firecrawl 1.21.0 → 1.21.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/index.cjs +1 -0
- package/dist/index.d.cts +15 -1
- package/dist/index.d.ts +15 -1
- package/dist/index.js +1 -0
- package/package.json +1 -1
- package/src/index.ts +15 -1
- package/dump.rdb +0 -0
package/dist/index.cjs
CHANGED
|
@@ -419,6 +419,7 @@ var FirecrawlApp = class {
|
|
|
419
419
|
* @param pollInterval - Time in seconds for job status checks.
|
|
420
420
|
* @param idempotencyKey - Optional idempotency key for the request.
|
|
421
421
|
* @param webhook - Optional webhook for the batch scrape.
|
|
422
|
+
* @param ignoreInvalidURLs - Optional flag to ignore invalid URLs.
|
|
422
423
|
* @returns The response from the crawl operation.
|
|
423
424
|
*/
|
|
424
425
|
async batchScrapeUrls(urls, params, pollInterval = 2, idempotencyKey, webhook, ignoreInvalidURLs) {
|
package/dist/index.d.cts
CHANGED
|
@@ -65,6 +65,11 @@ interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult | neve
|
|
|
65
65
|
screenshot?: string;
|
|
66
66
|
metadata?: FirecrawlDocumentMetadata;
|
|
67
67
|
actions: ActionsSchema;
|
|
68
|
+
compare?: {
|
|
69
|
+
previousScrapeAt: string | null;
|
|
70
|
+
changeStatus: "new" | "same" | "changed" | "removed";
|
|
71
|
+
visibility: "visible" | "hidden";
|
|
72
|
+
};
|
|
68
73
|
title?: string;
|
|
69
74
|
description?: string;
|
|
70
75
|
}
|
|
@@ -73,7 +78,7 @@ interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult | neve
|
|
|
73
78
|
* Defines the options and configurations available for scraping web content.
|
|
74
79
|
*/
|
|
75
80
|
interface CrawlScrapeOptions {
|
|
76
|
-
formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json")[];
|
|
81
|
+
formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json" | "compare")[];
|
|
77
82
|
headers?: Record<string, string>;
|
|
78
83
|
includeTags?: string[];
|
|
79
84
|
excludeTags?: string[];
|
|
@@ -132,6 +137,14 @@ interface ScrapeParams<LLMSchema extends zt.ZodSchema = any, ActionsSchema exten
|
|
|
132
137
|
}
|
|
133
138
|
interface ActionsResult {
|
|
134
139
|
screenshots: string[];
|
|
140
|
+
scrapes: ({
|
|
141
|
+
url: string;
|
|
142
|
+
html: string;
|
|
143
|
+
})[];
|
|
144
|
+
javascriptReturns: {
|
|
145
|
+
type: string;
|
|
146
|
+
value: unknown;
|
|
147
|
+
}[];
|
|
135
148
|
}
|
|
136
149
|
/**
|
|
137
150
|
* Response interface for scraping operations.
|
|
@@ -529,6 +542,7 @@ declare class FirecrawlApp {
|
|
|
529
542
|
* @param pollInterval - Time in seconds for job status checks.
|
|
530
543
|
* @param idempotencyKey - Optional idempotency key for the request.
|
|
531
544
|
* @param webhook - Optional webhook for the batch scrape.
|
|
545
|
+
* @param ignoreInvalidURLs - Optional flag to ignore invalid URLs.
|
|
532
546
|
* @returns The response from the crawl operation.
|
|
533
547
|
*/
|
|
534
548
|
batchScrapeUrls(urls: string[], params?: ScrapeParams, pollInterval?: number, idempotencyKey?: string, webhook?: CrawlParams["webhook"], ignoreInvalidURLs?: boolean): Promise<BatchScrapeStatusResponse | ErrorResponse>;
|
package/dist/index.d.ts
CHANGED
|
@@ -65,6 +65,11 @@ interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult | neve
|
|
|
65
65
|
screenshot?: string;
|
|
66
66
|
metadata?: FirecrawlDocumentMetadata;
|
|
67
67
|
actions: ActionsSchema;
|
|
68
|
+
compare?: {
|
|
69
|
+
previousScrapeAt: string | null;
|
|
70
|
+
changeStatus: "new" | "same" | "changed" | "removed";
|
|
71
|
+
visibility: "visible" | "hidden";
|
|
72
|
+
};
|
|
68
73
|
title?: string;
|
|
69
74
|
description?: string;
|
|
70
75
|
}
|
|
@@ -73,7 +78,7 @@ interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult | neve
|
|
|
73
78
|
* Defines the options and configurations available for scraping web content.
|
|
74
79
|
*/
|
|
75
80
|
interface CrawlScrapeOptions {
|
|
76
|
-
formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json")[];
|
|
81
|
+
formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json" | "compare")[];
|
|
77
82
|
headers?: Record<string, string>;
|
|
78
83
|
includeTags?: string[];
|
|
79
84
|
excludeTags?: string[];
|
|
@@ -132,6 +137,14 @@ interface ScrapeParams<LLMSchema extends zt.ZodSchema = any, ActionsSchema exten
|
|
|
132
137
|
}
|
|
133
138
|
interface ActionsResult {
|
|
134
139
|
screenshots: string[];
|
|
140
|
+
scrapes: ({
|
|
141
|
+
url: string;
|
|
142
|
+
html: string;
|
|
143
|
+
})[];
|
|
144
|
+
javascriptReturns: {
|
|
145
|
+
type: string;
|
|
146
|
+
value: unknown;
|
|
147
|
+
}[];
|
|
135
148
|
}
|
|
136
149
|
/**
|
|
137
150
|
* Response interface for scraping operations.
|
|
@@ -529,6 +542,7 @@ declare class FirecrawlApp {
|
|
|
529
542
|
* @param pollInterval - Time in seconds for job status checks.
|
|
530
543
|
* @param idempotencyKey - Optional idempotency key for the request.
|
|
531
544
|
* @param webhook - Optional webhook for the batch scrape.
|
|
545
|
+
* @param ignoreInvalidURLs - Optional flag to ignore invalid URLs.
|
|
532
546
|
* @returns The response from the crawl operation.
|
|
533
547
|
*/
|
|
534
548
|
batchScrapeUrls(urls: string[], params?: ScrapeParams, pollInterval?: number, idempotencyKey?: string, webhook?: CrawlParams["webhook"], ignoreInvalidURLs?: boolean): Promise<BatchScrapeStatusResponse | ErrorResponse>;
|
package/dist/index.js
CHANGED
|
@@ -383,6 +383,7 @@ var FirecrawlApp = class {
|
|
|
383
383
|
* @param pollInterval - Time in seconds for job status checks.
|
|
384
384
|
* @param idempotencyKey - Optional idempotency key for the request.
|
|
385
385
|
* @param webhook - Optional webhook for the batch scrape.
|
|
386
|
+
* @param ignoreInvalidURLs - Optional flag to ignore invalid URLs.
|
|
386
387
|
* @returns The response from the crawl operation.
|
|
387
388
|
*/
|
|
388
389
|
async batchScrapeUrls(urls, params, pollInterval = 2, idempotencyKey, webhook, ignoreInvalidURLs) {
|
package/package.json
CHANGED
package/src/index.ts
CHANGED
|
@@ -69,6 +69,11 @@ export interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult
|
|
|
69
69
|
screenshot?: string;
|
|
70
70
|
metadata?: FirecrawlDocumentMetadata;
|
|
71
71
|
actions: ActionsSchema;
|
|
72
|
+
compare?: {
|
|
73
|
+
previousScrapeAt: string | null;
|
|
74
|
+
changeStatus: "new" | "same" | "changed" | "removed";
|
|
75
|
+
visibility: "visible" | "hidden";
|
|
76
|
+
};
|
|
72
77
|
// v1 search only
|
|
73
78
|
title?: string;
|
|
74
79
|
description?: string;
|
|
@@ -79,7 +84,7 @@ export interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult
|
|
|
79
84
|
* Defines the options and configurations available for scraping web content.
|
|
80
85
|
*/
|
|
81
86
|
export interface CrawlScrapeOptions {
|
|
82
|
-
formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json")[];
|
|
87
|
+
formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json" | "compare")[];
|
|
83
88
|
headers?: Record<string, string>;
|
|
84
89
|
includeTags?: string[];
|
|
85
90
|
excludeTags?: string[];
|
|
@@ -141,6 +146,14 @@ export interface ScrapeParams<LLMSchema extends zt.ZodSchema = any, ActionsSchem
|
|
|
141
146
|
|
|
142
147
|
export interface ActionsResult {
|
|
143
148
|
screenshots: string[];
|
|
149
|
+
scrapes: ({
|
|
150
|
+
url: string;
|
|
151
|
+
html: string;
|
|
152
|
+
})[];
|
|
153
|
+
javascriptReturns: {
|
|
154
|
+
type: string;
|
|
155
|
+
value: unknown
|
|
156
|
+
}[];
|
|
144
157
|
}
|
|
145
158
|
|
|
146
159
|
/**
|
|
@@ -914,6 +927,7 @@ export default class FirecrawlApp {
|
|
|
914
927
|
* @param pollInterval - Time in seconds for job status checks.
|
|
915
928
|
* @param idempotencyKey - Optional idempotency key for the request.
|
|
916
929
|
* @param webhook - Optional webhook for the batch scrape.
|
|
930
|
+
* @param ignoreInvalidURLs - Optional flag to ignore invalid URLs.
|
|
917
931
|
* @returns The response from the crawl operation.
|
|
918
932
|
*/
|
|
919
933
|
async batchScrapeUrls(
|
package/dump.rdb
DELETED
|
Binary file
|