AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-15 02:25:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

e2e tests for python methods

Browse Source
This commit is contained in:
rafaelmmiller 2025-05-14 15:41:39 -03:00
parent f0b0afc5d6
commit 06cf6be9d5
18 changed files with 987 additions and 111 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

122
apps/python-sdk/tests/e2e/async/test_async_batch_scrape.py
View File

@ -1,9 +1,11 @@
import os
import pytest
import sys
from dotenv import load_dotenv
from firecrawl.firecrawl import AsyncFirecrawlApp
import asyncio
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../../')))
from firecrawl.firecrawl import AsyncFirecrawlApp, JsonConfig, LocationConfig, WaitAction, ScreenshotAction, WriteAction, PressAction, ScrollAction, ExecuteJavascriptAction
load_dotenv()
@ -12,7 +14,117 @@ API_KEY = os.getenv("TEST_API_KEY")
app = AsyncFirecrawlApp(api_url=API_URL, api_key=API_KEY)
TEST_URLS = [
"https://example.com",
"https://www.iana.org"
]
async def wait_for_batch_completion(app, job_id, timeout=60):
for _ in range(timeout):
status = await app.check_batch_scrape_status(job_id)
if status.status == "completed":
return status
await asyncio.sleep(1)
raise TimeoutError("Batch scrape did not complete in time")
@pytest.mark.asyncio
async def test_async_batch_scrape_urls_async_placeholder():
# TODO: Implement async E2E tests for async_batch_scrape_urls
assert True
async def test_async_batch_scrape_urls_simple():
job = await app.async_batch_scrape_urls(
TEST_URLS,
formats=["markdown"]
)
assert job.id is not None
status = await wait_for_batch_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) == len(TEST_URLS)
assert any("Example Domain" in doc.markdown for doc in status.data)
assert any("Internet Assigned Numbers" in doc.markdown for doc in status.data)
@pytest.mark.asyncio
async def test_async_batch_scrape_urls_all_params_with_extract():
location = LocationConfig(country="us", languages=["en"])
extract_schema = {"type": "object", "properties": {"title": {"type": "string"}}}
extract = JsonConfig(prompt="Extract the title", schema=extract_schema)
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
job = await app.async_batch_scrape_urls(
TEST_URLS,
formats=["markdown", "html", "raw_html", "links", "screenshot", "extract"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
extract=extract,
actions=actions
)
assert job.id is not None
status = await wait_for_batch_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) == len(TEST_URLS)
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "extract")
assert hasattr(doc, "metadata")
@pytest.mark.asyncio
async def test_async_batch_scrape_urls_all_params_with_json_options():
location = LocationConfig(country="us", languages=["en"])
json_schema = {"type": "object", "properties": {"title": {"type": "string"}}}
json_options = JsonConfig(prompt="Extract the title as JSON", schema=json_schema)
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
job = await app.async_batch_scrape_urls(
TEST_URLS,
formats=["markdown", "html", "raw_html", "links", "screenshot", "json"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
json_options=json_options,
actions=actions
)
assert job.id is not None
status = await wait_for_batch_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) == len(TEST_URLS)
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "json")
assert hasattr(doc, "metadata")

86
apps/python-sdk/tests/e2e/async/test_async_crawl.py
View File

@ -1,7 +1,11 @@
import os
import sys
import pytest
import asyncio
from dotenv import load_dotenv
from firecrawl import AsyncFirecrawlApp
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../../')))
from firecrawl.firecrawl import AsyncFirecrawlApp, LocationConfig, WaitAction, ScreenshotAction, WriteAction, PressAction, ScrollAction, ExecuteJavascriptAction, ScrapeOptions
load_dotenv()
@ -10,7 +14,81 @@ API_KEY = os.getenv("TEST_API_KEY")
app = AsyncFirecrawlApp(api_url=API_URL, api_key=API_KEY)
TEST_URL = "https://example.com"
async def wait_for_crawl_completion(app, job_id, timeout=60):
for _ in range(timeout):
status = await app.check_crawl_status(job_id)
if status.status == "completed":
return status
await asyncio.sleep(1)
raise TimeoutError("Crawl did not complete in time")
@pytest.mark.asyncio
async def test_async_crawl_url_async_placeholder():
# TODO: Implement async E2E tests for async_crawl_url
assert True
async def test_async_crawl_url_simple():
job = await app.async_crawl_url(
TEST_URL,
limit=1,
scrape_options=ScrapeOptions(formats=["markdown"])
)
assert job.id is not None
status = await wait_for_crawl_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) >= 1
assert any("Example Domain" in doc.markdown for doc in status.data)
@pytest.mark.asyncio
async def test_async_crawl_url_all_params():
location = LocationConfig(country="us", languages=["en"])
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
scrape_options = ScrapeOptions(
formats=["markdown", "html", "raw_html", "links", "screenshot"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
actions=actions
)
job = await app.async_crawl_url(
TEST_URL,
include_paths=["/"],
exclude_paths=["/notarealpage"],
max_depth=2,
max_discovery_depth=2,
limit=2,
allow_backward_links=True,
allow_external_links=True,
ignore_sitemap=True,
scrape_options=scrape_options,
deduplicate_similar_urls=True,
ignore_query_parameters=True,
regex_on_full_url=True,
delay=1
)
assert job.id is not None
status = await wait_for_crawl_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) >= 1
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "metadata")

12
apps/python-sdk/tests/e2e/async/test_batch_scrape.py
View File

@ -42,11 +42,11 @@ async def test_batch_scrape_urls_async_all_params_with_extract():
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="executeJavascript", script="function getTitle() { return document.title; }; getTitle();")
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
result = await app.batch_scrape_urls(
TEST_URLS,
formats=["markdown", "html", "rawHtml", "links", "screenshot", "extract"],
formats=["markdown", "html", "raw_html", "links", "screenshot", "extract"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
@ -68,7 +68,7 @@ async def test_batch_scrape_urls_async_all_params_with_extract():
for doc in result.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "rawHtml")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "extract")
@ -85,11 +85,11 @@ async def test_batch_scrape_urls_async_all_params_with_json_options():
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="executeJavascript", script="function getTitle() { return document.title; }; getTitle();")
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
result = await app.batch_scrape_urls(
TEST_URLS,
formats=["markdown", "html", "rawHtml", "links", "screenshot", "json"],
formats=["markdown", "html", "raw_html", "links", "screenshot", "json"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
@ -110,7 +110,7 @@ async def test_batch_scrape_urls_async_all_params_with_json_options():
for doc in result.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "rawHtml")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "json")

16
apps/python-sdk/tests/e2e/async/test_check_crawl_status.py
View File

@ -1,16 +0,0 @@
import os
import pytest
from dotenv import load_dotenv
from firecrawl import AsyncFirecrawlApp
load_dotenv()
API_URL = "https://api.firecrawl.dev"
API_KEY = os.getenv("TEST_API_KEY")
app = AsyncFirecrawlApp(api_url=API_URL, api_key=API_KEY)
@pytest.mark.asyncio
async def test_check_crawl_status_async_placeholder():
# TODO: Implement async E2E tests for check_crawl_status
assert True

86
apps/python-sdk/tests/e2e/async/test_crawl.py
View File

@ -1,7 +1,11 @@
import os
import sys
import pytest
import asyncio
from dotenv import load_dotenv
from firecrawl import AsyncFirecrawlApp
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../../')))
from firecrawl.firecrawl import AsyncFirecrawlApp, LocationConfig, WaitAction, ScreenshotAction, WriteAction, PressAction, ScrollAction, ExecuteJavascriptAction, ScrapeOptions
load_dotenv()
@ -10,7 +14,81 @@ API_KEY = os.getenv("TEST_API_KEY")
app = AsyncFirecrawlApp(api_url=API_URL, api_key=API_KEY)
TEST_URL = "https://example.com"
async def wait_for_crawl_completion(app, job_id, timeout=60):
for _ in range(timeout):
status = await app.check_crawl_status(job_id)
if status.status == "completed":
return status
await asyncio.sleep(1)
raise TimeoutError("Crawl did not complete in time")
@pytest.mark.asyncio
async def test_crawl_url_async_placeholder():
# TODO: Implement async E2E tests for crawl_url
assert True
async def test_crawl_url_async_simple():
job = await app.async_crawl_url(
TEST_URL,
limit=1,
scrape_options=ScrapeOptions(formats=["markdown"])
)
assert job.id is not None
status = await wait_for_crawl_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) >= 1
assert any("Example Domain" in doc.markdown for doc in status.data)
@pytest.mark.asyncio
async def test_crawl_url_async_all_params():
location = LocationConfig(country="us", languages=["en"])
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
scrape_options = ScrapeOptions(
formats=["markdown", "html", "raw_html", "links", "screenshot"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
actions=actions
)
job = await app.async_crawl_url(
TEST_URL,
include_paths=["/"],
exclude_paths=["/notarealpage"],
max_depth=2,
max_discovery_depth=2,
limit=2,
allow_backward_links=True,
allow_external_links=True,
ignore_sitemap=True,
scrape_options=scrape_options,
deduplicate_similar_urls=True,
ignore_query_parameters=True,
regex_on_full_url=True,
delay=1
)
assert job.id is not None
status = await wait_for_crawl_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) >= 1
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "metadata")

40
apps/python-sdk/tests/e2e/async/test_deep_research.py
View File

@ -1,7 +1,10 @@
import os
import sys
import pytest
from dotenv import load_dotenv
from firecrawl import AsyncFirecrawlApp
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../../')))
from firecrawl.firecrawl import AsyncFirecrawlApp
load_dotenv()
@ -11,6 +14,35 @@ API_KEY = os.getenv("TEST_API_KEY")
app = AsyncFirecrawlApp(api_url=API_URL, api_key=API_KEY)
@pytest.mark.asyncio
async def test_deep_research_async_placeholder():
# TODO: Implement async E2E tests for deep_research
assert True
async def test_deep_research_async_simple():
result = await app.deep_research("What is the capital of France?", max_urls=2)
assert hasattr(result, "status")
assert result.status == "completed"
assert hasattr(result, "success")
assert result.success
assert hasattr(result, "data")
assert result.data is not None
assert any("Paris" in str(result.data) or "France" in str(result.data) for _ in [0])
@pytest.mark.asyncio
async def test_deep_research_async_all_params():
result = await app.deep_research(
"What are the latest advancements in AI?",
max_depth=2,
time_limit=60,
max_urls=3,
analysis_prompt="Summarize the most important recent AI advancements.",
system_prompt="You are an expert AI researcher."
)
assert hasattr(result, "status")
assert result.status == "completed"
assert hasattr(result, "success")
assert result.success
assert hasattr(result, "data")
assert hasattr(result, "activities")
assert isinstance(result.activities, list)
assert result.data is not None
assert hasattr(result.data, "sources")
assert isinstance(result.data.sources, list)
assert hasattr(result.data, "final_analysis")
assert isinstance(result.data.final_analysis, str)

91
apps/python-sdk/tests/e2e/async/test_extract.py
View File

@ -1,7 +1,12 @@
import os
import sys
import pytest
from dotenv import load_dotenv
from firecrawl import AsyncFirecrawlApp
from pydantic import BaseModel
from typing import List
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../../')))
from firecrawl.firecrawl import AsyncFirecrawlApp
load_dotenv()
@ -10,7 +15,85 @@ API_KEY = os.getenv("TEST_API_KEY")
app = AsyncFirecrawlApp(api_url=API_URL, api_key=API_KEY)
class ExtractSchema(BaseModel):
title: str
description: str
links: List[str]
@pytest.mark.asyncio
async def test_extract_async_placeholder():
# TODO: Implement async E2E tests for extract
assert True
async def test_extract_async_simple_schema_class():
result = await app.extract(
["https://example.com"],
prompt="Extract the title, description, and links from the website",
schema=ExtractSchema
)
assert result.success
assert result.data is not None
assert hasattr(result.data, "title")
assert hasattr(result.data, "description")
assert hasattr(result.data, "links")
assert isinstance(result.data.links, list)
@pytest.mark.asyncio
async def test_extract_async_simple_schema_dict():
result = await app.extract(
["https://example.com"],
prompt="Extract the title, description, and links from the website",
schema=ExtractSchema.schema()
)
assert result.success
assert result.data is not None
assert hasattr(result.data, "title")
assert hasattr(result.data, "description")
assert hasattr(result.data, "links")
assert isinstance(result.data.links, list)
@pytest.mark.asyncio
async def test_extract_async_simple_schema_json():
# Try both model_json_schema (Pydantic v2) and schema_json (Pydantic v1)
schema = None
if hasattr(ExtractSchema, "model_json_schema"):
schema = ExtractSchema.model_json_schema()
elif hasattr(ExtractSchema, "schema_json"):
schema = ExtractSchema.schema_json()
else:
pytest.skip("No JSON schema export method available on ExtractSchema")
result = await app.extract(
["https://example.com"],
prompt="Extract the title, description, and links from the website",
schema=schema
)
assert result.success
assert result.data is not None
assert hasattr(result.data, "title")
assert hasattr(result.data, "description")
assert hasattr(result.data, "links")
assert isinstance(result.data.links, list)
@pytest.mark.asyncio
async def test_extract_async_all_params():
class AllParamsSchema(BaseModel):
title: str
description: str
links: List[str]
author: str
schema = AllParamsSchema.schema()
result = await app.extract(
["https://www.iana.org"],
prompt="Extract the title, description, links, and author from the website",
schema=schema,
system_prompt="You are a helpful extraction agent.",
allow_external_links=True,
enable_web_search=True,
show_sources=True,
agent={"model": "FIRE-1"}
)
assert result.success
assert result.data is not None
assert hasattr(result.data, "title")
assert hasattr(result.data, "description")
assert hasattr(result.data, "links")
assert hasattr(result.data, "author")
assert isinstance(result.data.links, list)
assert hasattr(result, "sources")
assert isinstance(result.sources, list)

35
apps/python-sdk/tests/e2e/async/test_generate_llms_text.py
View File

@ -1,7 +1,10 @@
import os
import sys
import pytest
from dotenv import load_dotenv
from firecrawl import AsyncFirecrawlApp
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../../')))
from firecrawl.firecrawl import AsyncFirecrawlApp
load_dotenv()
@ -11,6 +14,30 @@ API_KEY = os.getenv("TEST_API_KEY")
app = AsyncFirecrawlApp(api_url=API_URL, api_key=API_KEY)
@pytest.mark.asyncio
async def test_generate_llms_text_async_placeholder():
# TODO: Implement async E2E tests for generate_llms_text
assert True
async def test_generate_llms_text_async_simple():
result = await app.generate_llms_text("https://example.com")
assert hasattr(result, "status")
assert result.status == "completed"
assert hasattr(result, "data")
assert result.data is not None
assert hasattr(result.data, "llmstxt")
assert isinstance(result.data.llmstxt, str)
assert len(result.data.llmstxt) > 0
@pytest.mark.asyncio
async def test_generate_llms_text_async_all_params():
result = await app.generate_llms_text(
"https://www.iana.org",
max_urls=5,
show_full_text=True,
experimental_stream=True
)
assert hasattr(result, "status")
assert result.status == "completed"
assert hasattr(result, "data")
assert result.data is not None
assert hasattr(result.data, "llmstxt")
assert isinstance(result.data.llmstxt, str)
assert len(result.data.llmstxt) > 0
assert hasattr(result.data, "llmsfulltxt")
assert result.data.llmsfulltxt is None or isinstance(result.data.llmsfulltxt, str)

24
apps/python-sdk/tests/e2e/async/test_scrape.py
View File

@ -40,11 +40,11 @@ async def test_scrape_url_async_all_params_with_extract_screenshot():
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="executeJavascript", script="function getTitle() { return document.title; }; getTitle();")
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
response = await app.scrape_url(
url=TEST_URL,
formats=["markdown", "html", "rawHtml", "links", "screenshot", "extract", "changeTracking"],
formats=["markdown", "html", "raw_html", "links", "screenshot", "extract", "change_tracking"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
@ -64,12 +64,12 @@ async def test_scrape_url_async_all_params_with_extract_screenshot():
assert response.success
assert hasattr(response, "markdown")
assert hasattr(response, "html")
assert hasattr(response, "rawHtml")
assert hasattr(response, "raw_html")
assert hasattr(response, "links")
assert hasattr(response, "screenshot")
assert hasattr(response, "extract")
assert hasattr(response, "metadata")
assert hasattr(response, "changeTracking")
assert hasattr(response, "change_tracking")
@pytest.mark.asyncio
async def test_scrape_url_async_all_params_with_extract_full_page_screenshot():
@ -83,11 +83,11 @@ async def test_scrape_url_async_all_params_with_extract_full_page_screenshot():
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="executeJavascript", script="function getTitle() { return document.title; }; getTitle();")
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
response = await app.scrape_url(
url=TEST_URL,
formats=["markdown", "html", "rawHtml", "links", "screenshot@fullPage", "extract", "changeTracking"],
formats=["markdown", "html", "raw_html", "links", "screenshot@full_page", "extract", "change_tracking"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
@ -107,12 +107,12 @@ async def test_scrape_url_async_all_params_with_extract_full_page_screenshot():
assert response.success
assert hasattr(response, "markdown")
assert hasattr(response, "html")
assert hasattr(response, "rawHtml")
assert hasattr(response, "raw_html")
assert hasattr(response, "links")
assert hasattr(response, "screenshot")
assert hasattr(response, "extract")
assert hasattr(response, "metadata")
assert hasattr(response, "changeTracking")
assert hasattr(response, "change_tracking")
@pytest.mark.asyncio
async def test_scrape_url_async_all_params_with_json_options():
@ -126,11 +126,11 @@ async def test_scrape_url_async_all_params_with_json_options():
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="executeJavascript", script="function getTitle() { return document.title; }; getTitle();")
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
response = await app.scrape_url(
url=TEST_URL,
formats=["markdown", "html", "rawHtml", "links", "screenshot", "json", "changeTracking"],
formats=["markdown", "html", "raw_html", "links", "screenshot", "json", "change_tracking"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
@ -150,9 +150,9 @@ async def test_scrape_url_async_all_params_with_json_options():
assert response.success
assert hasattr(response, "markdown")
assert hasattr(response, "html")
assert hasattr(response, "rawHtml")
assert hasattr(response, "raw_html")
assert hasattr(response, "links")
assert hasattr(response, "screenshot")
assert hasattr(response, "json")
assert hasattr(response, "metadata")
assert hasattr(response, "changeTracking")
assert hasattr(response, "change_tracking")

119
apps/python-sdk/tests/e2e/test_async_batch_scrape.py
View File

@ -1,7 +1,10 @@
import os
import pytest
from dotenv import load_dotenv
from firecrawl import FirecrawlApp
import sys
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../')))
from firecrawl.firecrawl import FirecrawlApp, JsonConfig, LocationConfig, WaitAction, ScreenshotAction, WriteAction, PressAction, ScrollAction, ExecuteJavascriptAction
load_dotenv()
@ -10,6 +13,114 @@ API_KEY = os.getenv("TEST_API_KEY")
app = FirecrawlApp(api_url=API_URL, api_key=API_KEY)
def test_async_batch_scrape_urls_placeholder():
# TODO: Implement E2E tests for async_batch_scrape_urls
assert True
TEST_URLS = [
"https://example.com",
"https://www.iana.org"
]
def wait_for_batch_completion(app, job_id, timeout=60):
for _ in range(timeout):
status = app.check_batch_scrape_status(job_id)
if status.status == "completed":
return status
import time; time.sleep(1)
raise TimeoutError("Batch scrape did not complete in time")
def test_async_batch_scrape_urls_simple():
job = app.async_batch_scrape_urls(
TEST_URLS,
formats=["markdown"]
)
assert job.id is not None
status = wait_for_batch_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) == len(TEST_URLS)
assert any("Example Domain" in doc.markdown for doc in status.data)
assert any("Internet Assigned Numbers Authority" in doc.markdown for doc in status.data)
def test_async_batch_scrape_urls_all_params_with_extract():
location = LocationConfig(country="us", languages=["en"])
extract_schema = {"type": "object", "properties": {"title": {"type": "string"}}}
extract = JsonConfig(prompt="Extract the title", schema=extract_schema)
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
job = app.async_batch_scrape_urls(
TEST_URLS,
formats=["markdown", "html", "raw_html", "links", "screenshot", "extract"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
extract=extract,
actions=actions
)
assert job.id is not None
status = wait_for_batch_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) == len(TEST_URLS)
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "extract")
assert hasattr(doc, "metadata")
def test_async_batch_scrape_urls_all_params_with_json_options():
location = LocationConfig(country="us", languages=["en"])
json_schema = {"type": "object", "properties": {"title": {"type": "string"}}}
json_options = JsonConfig(prompt="Extract the title as JSON", schema=json_schema)
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
job = app.async_batch_scrape_urls(
TEST_URLS,
formats=["markdown", "html", "raw_html", "links", "screenshot", "json"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
json_options=json_options,
actions=actions
)
assert job.id is not None
status = wait_for_batch_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) == len(TEST_URLS)
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "json")
assert hasattr(doc, "metadata")

84
apps/python-sdk/tests/e2e/test_async_crawl.py
View File

@ -1,7 +1,10 @@
import os
import pytest
import sys
from dotenv import load_dotenv
from firecrawl import FirecrawlApp
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../')))
from firecrawl.firecrawl import FirecrawlApp, LocationConfig, WaitAction, ScreenshotAction, WriteAction, PressAction, ScrollAction, ExecuteJavascriptAction, ScrapeOptions
load_dotenv()
@ -10,6 +13,79 @@ API_KEY = os.getenv("TEST_API_KEY")
app = FirecrawlApp(api_url=API_URL, api_key=API_KEY)
def test_async_crawl_url_placeholder():
# TODO: Implement E2E tests for async_crawl_url
assert True
TEST_URL = "https://example.com"
def wait_for_crawl_completion(app, job_id, timeout=60):
for _ in range(timeout):
status = app.check_crawl_status(job_id)
if status.status == "completed":
return status
import time; time.sleep(1)
raise TimeoutError("Crawl did not complete in time")
def test_crawl_url_simple():
job = app.async_crawl_url(
TEST_URL,
limit=1,
scrape_options=ScrapeOptions(formats=["markdown"])
)
assert job.id is not None
status = wait_for_crawl_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) >= 1
assert any("Example Domain" in doc.markdown for doc in status.data)
def test_crawl_url_all_params():
location = LocationConfig(country="us", languages=["en"])
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
scrape_options = ScrapeOptions(
formats=["markdown", "html", "raw_html", "links", "screenshot"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
actions=actions
)
job = app.async_crawl_url(
TEST_URL,
include_paths=["/"],
exclude_paths=["/notarealpage"],
max_depth=2,
max_discovery_depth=2,
limit=2,
allow_backward_links=True,
allow_external_links=True,
ignore_sitemap=True,
scrape_options=scrape_options,
deduplicate_similar_urls=True,
ignore_query_parameters=True,
regex_on_full_url=True,
delay=1
)
assert job.id is not None
status = wait_for_crawl_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) >= 1
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "metadata")

119
apps/python-sdk/tests/e2e/test_batch_scrape.py
View File

@ -1,7 +1,10 @@
import os
import pytest
from dotenv import load_dotenv
from firecrawl import FirecrawlApp
import sys
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../')))
from firecrawl.firecrawl import FirecrawlApp, JsonConfig, LocationConfig, WaitAction, ScreenshotAction, WriteAction, PressAction, ScrollAction, ExecuteJavascriptAction
load_dotenv()
@ -10,6 +13,114 @@ API_KEY = os.getenv("TEST_API_KEY")
app = FirecrawlApp(api_url=API_URL, api_key=API_KEY)
def test_batch_scrape_urls_placeholder():
# TODO: Implement E2E tests for batch_scrape_urls
assert True
TEST_URLS = [
"https://example.com",
"https://www.iana.org"
]
def wait_for_batch_completion(app, job_id, timeout=60):
for _ in range(timeout):
status = app.check_batch_scrape_status(job_id)
if status.status == "completed":
return status
import time; time.sleep(1)
raise TimeoutError("Batch scrape did not complete in time")
def test_batch_scrape_urls_simple():
job = app.async_batch_scrape_urls(
TEST_URLS,
formats=["markdown"]
)
assert job.id is not None
status = wait_for_batch_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) == len(TEST_URLS)
assert any("Example Domain" in doc.markdown for doc in status.data)
assert any("Internet Assigned Numbers Authority" in doc.markdown for doc in status.data)
def test_batch_scrape_urls_all_params_with_extract():
location = LocationConfig(country="us", languages=["en"])
extract_schema = {"type": "object", "properties": {"title": {"type": "string"}}}
extract = JsonConfig(prompt="Extract the title", schema=extract_schema)
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
job = app.async_batch_scrape_urls(
TEST_URLS,
formats=["markdown", "html", "raw_html", "links", "screenshot", "extract"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
extract=extract,
actions=actions
)
assert job.id is not None
status = wait_for_batch_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) == len(TEST_URLS)
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "extract")
assert hasattr(doc, "metadata")
def test_batch_scrape_urls_all_params_with_json_options():
location = LocationConfig(country="us", languages=["en"])
json_schema = {"type": "object", "properties": {"title": {"type": "string"}}}
json_options = JsonConfig(prompt="Extract the title as JSON", schema=json_schema)
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
job = app.async_batch_scrape_urls(
TEST_URLS,
formats=["markdown", "html", "raw_html", "links", "screenshot", "json"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
json_options=json_options,
actions=actions
)
assert job.id is not None
status = wait_for_batch_completion(app, job.id)
assert status.success
assert hasattr(status, "data")
assert len(status.data) == len(TEST_URLS)
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "json")
assert hasattr(doc, "metadata")

15
apps/python-sdk/tests/e2e/test_check_crawl_status.py
View File

@ -1,15 +0,0 @@
import os
import pytest
from dotenv import load_dotenv
from firecrawl import FirecrawlApp
load_dotenv()
API_URL = "https://api.firecrawl.dev"
API_KEY = os.getenv("TEST_API_KEY")
app = FirecrawlApp(api_url=API_URL, api_key=API_KEY)
def test_check_crawl_status_placeholder():
# TODO: Implement E2E tests for check_crawl_status
assert True

73
apps/python-sdk/tests/e2e/test_crawl.py
View File

@ -1,7 +1,9 @@
import os
import pytest
import sys
from dotenv import load_dotenv
from firecrawl import FirecrawlApp
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../')))
from firecrawl.firecrawl import FirecrawlApp, LocationConfig, WaitAction, ScreenshotAction, WriteAction, PressAction, ScrollAction, ExecuteJavascriptAction, ScrapeOptions
load_dotenv()
@ -10,6 +12,67 @@ API_KEY = os.getenv("TEST_API_KEY")
app = FirecrawlApp(api_url=API_URL, api_key=API_KEY)
def test_crawl_url_placeholder():
# TODO: Implement E2E tests for crawl_url
assert True
TEST_URL = "https://example.com"
def test_crawl_url_simple():
status = app.crawl_url(
TEST_URL,
limit=1,
scrape_options=ScrapeOptions(formats=["markdown"])
)
assert status.success
assert hasattr(status, "data")
assert len(status.data) >= 1
assert any("Example Domain" in doc.markdown for doc in status.data)
def test_crawl_url_all_params():
location = LocationConfig(country="us", languages=["en"])
actions = [
WaitAction(type="wait", milliseconds=500),
ScreenshotAction(type="screenshot", fullPage=True),
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
scrape_options = ScrapeOptions(
formats=["markdown", "html", "raw_html", "links", "screenshot"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
wait_for=1000,
timeout=15000,
location=location,
mobile=True,
skip_tls_verification=True,
remove_base64_images=True,
block_ads=True,
proxy="basic",
actions=actions
)
status = app.crawl_url(
TEST_URL,
include_paths=["/"],
exclude_paths=["/notarealpage"],
max_depth=2,
max_discovery_depth=2,
limit=2,
allow_backward_links=True,
allow_external_links=True,
ignore_sitemap=True,
scrape_options=scrape_options,
deduplicate_similar_urls=True,
ignore_query_parameters=True,
regex_on_full_url=True,
delay=1
)
assert status.success
assert hasattr(status, "data")
assert len(status.data) >= 1
for doc in status.data:
assert hasattr(doc, "markdown")
assert hasattr(doc, "html")
assert hasattr(doc, "raw_html")
assert hasattr(doc, "links")
assert hasattr(doc, "screenshot")
assert hasattr(doc, "metadata")

39
apps/python-sdk/tests/e2e/test_deep_research.py
View File

@ -1,7 +1,10 @@
import os
import sys
import pytest
from dotenv import load_dotenv
from firecrawl import FirecrawlApp
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../')))
from firecrawl.firecrawl import FirecrawlApp
load_dotenv()
@ -10,6 +13,34 @@ API_KEY = os.getenv("TEST_API_KEY")
app = FirecrawlApp(api_url=API_URL, api_key=API_KEY)
def test_deep_research_placeholder():
# TODO: Implement E2E tests for deep_research
assert True
def test_deep_research_simple():
result = app.deep_research("What is the capital of France?", max_urls=2)
assert hasattr(result, "status")
assert result.status == "completed"
assert hasattr(result, "success")
assert result.success
assert hasattr(result, "data")
assert result.data is not None
assert any("Paris" in str(result.data) or "France" in str(result.data) for _ in [0])
def test_deep_research_all_params():
result = app.deep_research(
"What are the latest advancements in AI?",
max_depth=2,
time_limit=60,
max_urls=3,
analysis_prompt="Summarize the most important recent AI advancements.",
system_prompt="You are an expert AI researcher."
)
assert hasattr(result, "status")
assert result.status == "completed"
assert hasattr(result, "success")
assert result.success
assert hasattr(result, "data")
assert hasattr(result, "activities")
assert isinstance(result.activities, list)
assert result.data is not None
assert hasattr(result.data, "sources")
assert isinstance(result.data.sources, list)
assert hasattr(result.data, "final_analysis")
assert isinstance(result.data.final_analysis, str)

87
apps/python-sdk/tests/e2e/test_extract.py
View File

@ -1,7 +1,12 @@
import os
import sys
import pytest
from dotenv import load_dotenv
from firecrawl import FirecrawlApp
from pydantic import BaseModel
from typing import List
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../')))
from firecrawl.firecrawl import FirecrawlApp
load_dotenv()
@ -10,6 +15,80 @@ API_KEY = os.getenv("TEST_API_KEY")
app = FirecrawlApp(api_url=API_URL, api_key=API_KEY)
def test_extract_placeholder():
# TODO: Implement E2E tests for extract
assert True
class ExtractSchema(BaseModel):
title: str
description: str
links: List[str]
def test_extract_simple_schema_class():
result = app.extract(
["https://example.com"],
prompt="Extract the title, description, and links from the website",
schema=ExtractSchema
)
assert result.success
assert result.data is not None
assert hasattr(result.data, "title")
assert hasattr(result.data, "description")
assert hasattr(result.data, "links")
assert isinstance(result.data.links, list)
def test_extract_simple_schema_dict():
result = app.extract(
["https://example.com"],
prompt="Extract the title, description, and links from the website",
schema=ExtractSchema.schema()
)
assert result.success
assert result.data is not None
assert hasattr(result.data, "title")
assert hasattr(result.data, "description")
assert hasattr(result.data, "links")
assert isinstance(result.data.links, list)
def test_extract_simple_schema_json():
schema = None
if hasattr(ExtractSchema, "model_json_schema"):
schema = ExtractSchema.model_json_schema()
elif hasattr(ExtractSchema, "schema_json"):
schema = ExtractSchema.schema_json()
else:
pytest.skip("No JSON schema export method available on ExtractSchema")
result = app.extract(
["https://example.com"],
prompt="Extract the title, description, and links from the website",
schema=schema
)
assert result.success
assert result.data is not None
assert hasattr(result.data, "title")
assert hasattr(result.data, "description")
assert hasattr(result.data, "links")
assert isinstance(result.data.links, list)
def test_extract_all_params():
class AllParamsSchema(BaseModel):
title: str
description: str
links: List[str]
author: str
schema = AllParamsSchema.schema()
result = app.extract(
["https://www.iana.org"],
prompt="Extract the title, description, links, and author from the website",
schema=schema,
system_prompt="You are a helpful extraction agent.",
allow_external_links=True,
enable_web_search=True,
show_sources=True,
agent={"model": "FIRE-1"}
)
assert result.success
assert result.data is not None
assert hasattr(result.data, "title")
assert hasattr(result.data, "description")
assert hasattr(result.data, "links")
assert hasattr(result.data, "author")
assert isinstance(result.data.links, list)
assert hasattr(result, "sources")
assert isinstance(result.sources, list)

34
apps/python-sdk/tests/e2e/test_generate_llms_text.py
View File

@ -1,7 +1,10 @@
import os
import sys
import pytest
from dotenv import load_dotenv
from firecrawl import FirecrawlApp
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../')))
from firecrawl.firecrawl import FirecrawlApp
load_dotenv()
@ -10,6 +13,29 @@ API_KEY = os.getenv("TEST_API_KEY")
app = FirecrawlApp(api_url=API_URL, api_key=API_KEY)
def test_generate_llms_text_placeholder():
# TODO: Implement E2E tests for generate_llms_text
assert True
def test_generate_llms_text_simple():
result = app.generate_llms_text("https://example.com")
assert hasattr(result, "status")
assert result.status == "completed"
assert hasattr(result, "data")
assert result.data is not None
assert hasattr(result.data, "llmstxt")
assert isinstance(result.data.llmstxt, str)
assert len(result.data.llmstxt) > 0
def test_generate_llms_text_all_params():
result = app.generate_llms_text(
"https://www.iana.org",
max_urls=5,
show_full_text=True,
experimental_stream=True
)
assert hasattr(result, "status")
assert result.status == "completed"
assert hasattr(result, "data")
assert result.data is not None
assert hasattr(result.data, "llmstxt")
assert isinstance(result.data.llmstxt, str)
assert len(result.data.llmstxt) > 0
assert hasattr(result.data, "llmsfulltxt")
assert result.data.llmsfulltxt is None or isinstance(result.data.llmsfulltxt, str)

16
apps/python-sdk/tests/e2e/test_scrape.py
View File

@ -80,11 +80,11 @@ def test_scrape_url_all_params_with_extract_full_page_screenshot():
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="executeJavascript", script="function getTitle() { return document.title; }; getTitle();")
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
response = app.scrape_url(
url=TEST_URL,
formats=["markdown", "html", "rawHtml", "links", "screenshot@fullPage", "extract", "changeTracking"],
formats=["markdown", "html", "raw_html", "links", "screenshot@full_page", "extract", "change_tracking"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
@ -104,12 +104,12 @@ def test_scrape_url_all_params_with_extract_full_page_screenshot():
assert response.success
assert hasattr(response, "markdown")
assert hasattr(response, "html")
assert hasattr(response, "rawHtml")
assert hasattr(response, "raw_html")
assert hasattr(response, "links")
assert hasattr(response, "screenshot")
assert hasattr(response, "extract")
assert hasattr(response, "metadata")
assert hasattr(response, "changeTracking")
assert hasattr(response, "change_tracking")
def test_scrape_url_all_params_with_json_options():
location = LocationConfig(country="us", languages=["en"])
@ -122,11 +122,11 @@ def test_scrape_url_all_params_with_json_options():
WriteAction(type="write", text="test input"),
PressAction(type="press", key="Enter"),
ScrollAction(type="scroll", direction="down"),
ExecuteJavascriptAction(type="executeJavascript", script="function getTitle() { return document.title; }; getTitle();")
ExecuteJavascriptAction(type="execute_javascript", script="function get_title() { return document.title; }; get_title();")
]
response = app.scrape_url(
url=TEST_URL,
formats=["markdown", "html", "rawHtml", "links", "screenshot", "json", "changeTracking"],
formats=["markdown", "html", "raw_html", "links", "screenshot", "json", "change_tracking"],
include_tags=["h1", "p"],
exclude_tags=["footer"],
only_main_content=True,
@ -146,9 +146,9 @@ def test_scrape_url_all_params_with_json_options():
assert response.success
assert hasattr(response, "markdown")
assert hasattr(response, "html")
assert hasattr(response, "rawHtml")
assert hasattr(response, "raw_html")
assert hasattr(response, "links")
assert hasattr(response, "screenshot")
assert hasattr(response, "json")
assert hasattr(response, "metadata")
assert hasattr(response, "changeTracking")
assert hasattr(response, "change_tracking")