feat!: migrate python SDK to v2 API surface

Port the Python SDK to the new v2 API surface, mirroring scrapegraph-js PR #11.

Breaking changes:
- smartscraper -> extract (POST /api/v1/extract)
- searchscraper -> search (POST /api/v1/search)
- scrape now uses format-specific config (markdown/html/screenshot/branding)
- crawl/monitor are now namespaced: client.crawl.start(), client.monitor.create()
- Removed: markdownify, agenticscraper, sitemap, healthz, feedback, scheduled jobs
- Auth: sends both Authorization: Bearer and SGAI-APIKEY headers
- Added X-SDK-Version header, base_url parameter for custom endpoints
- Version bumped to 2.0.0

Tested against dev API (https://sgai-api-dev-v2.onrender.com/api/v1/scrape):
- Scrape markdown: returns markdown content successfully
- Scrape html: returns content successfully
- All 72 unit tests pass with 81% coverage

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: VinciGit00

scrapegraph-py/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "scrapegraph_py"
-version = "1.12.2"
+version = "2.0.0"
 description = "ScrapeGraph Python SDK for API"
 authors = [
     { name = "Marco Vinciguerra", email = "marco@scrapegraphai.com" },

scrapegraph-py/scrapegraph_py/__init__.py

@@ -1,97 +1,62 @@
-"""
-ScrapeGraphAI Python SDK
-
-A comprehensive Python SDK for the ScrapeGraphAI API, providing both synchronous
-and asynchronous clients for all API endpoints.
-
-Main Features:
-    - SmartScraper: AI-powered web scraping with structured data extraction
-    - SearchScraper: Web research across multiple sources
-    - Agentic Scraper: Automated browser interactions and form filling
-    - Crawl: Website crawling with AI extraction or markdown conversion
-    - Markdownify: Convert web pages to clean markdown
-    - Schema Generation: AI-assisted schema creation for data extraction
-    - Scheduled Jobs: Automate recurring scraping tasks
-
-Quick Start:
-    >>> from scrapegraph_py import Client
-    >>>
-    >>> # Initialize client from environment variables
-    >>> client = Client.from_env()
-    >>>
-    >>> # Basic scraping
-    >>> result = client.smartscraper(
-    ...     website_url="https://example.com",
-    ...     user_prompt="Extract all product information"
-    ... )
-    >>>
-    >>> # With context manager
-    >>> with Client.from_env() as client:
-    ...     result = client.scrape(website_url="https://example.com")
-
-Async Usage:
-    >>> import asyncio
-    >>> from scrapegraph_py import AsyncClient
-    >>>
-    >>> async def main():
-    ...     async with AsyncClient.from_env() as client:
-    ...         result = await client.smartscraper(
-    ...             website_url="https://example.com",
-    ...             user_prompt="Extract products"
-    ...         )
-    >>>
-    >>> asyncio.run(main())
-
-For more information visit: https://scrapegraphai.com
-Documentation: https://docs.scrapegraphai.com
-"""
-
-from .async_client import AsyncClient
-from .client import Client
-
-# Scrape Models
-from .models.scrape import (
-    ScrapeRequest,
-    GetScrapeRequest,
-)
-
-# Scheduled Jobs Models
-from .models.scheduled_jobs import (
-    GetJobExecutionsRequest,
-    GetScheduledJobRequest,
-    GetScheduledJobsRequest,
-    JobActionRequest,
-    JobActionResponse,
-    JobExecutionListResponse,
-    JobExecutionResponse,
-    JobTriggerResponse,
-    ScheduledJobCreate,
-    ScheduledJobListResponse,
-    ScheduledJobResponse,
-    ScheduledJobUpdate,
-    ServiceType,
-    TriggerJobRequest,
-)
-
-__all__ = [
-    "Client", 
-    "AsyncClient",
-    # Scrape Models
-    "ScrapeRequest",
-    "GetScrapeRequest",
-    # Scheduled Jobs Models
-    "ServiceType",
-    "ScheduledJobCreate",
-    "ScheduledJobUpdate", 
-    "ScheduledJobResponse",
-    "ScheduledJobListResponse",
-    "JobExecutionResponse",
-    "JobExecutionListResponse",
-    "JobTriggerResponse",
-    "JobActionResponse",
-    "GetScheduledJobsRequest",
-    "GetScheduledJobRequest",
-    "GetJobExecutionsRequest",
-    "TriggerJobRequest",
-    "JobActionRequest",
-]
+"""
+ScrapeGraphAI Python SDK v2
+
+A Python SDK for the ScrapeGraphAI v2 API, providing both synchronous
+and asynchronous clients for intelligent web scraping powered by AI.
+
+Quick Start:
+    >>> from scrapegraph_py import Client
+    >>> client = Client(api_key="sgai-...")
+    >>> result = client.scrape("https://example.com")
+    >>> result = client.extract("https://example.com", prompt="Extract prices")
+    >>> job = client.crawl.start("https://example.com", depth=3)
+
+Async Usage:
+    >>> import asyncio
+    >>> from scrapegraph_py import AsyncClient
+    >>> async def main():
+    ...     async with AsyncClient(api_key="sgai-...") as client:
+    ...         result = await client.extract(
+    ...             url="https://example.com",
+    ...             prompt="Extract products"
+    ...         )
+    >>> asyncio.run(main())
+"""
+
+from .async_client import AsyncClient
+from .client import Client
+from .config import VERSION
+from .models.crawl import CrawlFormat, CrawlRequest
+from .models.extract import ExtractRequest
+from .models.history import HistoryFilter
+from .models.monitor import MonitorCreateRequest
+from .models.schema import SchemaRequest
+from .models.scrape import ScrapeFormat, ScrapeRequest
+from .models.search import SearchRequest
+from .models.shared import FetchConfig, LlmConfig
+
+__version__ = VERSION
+
+__all__ = [
+    "Client",
+    "AsyncClient",
+    # Shared config
+    "FetchConfig",
+    "LlmConfig",
+    # Scrape
+    "ScrapeFormat",
+    "ScrapeRequest",
+    # Extract
+    "ExtractRequest",
+    # Search
+    "SearchRequest",
+    # Schema
+    "SchemaRequest",
+    # Crawl
+    "CrawlFormat",
+    "CrawlRequest",
+    # Monitor
+    "MonitorCreateRequest",
+    # History
+    "HistoryFilter",
+]