
/// A `BatchScrapeJob` containing all scraped documents.
///
/// # Example
///
/// ```no_run
/// use firecrawl::{Client, BatchScrapeOptions, ScrapeOptions, Format};
///
/// #[tokio::main]
/// async fn main() -> Result<(), Box<dyn std::error::Error>> {
/// let client = Client::new("your-api-key")?;
///
/// let urls = vec![
/// "https://example.com/page1".to_string(),
/// "https://example.com/page2".to_string(),
/// "https://example.com/page3".to_string(),
/// ];
///
/// let options = BatchScrapeOptions {
/// options: Some(ScrapeOptions {
/// formats: Some(vec![Format::Markdown, Format::Links]),
/// ..Default::default()
/// }),
/// ignore_invalid_urls: Some(true),
/// poll_interval: Some(3000),
/// ..Default::default()
/// };
///
/// let result = client.batch_scrape(urls, options).await?;
/// println!("Scraped {} pages", result.data.len());
///
/// for doc in result.data {
/// println!("URL: {:?}", doc.metadata.and_then(|m| m.source_url));
/// }
///
/// Ok(())
/// }
/// ```
pub async fn batch_scrape(
&self,
urls: Vec<String>,
options: impl Into<Option<BatchScrapeOptions>>,
) -> Result<BatchScrapeJob, FirecrawlError> {
let options = options.into().unwrap_or_default();
let poll_interval = options.poll_interval.unwrap_or(2000);
let response = self.start_batch_scrape(urls, options).await?;
self.wait_for_batch_scrape(&response.id, poll_interval)
.await
}
/// Waits for a batch scrape job to complete.
async fn wait_for_batch_scrape(
&self,
id: &str,
poll_interval: u64,
) -> Result<BatchScrapeJob, FirecrawlError> {
loop {
let status = self.get_batch_scrape_status(id).await?;
match status.status {
JobStatus::Completed => return Ok(status),
JobStatus::Scraping => {
tokio::time::sleep(tokio::time::Duration::from_millis(poll_interval)).await;
}
JobStatus::Failed => {
return Err(FirecrawlError::JobFailed(
"Batch scrape job failed".to_string(),
JobStatus::Failed,
));
}
JobStatus::Cancelled => {
return Err(FirecrawlError::JobFailed(
"Batch scrape job was cancelled".to_string(),
JobStatus::Cancelled,
));
}
}
}
}
/// Gets errors from a batch scrape job.
///
/// # Arguments
///
/// * `id` - The batch scrape job ID.
///
/// # Returns
///
/// A `CrawlErrorsResponse` containing error details.
///
/// # Example
///
/// ```no_run
/// use firecrawl::Client;
///
/// #[tokio::main]
/// async fn main() -> Result<(), Box<dyn std::error::Error>> {
/// let client = Client::new("your-api-key")?;
///
/// let errors = client.get_batch_scrape_errors("job-id").await?;
/// for error in errors.errors {
/// println!("Error on {}: {}", error.url, error.error);
/// }
///
/// Ok(())
/// }
/// ```
pub async fn get_batch_scrape_errors(
&self,
id: impl AsRef<str>,
) -> Result<CrawlErrorsResponse, FirecrawlError> {
let response = self
.client
.get(self.url(&format!("/batch/scrape/{}/errors", id.as_ref())))
.headers(self.prepare_headers(None))
.send()
.await
.map_err(|e| {
FirecrawlError::HttpError(format!("Getting batch scrape errors {}", id.as_ref()), e)
})?;
self.handle_response(response, "batch scrape errors").await
}
}
#[cfg(test)]
mod tests {
use super::*;
use serde_json::json;
#[tokio::test]
async fn test_start_batch_scrape_with_mock() {
let mut server = mockito::Server::new_async().await;
let mock = server
.mock("POST", "/v2/batch/scrape")
.with_status(200)
.with_header("content-type", "application/json")
.with_body(
json!({
"success": true,
"id": "batch-123",
"url": "https://api.firecrawl.dev/v2/batch/scrape/batch-123"
})
.to_string(),
)
.create();
let client = Client::new_selfhosted(server.url(), Some("test_key")).unwrap();
let urls = vec![
"https://example.com".to_string(),
"https://example.org".to_string(),
];
let response = client.start_batch_scrape(urls, None).await.unwrap();
assert!(response.success);
assert_eq!(response.id, "batch-123");
mock.assert();
}
#[tokio::test]
async fn test_get_batch_scrape_status_with_mock() {
let mut server = mockito::Server::new_async().await;
let mock = server
.mock("GET", "/v2/batch/scrape/batch-123")
.with_status(200)
.with_header("content-type", "application/json")
.with_body(
json!({
"status": "completed",
"total": 3,
"completed": 3,
"creditsUsed": 3,
"data": [
{
"markdown": "# Page 1",
"metadata": { "sourceURL": "https://example.com/1", "statusCode": 200 }
},
{
"markdown": "# Page 2",
"metadata": { "sourceURL": "https://example.com/2", "statusCode": 200 }
}
]
})
.to_string(),
)
.create();
let client = Client::new_selfhosted(server.url(), Some("test_key")).unwrap();
let status = client.get_batch_scrape_status("batch-123").await.unwrap();
assert_eq!(status.status, JobStatus::Completed);
assert_eq!(status.total, 3);
assert_eq!(status.completed, 3);
assert_eq!(status.data.len(), 2);
mock.assert();
}
#[tokio::test]
async fn test_batch_scrape_with_invalid_urls() {
let mut server = mockito::Server::new_async().await;
let mock = server
.mock("POST", "/v2/batch/scrape")
.with_status(200)
.with_header("content-type", "application/json")
.with_body(
json!({
"success": true,
"id": "batch-456",
"url": "https://api.firecrawl.dev/v2/batch/scrape/batch-456",
"invalidURLs": ["not-a-url"]
})
.to_string(),
)
.create();
let client = Client::new_selfhosted(server.url(), Some("test_key")).unwrap();
let urls = vec!["https://example.com".to_string(), "not-a-url".to_string()];
let options = BatchScrapeOptions {
ignore_invalid_urls: Some(true),
..Default::default()
};
let response = client.start_batch_scrape(urls, options).await.unwrap();
assert!(response.success);
assert_eq!(response.invalid_urls, Some(vec!["not-a-url".to_string()]));
mock.assert();
}
#[tokio::test]
async fn test_batch_scrape_sync() {
let mut server = mockito::Server::new_async().await;
// Mock the start endpoint
let start_mock = server
.mock("POST", "/v2/batch/scrape")
.with_status(200)
.with_header("content-type", "application/json")
.with_body(
json!({
"success": true,
"id": "batch-789",
"url": "https://api.firecrawl.dev/v2/batch/scrape/batch-789"
})
.to_string(),
)
.create();
// Mock the status endpoint (completed immediately)
let status_mock = server
.mock("GET", "/v2/batch/scrape/batch-789")
.with_status(200)
.with_header("content-type", "application/json")
.with_body(
json!({
"status": "completed",
"total": 2,
"completed": 2,
"data": [
{
"markdown": "# Content",
"metadata": { "sourceURL": "https://example.com", "statusCode": 200 }
}
]
})
.to_string(),
)
.create();
let client = Client::new_selfhosted(server.url(), Some("test_key")).unwrap();
let urls = vec!["https://example.com".to_string()];
let result = client.batch_scrape(urls, None).await.unwrap();
assert_eq!(result.status, JobStatus::Completed);
assert_eq!(result.data.len(), 1);
start_mock.assert();
status_mock.assert();
}
#[tokio::test]
async fn test_get_batch_scrape_errors() {
let mut server = mockito::Server::new_async().await;
let mock = server
.mock("GET", "/v2/batch/scrape/batch-123/errors")
.with_status(200)
.with_header("content-type", "application/json")
.with_body(
json!({
"errors": [
{
"id": "err-1",
"url": "https://example.com/broken",
"error": "Connection timeout"
}
],
"robotsBlocked": []
})
.to_string(),
)
.create();
let client = Client::new_selfhosted(server.url(), Some("test_key")).unwrap();
let errors = client.get_batch_scrape_errors("batch-123").await.unwrap();
assert_eq!(errors.errors.len(), 1);
assert_eq!(errors.errors[0].error, "Connection timeout");
mock.assert();
}
}
|