Nick: python working

apps/js-sdk/firecrawl/src/index.ts

@@ -75,6 +75,7 @@ export interface FirecrawlDocument {
   html?: string;
   rawHtml?: string;
   links?: string[];
+  extract?: Record<any, any>;
   screenshot?: string;
   metadata: FirecrawlDocumentMetadata;
 }
@@ -344,12 +345,13 @@ export default class FirecrawlApp<T extends "v0" | "v1"> {
       Authorization: `Bearer ${this.apiKey}`,
     } as AxiosRequestHeaders;
     let jsonData: any = { url, ...params };
-    if (jsonData?.extractorOptions?.extractionSchema) {
+    if (jsonData?.extractorOptions?.extractionSchema || jsonData?.extract?.schema) {
-      let schema = jsonData.extractorOptions.extractionSchema;
+      let schema = jsonData.extractorOptions?.extractionSchema || jsonData.extract?.schema;
       // Check if schema is an instance of ZodSchema to correctly identify Zod schemas
       if (schema instanceof z.ZodSchema) {
         schema = zodToJsonSchema(schema);
       }
+      if(this.version === 'v0') {
         jsonData = {
           ...jsonData,
           extractorOptions: {
@@ -358,6 +360,15 @@ export default class FirecrawlApp<T extends "v0" | "v1"> {
             mode: jsonData.extractorOptions.mode || "llm-extraction",
           },
         };
+      } else {
+        jsonData = {
+          ...jsonData,
+          extract: {
+            ...jsonData.extract,
+            schema: schema,
+          },
+        };
+      }
     }
     try {
       const response: AxiosResponse = await axios.post(

apps/python-sdk/example.py

@@ -1,17 +1,18 @@
 import uuid
 from firecrawl.firecrawl import FirecrawlApp
 
-app = FirecrawlApp(api_key="fc-YOUR_API_KEY")
+app = FirecrawlApp(api_key="fc-")
 
 # Scrape a website:
 scrape_result = app.scrape_url('firecrawl.dev')
 print(scrape_result['markdown'])
 
 # Crawl a website:
-idempotency_key = str(uuid.uuid4()) # optional idempotency key
+crawl_result = app.crawl_url('docs.firecrawl.dev', {}, True, 2)
-crawl_result = app.crawl_url('mendable.ai', {'crawlerOptions': {'excludes': ['blog/*']}}, True, 2, idempotency_key)
 print(crawl_result)
 
+
+
 # LLM Extraction:
 # Define schema to extract contents into using pydantic
 from pydantic import BaseModel, Field
@@ -27,18 +28,15 @@ class TopArticlesSchema(BaseModel):
     top: List[ArticleSchema] = Field(..., max_items=5, description="Top 5 stories")
 
 llm_extraction_result = app.scrape_url('https://news.ycombinator.com', {
-    'extractorOptions': {
+    'formats': ['extract'],
-        'extractionSchema': TopArticlesSchema.model_json_schema(),
+    'extract': {
-        'mode': 'llm-extraction'
+        'schema': TopArticlesSchema.model_json_schema()
-    },
-    'pageOptions':{
-        'onlyMainContent': True
     }
 })
 
-print(llm_extraction_result['llm_extraction'])
+print(llm_extraction_result['extract'])
 
-# Define schema to extract contents into using json schema
+# # Define schema to extract contents into using json schema
 json_schema = {
   "type": "object",
   "properties": {
@@ -62,7 +60,10 @@ json_schema = {
   "required": ["top"]
 }
 
-llm_extraction_result = app.scrape_url('https://news.ycombinator.com', {
+app2 = FirecrawlApp(api_key="fc-", version="v0")
+
+
+llm_extraction_result = app2.scrape_url('https://news.ycombinator.com', {
     'extractorOptions': {
         'extractionSchema': json_schema,
         'mode': 'llm-extraction'

apps/python-sdk/firecrawl/firecrawl.py

@@ -58,20 +58,30 @@ class FirecrawlApp:
 
         # If there are additional params, process them
         if params:
-            # Initialize extractorOptions if present
+            if self.version == 'v0':
+                # Handle extractorOptions (for v0 compatibility)
                 extractor_options = params.get('extractorOptions', {})
-            # Check and convert the extractionSchema if it's a Pydantic model
+                if extractor_options:
-            if 'extractionSchema' in extractor_options:
+                    if 'extractionSchema' in extractor_options and hasattr(extractor_options['extractionSchema'], 'schema'):
-                if hasattr(extractor_options['extractionSchema'], 'schema'):
                         extractor_options['extractionSchema'] = extractor_options['extractionSchema'].schema()
-                # Ensure 'mode' is set, defaulting to 'llm-extraction' if not explicitly provided
                     extractor_options['mode'] = extractor_options.get('mode', 'llm-extraction')
-                # Update the scrape_params with the processed extractorOptions
                     scrape_params['extractorOptions'] = extractor_options
 
                 # Include any other params directly at the top level of scrape_params
                 for key, value in params.items():
-                if key != 'extractorOptions':
+                    if key not in ['extractorOptions']:
+                        scrape_params[key] = value
+            elif self.version == 'v1':
+                # Handle extract (for v1)
+                extract = params.get('extract', {})
+                if extract:
+                    if 'schema' in extract and hasattr(extract['schema'], 'schema'):
+                        extract['schema'] = extract['schema'].schema()
+                    scrape_params['extract'] = extract
+
+                # Include any other params directly at the top level of scrape_params
+                for key, value in params.items():
+                    if key not in ['extract']:
                         scrape_params[key] = value
 
         endpoint = f'/{self.version}/scrape'