firecrawl 0.0.19__tar.gz → 1.1.1__tar.gz

firecrawl-1.1.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Sideguide Technologies Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

{firecrawl-0.0.19 → firecrawl-1.1.1}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.1
 Name: firecrawl
-Version: 0.0.19
+Version: 1.1.1
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/mendableai/firecrawl
 Author: Mendable.ai
 Author-email: "Mendable.ai" <nick@mendable.ai>
 Maintainer-email: "Mendable.ai" <nick@mendable.ai>
-License: GNU General Public License v3 (GPLv3)
+License: GNU Affero General Public License v3 (AGPLv3)
 Project-URL: Documentation, https://docs.firecrawl.dev
 Project-URL: Source, https://github.com/mendableai/firecrawl
 Project-URL: Tracker, https://github.com/mendableai/firecrawl/issues
@@ -30,9 +30,14 @@ Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Text Processing
 Classifier: Topic :: Text Processing :: Indexing
-Requires-Python: >=3.7
+Requires-Python: >=3.8
 Description-Content-Type: text/markdown
+License-File: LICENSE
 Requires-Dist: requests
+Requires-Dist: python-dotenv
+Requires-Dist: websockets
+Requires-Dist: asyncio
+Requires-Dist: nest-asyncio
 
 # Firecrawl Python SDK
 
@@ -51,27 +56,31 @@ pip install firecrawl-py
 1. Get an API key from [firecrawl.dev](https://firecrawl.dev)
 2. Set the API key as an environment variable named `FIRECRAWL_API_KEY` or pass it as a parameter to the `FirecrawlApp` class.
 
-
 Here's an example of how to use the SDK:
 
 ```python
-from firecrawl import FirecrawlApp
-
-# Initialize the FirecrawlApp with your API key
-app = FirecrawlApp(api_key='your_api_key')
-
-# Scrape a single URL
-url = 'https://mendable.ai'
-scraped_data = app.scrape_url(url)
-
-# Crawl a website
-crawl_url = 'https://mendable.ai'
-params = {
-    'pageOptions': {
-        'onlyMainContent': True
-    }
-}
-crawl_result = app.crawl_url(crawl_url, params=params)
+from firecrawl.firecrawl import FirecrawlApp
+
+app = FirecrawlApp(api_key="fc-YOUR_API_KEY")
+
+# Scrape a website:
+scrape_status = app.scrape_url(
+  'https://firecrawl.dev', 
+  params={'formats': ['markdown', 'html']}
+)
+print(scrape_status)
+
+# Crawl a website:
+crawl_status = app.crawl_url(
+  'https://firecrawl.dev', 
+  params={
+    'limit': 100, 
+    'scrapeOptions': {'formats': ['markdown', 'html']}
+  }, 
+  wait_until_done=True, 
+  poll_interval=30
+)
+print(crawl_status)
 ```
 
 ### Scraping a URL
@@ -82,6 +91,7 @@ To scrape a single URL, use the `scrape_url` method. It takes the URL as a param
 url = 'https://example.com'
 scraped_data = app.scrape_url(url)
 ```
+
 ### Extracting structured data from a URL
 
 With LLM extraction, you can easily extract structured data from any URL. We support pydantic schemas to make it easier for you too. Here is how you to use it:
@@ -89,7 +99,7 @@ With LLM extraction, you can easily extract structured data from any URL. We sup
 ```python
 class ArticleSchema(BaseModel):
     title: str
-    points: int 
+    points: int
     by: str
     commentsURL: str
 
@@ -108,45 +118,77 @@ data = app.scrape_url('https://news.ycombinator.com', {
 print(data["llm_extraction"])
 ```
 
-### Search for a query
+### Crawling a Website
 
-Used to search the web, get the most relevant results, scrap each page and return the markdown.
+To crawl a website, use the `crawl_url` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
 
 ```python
-query = 'what is mendable?'
-search_result = app.search(query)
+idempotency_key = str(uuid.uuid4()) # optional idempotency key
+crawl_result = app.crawl_url('firecrawl.dev', {'excludePaths': ['blog/*']}, 2, idempotency_key)
+print(crawl_result)
 ```
 
-### Crawling a Website
-
-To crawl a website, use the `crawl_url` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
+### Asynchronous Crawl a Website
 
-The `wait_until_done` parameter determines whether the method should wait for the crawl job to complete before returning the result. If set to `True`, the method will periodically check the status of the crawl job until it is completed or the specified `timeout` (in seconds) is reached. If set to `False`, the method will return immediately with the job ID, and you can manually check the status of the crawl job using the `check_crawl_status` method.
+To crawl a website asynchronously, use the `async_crawl_url` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
 
 ```python
-crawl_url = 'https://example.com'
-params = {
-    'crawlerOptions': {
-        'excludes': ['blog/*'],
-        'includes': [], # leave empty for all pages
-        'limit': 1000,
-    },
-    'pageOptions': {
-        'onlyMainContent': True
-    }
-}
-crawl_result = app.crawl_url(crawl_url, params=params, wait_until_done=True, timeout=5)
+crawl_result = app.async_crawl_url('firecrawl.dev', {'excludePaths': ['blog/*']}, "")
+print(crawl_result)
 ```
 
-If `wait_until_done` is set to `True`, the `crawl_url` method will return the crawl result once the job is completed. If the job fails or is stopped, an exception will be raised.
-
 ### Checking Crawl Status
 
 To check the status of a crawl job, use the `check_crawl_status` method. It takes the job ID as a parameter and returns the current status of the crawl job.
 
 ```python
-job_id = crawl_result['jobId']
-status = app.check_crawl_status(job_id)
+id = crawl_result['id']
+status = app.check_crawl_status(id)
+```
+
+### Map a Website
+
+Use `map_url` to generate a list of URLs from a website. The `params` argument let you customize the mapping process, including options to exclude subdomains or to utilize the sitemap.
+
+```python
+# Map a website:
+map_result = app.map_url('https://example.com')
+print(map_result)
+```
+
+### Crawl a website with WebSockets
+
+To crawl a website with WebSockets, use the `crawl_url_and_watch` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
+
+```python
+# inside an async function...
+nest_asyncio.apply()
+
+# Define event handlers
+def on_document(detail):
+    print("DOC", detail)
+
+def on_error(detail):
+    print("ERR", detail['error'])
+
+def on_done(detail):
+    print("DONE", detail['status'])
+
+    # Function to start the crawl and watch process
+async def start_crawl_and_watch():
+    # Initiate the crawl job and get the watcher
+    watcher = app.crawl_url_and_watch('firecrawl.dev', { 'excludePaths': ['blog/*'], 'limit': 5 })
+
+    # Add event listeners
+    watcher.add_event_listener("document", on_document)
+    watcher.add_event_listener("error", on_error)
+    watcher.add_event_listener("done", on_done)
+
+    # Start the watcher
+    await watcher.connect()
+
+# Run the event loop
+await start_crawl_and_watch()
 ```
 
 ## Error Handling
@@ -162,20 +204,27 @@ To ensure the functionality of the Firecrawl Python SDK, we have included end-to
 To run the tests, execute the following commands:
 
 Install pytest:
+
 ```bash
 pip install pytest
 ```
 
 Run:
+
 ```bash
 pytest firecrawl/__tests__/e2e_withAuth/test.py
 ```
 
-
 ## Contributing
 
 Contributions to the Firecrawl Python SDK are welcome! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request on the GitHub repository.
 
 ## License
 
-The Firecrawl Python SDK is open-source and released under the [MIT License](https://opensource.org/licenses/MIT).
+The Firecrawl Python SDK is licensed under the MIT License. This means you are free to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the SDK, subject to the following conditions:
+
+- The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+Please note that while this SDK is MIT licensed, it is part of a larger project which may be under different licensing terms. Always refer to the license information in the root directory of the main project for overall licensing details.

firecrawl-1.1.1/README.md

@@ -0,0 +1,189 @@
+# Firecrawl Python SDK
+
+The Firecrawl Python SDK is a library that allows you to easily scrape and crawl websites, and output the data in a format ready for use with language models (LLMs). It provides a simple and intuitive interface for interacting with the Firecrawl API.
+
+## Installation
+
+To install the Firecrawl Python SDK, you can use pip:
+
+```bash
+pip install firecrawl-py
+```
+
+## Usage
+
+1. Get an API key from [firecrawl.dev](https://firecrawl.dev)
+2. Set the API key as an environment variable named `FIRECRAWL_API_KEY` or pass it as a parameter to the `FirecrawlApp` class.
+
+Here's an example of how to use the SDK:
+
+```python
+from firecrawl.firecrawl import FirecrawlApp
+
+app = FirecrawlApp(api_key="fc-YOUR_API_KEY")
+
+# Scrape a website:
+scrape_status = app.scrape_url(
+  'https://firecrawl.dev', 
+  params={'formats': ['markdown', 'html']}
+)
+print(scrape_status)
+
+# Crawl a website:
+crawl_status = app.crawl_url(
+  'https://firecrawl.dev', 
+  params={
+    'limit': 100, 
+    'scrapeOptions': {'formats': ['markdown', 'html']}
+  }, 
+  wait_until_done=True, 
+  poll_interval=30
+)
+print(crawl_status)
+```
+
+### Scraping a URL
+
+To scrape a single URL, use the `scrape_url` method. It takes the URL as a parameter and returns the scraped data as a dictionary.
+
+```python
+url = 'https://example.com'
+scraped_data = app.scrape_url(url)
+```
+
+### Extracting structured data from a URL
+
+With LLM extraction, you can easily extract structured data from any URL. We support pydantic schemas to make it easier for you too. Here is how you to use it:
+
+```python
+class ArticleSchema(BaseModel):
+    title: str
+    points: int
+    by: str
+    commentsURL: str
+
+class TopArticlesSchema(BaseModel):
+    top: List[ArticleSchema] = Field(..., max_items=5, description="Top 5 stories")
+
+data = app.scrape_url('https://news.ycombinator.com', {
+    'extractorOptions': {
+        'extractionSchema': TopArticlesSchema.model_json_schema(),
+        'mode': 'llm-extraction'
+    },
+    'pageOptions':{
+        'onlyMainContent': True
+    }
+})
+print(data["llm_extraction"])
+```
+
+### Crawling a Website
+
+To crawl a website, use the `crawl_url` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
+
+```python
+idempotency_key = str(uuid.uuid4()) # optional idempotency key
+crawl_result = app.crawl_url('firecrawl.dev', {'excludePaths': ['blog/*']}, 2, idempotency_key)
+print(crawl_result)
+```
+
+### Asynchronous Crawl a Website
+
+To crawl a website asynchronously, use the `async_crawl_url` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
+
+```python
+crawl_result = app.async_crawl_url('firecrawl.dev', {'excludePaths': ['blog/*']}, "")
+print(crawl_result)
+```
+
+### Checking Crawl Status
+
+To check the status of a crawl job, use the `check_crawl_status` method. It takes the job ID as a parameter and returns the current status of the crawl job.
+
+```python
+id = crawl_result['id']
+status = app.check_crawl_status(id)
+```
+
+### Map a Website
+
+Use `map_url` to generate a list of URLs from a website. The `params` argument let you customize the mapping process, including options to exclude subdomains or to utilize the sitemap.
+
+```python
+# Map a website:
+map_result = app.map_url('https://example.com')
+print(map_result)
+```
+
+### Crawl a website with WebSockets
+
+To crawl a website with WebSockets, use the `crawl_url_and_watch` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
+
+```python
+# inside an async function...
+nest_asyncio.apply()
+
+# Define event handlers
+def on_document(detail):
+    print("DOC", detail)
+
+def on_error(detail):
+    print("ERR", detail['error'])
+
+def on_done(detail):
+    print("DONE", detail['status'])
+
+    # Function to start the crawl and watch process
+async def start_crawl_and_watch():
+    # Initiate the crawl job and get the watcher
+    watcher = app.crawl_url_and_watch('firecrawl.dev', { 'excludePaths': ['blog/*'], 'limit': 5 })
+
+    # Add event listeners
+    watcher.add_event_listener("document", on_document)
+    watcher.add_event_listener("error", on_error)
+    watcher.add_event_listener("done", on_done)
+
+    # Start the watcher
+    await watcher.connect()
+
+# Run the event loop
+await start_crawl_and_watch()
+```
+
+## Error Handling
+
+The SDK handles errors returned by the Firecrawl API and raises appropriate exceptions. If an error occurs during a request, an exception will be raised with a descriptive error message.
+
+## Running the Tests with Pytest
+
+To ensure the functionality of the Firecrawl Python SDK, we have included end-to-end tests using `pytest`. These tests cover various aspects of the SDK, including URL scraping, web searching, and website crawling.
+
+### Running the Tests
+
+To run the tests, execute the following commands:
+
+Install pytest:
+
+```bash
+pip install pytest
+```
+
+Run:
+
+```bash
+pytest firecrawl/__tests__/e2e_withAuth/test.py
+```
+
+## Contributing
+
+Contributions to the Firecrawl Python SDK are welcome! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request on the GitHub repository.
+
+## License
+
+The Firecrawl Python SDK is licensed under the MIT License. This means you are free to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the SDK, subject to the following conditions:
+
+- The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+Please note that while this SDK is MIT licensed, it is part of a larger project which may be under different licensing terms. Always refer to the license information in the root directory of the main project for overall licensing details.

{firecrawl-0.0.19 → firecrawl-1.1.1}/firecrawl/__init__.py

@@ -13,7 +13,7 @@ import os
 
 from .firecrawl import FirecrawlApp
 
-__version__ = "0.0.19"
+__version__ = "1.1.1"
 
 # Define the logger for the Firecrawl project
 logger: logging.Logger = logging.getLogger("firecrawl")

{firecrawl-0.0.19 → firecrawl-1.1.1}/firecrawl/__tests__/e2e_withAuth/test.py

@@ -7,7 +7,7 @@ from dotenv import load_dotenv
 
 load_dotenv()
 
-API_URL = "http://127.0.0.1:3002";
+API_URL = "http://127.0.0.1:3002"
 ABSOLUTE_FIRECRAWL_PATH = "firecrawl/firecrawl.py"
 TEST_API_KEY = os.getenv('TEST_API_KEY')
 
@@ -20,32 +20,34 @@ FirecrawlApp = firecrawl.FirecrawlApp
 
 def test_no_api_key():
     with pytest.raises(Exception) as excinfo:
-      invalid_app = FirecrawlApp(api_url=API_URL)
+      invalid_app = FirecrawlApp(api_url=API_URL, version='v0')
     assert "No API key provided" in str(excinfo.value)
 
 def test_scrape_url_invalid_api_key():
-    invalid_app = FirecrawlApp(api_url=API_URL, api_key="invalid_api_key")
+    invalid_app = FirecrawlApp(api_url=API_URL, api_key="invalid_api_key", version='v0')
     with pytest.raises(Exception) as excinfo:
         invalid_app.scrape_url('https://firecrawl.dev')
     assert "Unexpected error during scrape URL: Status code 401. Unauthorized: Invalid token" in str(excinfo.value)
 
 def test_blocklisted_url():
     blocklisted_url = "https://facebook.com/fake-test"
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     with pytest.raises(Exception) as excinfo:
         app.scrape_url(blocklisted_url)
     assert "Unexpected error during scrape URL: Status code 403. Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it." in str(excinfo.value)
 
 def test_successful_response_with_valid_preview_token():
-    app = FirecrawlApp(api_url=API_URL, api_key="this_is_just_a_preview_token")
+    app = FirecrawlApp(api_url=API_URL, api_key="this_is_just_a_preview_token", version='v0')
     response = app.scrape_url('https://roastmywebsite.ai')
     assert response is not None
     assert 'content' in response
     assert "_Roast_" in response['content']
 
 def test_scrape_url_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     response = app.scrape_url('https://roastmywebsite.ai')
+    print(response)
+
     assert response is not None
     assert 'content' in response
     assert 'markdown' in response
@@ -54,7 +56,7 @@ def test_scrape_url_e2e():
     assert "_Roast_" in response['content']
 
 def test_successful_response_with_valid_api_key_and_include_html():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     response = app.scrape_url('https://roastmywebsite.ai', {'pageOptions': {'includeHtml': True}})
     assert response is not None
     assert 'content' in response
@@ -66,7 +68,7 @@ def test_successful_response_with_valid_api_key_and_include_html():
     assert "<h1" in response['html']
 
 def test_successful_response_for_valid_scrape_with_pdf_file():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     response = app.scrape_url('https://arxiv.org/pdf/astro-ph/9301001.pdf')
     assert response is not None
     assert 'content' in response
@@ -74,7 +76,7 @@ def test_successful_response_for_valid_scrape_with_pdf_file():
     assert 'We present spectrophotometric observations of the Broad Line Radio Galaxy' in response['content']
 
 def test_successful_response_for_valid_scrape_with_pdf_file_without_explicit_extension():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     response = app.scrape_url('https://arxiv.org/pdf/astro-ph/9301001')
     time.sleep(6)  # wait for 6 seconds
     assert response is not None
@@ -83,20 +85,20 @@ def test_successful_response_for_valid_scrape_with_pdf_file_without_explicit_ext
     assert 'We present spectrophotometric observations of the Broad Line Radio Galaxy' in response['content']
 
 def test_crawl_url_invalid_api_key():
-    invalid_app = FirecrawlApp(api_url=API_URL, api_key="invalid_api_key")
+    invalid_app = FirecrawlApp(api_url=API_URL, api_key="invalid_api_key", version='v0')
     with pytest.raises(Exception) as excinfo:
         invalid_app.crawl_url('https://firecrawl.dev')
     assert "Unexpected error during start crawl job: Status code 401. Unauthorized: Invalid token" in str(excinfo.value)
 
 def test_should_return_error_for_blocklisted_url():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     blocklisted_url = "https://twitter.com/fake-test"
     with pytest.raises(Exception) as excinfo:
         app.crawl_url(blocklisted_url)
     assert "Unexpected error during start crawl job: Status code 403. Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it." in str(excinfo.value)
 
 def test_crawl_url_wait_for_completion_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     response = app.crawl_url('https://roastmywebsite.ai', {'crawlerOptions': {'excludes': ['blog/*']}}, True)
     assert response is not None
     assert len(response) > 0
@@ -104,7 +106,7 @@ def test_crawl_url_wait_for_completion_e2e():
     assert "_Roast_" in response[0]['content']
 
 def test_crawl_url_with_idempotency_key_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     uniqueIdempotencyKey = str(uuid4())
     response = app.crawl_url('https://roastmywebsite.ai', {'crawlerOptions': {'excludes': ['blog/*']}}, True, 2, uniqueIdempotencyKey)
     assert response is not None
@@ -117,7 +119,7 @@ def test_crawl_url_with_idempotency_key_e2e():
     assert "Conflict: Failed to start crawl job due to a conflict. Idempotency key already used" in str(excinfo.value) 
 
 def test_check_crawl_status_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     response = app.crawl_url('https://firecrawl.dev', {'crawlerOptions': {'excludes': ['blog/*']}}, False)
     assert response is not None
     assert 'jobId' in response
@@ -131,21 +133,21 @@ def test_check_crawl_status_e2e():
     assert len(status_response['data']) > 0
 
 def test_search_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
     response = app.search("test query")
     assert response is not None
     assert 'content' in response[0]
     assert len(response) > 2
 
 def test_search_invalid_api_key():
-    invalid_app = FirecrawlApp(api_url=API_URL, api_key="invalid_api_key")
+    invalid_app = FirecrawlApp(api_url=API_URL, api_key="invalid_api_key", version='v0')
     with pytest.raises(Exception) as excinfo:
         invalid_app.search("test query")
     assert "Unexpected error during search: Status code 401. Unauthorized: Invalid token" in str(excinfo.value)
 
 def test_llm_extraction():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
-    response = app.scrape_url("https://mendable.ai", {
+    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
+    response = app.scrape_url("https://firecrawl.dev", {
         'extractorOptions': {
             'mode': 'llm-extraction',
             'extractionPrompt': "Based on the information on the page, find what the company's mission is and whether it supports SSO, and whether it is open source",