Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. π₯
TypeScript aiai-agentsai-crawlerai-scrapingai-searchcrawlerdata-extractionhtml-to-markdownllmmarkdownscraperscrapingweb-crawlerweb-dataweb-data-extractionweb-scraperweb-scrapingweb-searchwebscraping
feat(search): accept the gov category
PhantomInTheWire8cc906812030
diff --git a/apps/js-sdk/firecrawl/README.md b/apps/js-sdk/firecrawl/README.mdindex 3e8fa9e79..1bbd87430 100644--- a/apps/js-sdk/firecrawl/README.md+++ b/apps/js-sdk/firecrawl/README.md@@ -191,7 +191,7 @@ const scraped = await app.search('firecrawl changelog', {```Results are grouped by source: `.web`, `.news` and `.images`. Developer-category results are served inside `.web`.+and gov category results are served inside `.web`.Use `categories` to narrow web search to a kind of site:@@ -242,6 +242,8 @@ Use `legalRegulatorySearch` to search the Legal and Regulatory Index: primarylaw and regulatory material from US federal, state, and local governmentsources, including statutes, regulations, codes, court opinions, and othergovernment publications. Results come back in the ordinary web-result shape.+Generic `search(..., { categories: ['gov'] })` returns index results inside+`.web`; like `developer`, it cannot be combined with other categories.```jsconst law = await app.legalRegulatorySearch('food labeling requirements', {diff --git a/apps/js-sdk/firecrawl/src/v2/types.ts b/apps/js-sdk/firecrawl/src/v2/types.tsindex 8af462474..5ef12d48c 100644--- a/apps/js-sdk/firecrawl/src/v2/types.ts+++ b/apps/js-sdk/firecrawl/src/v2/types.ts@@ -983,6 +983,8 @@ export interface AlexandriaOptions {* - `pdf` β restrict results to PDFs (adds `filetype:pdf`).* - `developer` β developer-index results (issues, pull requests, READMEs and* documentation) served in `web`; cannot be combined with other categories.+ * - `gov` β legal and regulatory results served in `web`; cannot be combined+ * with other categories.** β οΈ `categories: ["research"]` is **not** Firecrawl's research paper index.* To search papers themselves β ~43M abstracts, roughly 90% biomedical@@ -994,7 +996,7 @@ export interface AlexandriaOptions {* happen to live on academic domains β `search({ categories: ["research"] })`.*/export interface CategoryOption {- type: "github" | "research" | "pdf" | "developer";+ type: "github" | "research" | "pdf" | "developer" | "gov";}export interface SearchRequest {@@ -1016,7 +1018,7 @@ export interface SearchRequest {* `firecrawl.research.searchPapers()` instead.*/categories?: Array<- "github" | "research" | "pdf" | "developer" | CategoryOption+ "github" | "research" | "pdf" | "developer" | "gov" | CategoryOption>;includeDomains?: string[];excludeDomains?: string[];diff --git a/apps/python-sdk/README.md b/apps/python-sdk/README.mdindex c8b8c994a..21973c10e 100644--- a/apps/python-sdk/README.md+++ b/apps/python-sdk/README.md@@ -264,6 +264,8 @@ Use `legal_regulatory_search` to search the Legal and Regulatory Index: primarylaw and regulatory material from US federal, state, and local governmentsources, including statutes, regulations, codes, court opinions, and othergovernment publications. Results come back in the ordinary web-result shape.+Generic `search(categories=["gov"])` returns index results inside `.web`;+like `developer`, it cannot be combined with other categories.```pythonlaw = firecrawl.legal_regulatory_search("food labeling requirements", k=5)diff --git a/apps/python-sdk/firecrawl/v2/methods/search.py b/apps/python-sdk/firecrawl/v2/methods/search.pyindex b46709688..0cb884863 100644--- a/apps/python-sdk/firecrawl/v2/methods/search.py+++ b/apps/python-sdk/firecrawl/v2/methods/search.py@@ -136,7 +136,7 @@ def _validate_search_request(request: SearchRequest) -> SearchRequest:# Validate categories (if provided)if request.categories is not None:- valid_categories = {"github", "research", "pdf", "developer"}+ valid_categories = {"github", "research", "pdf", "developer", "gov"}for category in request.categories:if isinstance(category, str):if category not in valid_categories:diff --git a/apps/python-sdk/firecrawl/v2/types.py b/apps/python-sdk/firecrawl/v2/types.pyindex 3c0738b8f..676e2cfef 100644--- a/apps/python-sdk/firecrawl/v2/types.py+++ b/apps/python-sdk/firecrawl/v2/types.py@@ -635,6 +635,8 @@ class Category(BaseModel):- "pdf": Filter results to PDF files (adds filetype:pdf to search)- "developer": Developer-index results (issues, pull requests, READMEs anddocumentation) served in `web`; cannot be combined with other categories+ - "gov": Legal and regulatory results served in `web`; cannot be combined+ with other categories.. warning::``categories=["research"]`` is **not** Firecrawl's research paper index.