feat!: migrate Python SDK to v2 API surface

.github/workflows/test.yml

@@ -29,68 +29,18 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install pytest pytest-asyncio responses aioresponses
+        pip install pytest pytest-asyncio responses aioresponses flake8 black isort
         cd scrapegraph-py
         pip install -e ".[html]"
 
-    - name: Run tests
-      run: |
-        cd scrapegraph-py
-        pytest tests/ -v --ignore=tests/test_integration_v2.py
-    - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v3
-      with:
-        file: ./scrapegraph-py/coverage.xml
-        flags: unittests
-        name: codecov-umbrella
-        fail_ci_if_error: false
-
-  lint:
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v4
-
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: "3.11"
-
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install flake8 black isort mypy
-        cd scrapegraph-py
-        pip install -e .
-
-    - name: Run linting
+    - name: Lint
       run: |
         cd scrapegraph-py
-        flake8 scrapegraph_py/ tests/ --max-line-length=120 --extend-ignore=E203,W503,E501,F401,F841
         black --check scrapegraph_py/ tests/
         isort --check-only scrapegraph_py/ tests/
-        mypy scrapegraph_py/ --ignore-missing-imports
-
-  security:
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v4
-
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: "3.11"
-
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install bandit safety
-        cd scrapegraph-py
-        pip install -e .
+        flake8 scrapegraph_py/ tests/ --max-line-length=120 --extend-ignore=E203,W503,E501,F401,F841
 
-    - name: Run security checks
+    - name: Run tests
       run: |
         cd scrapegraph-py
-        bandit -r scrapegraph_py/ -f json -o bandit-report.json || true
-        safety check --json --output safety-report.json || true
+        pytest tests/ -v --ignore=tests/test_integration_v2.py

examples/async_crawl_example.py

@@ -0,0 +1,33 @@
+"""
+Async crawl example.
+"""
+
+import asyncio
+import json
+
+from scrapegraph_py import AsyncClient
+
+
+async def main():
+    async with AsyncClient() as client:
+        # Start crawl
+        job = await client.crawl.start(
+            "https://example.com",
+            depth=2,
+            max_pages=5,
+        )
+        print("Crawl started:", json.dumps(job, indent=2))
+
+        # Poll for completion
+        crawl_id = job["id"]
+        while True:
+            status = await client.crawl.status(crawl_id)
+            print(f"Status: {status.get('status')}")
+            if status.get("status") in ("completed", "failed"):
+                break
+            await asyncio.sleep(2)
+
+        print("\nResult:", json.dumps(status, indent=2))
+
+
+asyncio.run(main())

examples/async_credits_example.py

@@ -0,0 +1,17 @@
+"""
+Async credits check.
+"""
+
+import asyncio
+import json
+
+from scrapegraph_py import AsyncClient
+
+
+async def main():
+    async with AsyncClient() as client:
+        credits = await client.credits()
+        print(json.dumps(credits, indent=2))
+
+
+asyncio.run(main())

examples/async_extract_example.py

@@ -0,0 +1,40 @@
+"""
+Async extract example - extract data from multiple pages concurrently.
+"""
+
+import asyncio
+import json
+
+from pydantic import BaseModel, Field
+
+from scrapegraph_py import AsyncClient
+
+
+class PageInfo(BaseModel):
+    title: str = Field(description="Page title")
+    description: str = Field(description="Brief description of the page content")
+
+
+async def main():
+    async with AsyncClient() as client:
+        urls = [
+            "https://example.com",
+            "https://httpbin.org/html",
+        ]
+
+        tasks = [
+            client.extract(
+                url=url,
+                prompt="Extract the page title and a brief description",
+                output_schema=PageInfo,
+            )
+            for url in urls
+        ]
+        results = await asyncio.gather(*tasks)
+
+        for url, result in zip(urls, results):
+            print(f"\n=== {url} ===")
+            print(json.dumps(result, indent=2))
+
+
+asyncio.run(main())

examples/async_monitor_example.py

@@ -0,0 +1,27 @@
+"""
+Async monitor example.
+"""
+
+import asyncio
+import json
+
+from scrapegraph_py import AsyncClient
+
+
+async def main():
+    async with AsyncClient() as client:
+        # Create a monitor
+        monitor = await client.monitor.create(
+            name="Async Price Tracker",
+            url="https://example.com/products",
+            prompt="Extract product prices",
+            interval="0 12 * * *",  # Every day at noon
+        )
+        print("Created:", json.dumps(monitor, indent=2))
+
+        # List all monitors
+        all_monitors = await client.monitor.list()
+        print("\nAll monitors:", json.dumps(all_monitors, indent=2))
+
+
+asyncio.run(main())

examples/async_scrape_example.py

@@ -0,0 +1,27 @@
+"""
+Async scrape example - scrape multiple pages concurrently.
+"""
+
+import asyncio
+import json
+
+from scrapegraph_py import AsyncClient
+
+
+async def main():
+    async with AsyncClient() as client:
+        # Scrape multiple pages concurrently
+        urls = [
+            "https://example.com",
+            "https://httpbin.org/html",
+        ]
+
+        tasks = [client.scrape(url) for url in urls]
+        results = await asyncio.gather(*tasks)
+
+        for url, result in zip(urls, results):
+            print(f"\n=== {url} ===")
+            print(json.dumps(result, indent=2))
+
+
+asyncio.run(main())

examples/async_search_example.py

@@ -0,0 +1,26 @@
+"""
+Async search example - run multiple searches concurrently.
+"""
+
+import asyncio
+import json
+
+from scrapegraph_py import AsyncClient
+
+
+async def main():
+    async with AsyncClient() as client:
+        queries = [
+            "best python frameworks 2025",
+            "top javascript libraries 2025",
+        ]
+
+        tasks = [client.search(q, num_results=3) for q in queries]
+        results = await asyncio.gather(*tasks)
+
+        for query, result in zip(queries, results):
+            print(f"\n=== {query} ===")
+            print(json.dumps(result, indent=2))
+
+
+asyncio.run(main())