thordata-sdk 1.6.0__tar.gz → 1.8.0__tar.gz

{thordata_sdk-1.6.0/src/thordata_sdk.egg-info → thordata_sdk-1.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: thordata-sdk
-Version: 1.6.0
+Version: 1.8.0
 Summary: The Official Python SDK for Thordata - AI Data Infrastructure & Proxy Network.
 Author-email: Thordata Developer Team <support@thordata.com>
 License: MIT
@@ -40,6 +40,8 @@ Requires-Dist: ruff>=0.1.0; extra == "dev"
 Requires-Dist: mypy>=1.0.0; extra == "dev"
 Requires-Dist: types-requests>=2.28.0; extra == "dev"
 Requires-Dist: aioresponses>=0.7.6; extra == "dev"
+Provides-Extra: browser
+Requires-Dist: playwright>=1.40.0; extra == "browser"
 Dynamic: license-file
 
 # Thordata Python SDK
@@ -63,7 +65,7 @@ Dynamic: license-file
 
 ## 📖 Introduction
 
-The **Thordata Python SDK v1.6.0** is a production-ready wrapper for Thordata's AI data infrastructure. It is architected for high reliability, strict type safety, and maximum performance.
+The **Thordata Python SDK v1.8.0** is a production-ready wrapper for Thordata's AI data infrastructure. It is architected for high reliability, strict type safety, and maximum performance.
 
 **Why v1.6.0?**
 *   **🛡️ Bulletproof Networking**: Custom core handles `HTTP`, `HTTPS`, and `SOCKS5h` (Remote DNS) tunneling, solving common SSL/TLS handshake issues in complex network environments.

{thordata_sdk-1.6.0 → thordata_sdk-1.8.0}/README.md

@@ -19,7 +19,7 @@
 
 ## 📖 Introduction
 
-The **Thordata Python SDK v1.6.0** is a production-ready wrapper for Thordata's AI data infrastructure. It is architected for high reliability, strict type safety, and maximum performance.
+The **Thordata Python SDK v1.8.0** is a production-ready wrapper for Thordata's AI data infrastructure. It is architected for high reliability, strict type safety, and maximum performance.
 
 **Why v1.6.0?**
 *   **🛡️ Bulletproof Networking**: Custom core handles `HTTP`, `HTTPS`, and `SOCKS5h` (Remote DNS) tunneling, solving common SSL/TLS handshake issues in complex network environments.

{thordata_sdk-1.6.0 → thordata_sdk-1.8.0}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "thordata-sdk"
-version = "1.6.0"
+version = "1.8.0"
 description = "The Official Python SDK for Thordata - AI Data Infrastructure & Proxy Network."
 readme = "README.md"
 requires-python = ">=3.9"
@@ -61,6 +61,9 @@ dev = [
     "types-requests>=2.28.0",
     "aioresponses>=0.7.6",
 ]
+browser = [
+    "playwright>=1.40.0",
+]
 
 [project.urls]
 "Homepage" = "https://www.thordata.com"
@@ -115,6 +118,7 @@ check_untyped_defs = false
 strict_optional = false
 show_error_codes = true
 ignore_missing_imports = true
+follow_imports = "skip"
 
 [[tool.mypy.overrides]]
 module = ["aiohttp.*", "requests.*"]

{thordata_sdk-1.6.0 → thordata_sdk-1.8.0}/src/thordata/__init__.py

@@ -5,7 +5,7 @@ Official Python client for Thordata's Proxy Network, SERP API,
 Universal Scraping API (Web Unlocker), and Web Scraper API.
 """
 
-__version__ = "1.6.0"
+__version__ = "1.8.0"
 __author__ = "Thordata Developer Team/Kael Odin"
 __email__ = "support@thordata.com"
 

{thordata_sdk-1.6.0 → thordata_sdk-1.8.0}/src/thordata/async_client.py

@@ -244,6 +244,7 @@ class AsyncThordataClient:
         render_js: bool | None = None,
         no_cache: bool | None = None,
         output_format: str = "json",
+        ai_overview: bool = False,
         **kwargs: Any,
     ) -> dict[str, Any]:
         engine_str = engine.value if isinstance(engine, Engine) else engine.lower()
@@ -258,13 +259,14 @@ class AsyncThordataClient:
             render_js=render_js,
             no_cache=no_cache,
             output_format=output_format,
+            ai_overview=ai_overview,
             extra_params=kwargs,
         )
         return await self.serp_search_advanced(request)
 
     async def serp_search_advanced(self, request: SerpRequest) -> dict[str, Any]:
         if not self.scraper_token:
-            raise ThordataConfigError("scraper_token required")
+            raise ThordataConfigError("scraper_token is required for SERP API")
         payload = request.to_payload()
         headers = build_auth_headers(self.scraper_token, mode=self._auth_mode)
         logger.info(f"Async SERP: {request.engine} - {request.query}")
@@ -293,30 +295,38 @@ class AsyncThordataClient:
         url: str,
         *,
         js_render: bool = False,
-        output_format: str = "html",
+        output_format: str | list[str] = "html",
         country: str | None = None,
         block_resources: str | None = None,
+        clean_content: str | None = None,
         wait: int | None = None,
         wait_for: str | None = None,
+        follow_redirect: bool | None = None,
+        headers: list[dict[str, str]] | None = None,
+        cookies: list[dict[str, str]] | None = None,
         **kwargs: Any,
-    ) -> str | bytes:
+    ) -> str | bytes | dict[str, str | bytes]:
         request = UniversalScrapeRequest(
             url=url,
             js_render=js_render,
             output_format=output_format,
             country=country,
             block_resources=block_resources,
+            clean_content=clean_content,
             wait=wait,
             wait_for=wait_for,
+            follow_redirect=follow_redirect,
+            headers=headers,
+            cookies=cookies,
             extra_params=kwargs,
         )
         return await self.universal_scrape_advanced(request)
 
     async def universal_scrape_advanced(
         self, request: UniversalScrapeRequest
-    ) -> str | bytes:
+    ) -> str | bytes | dict[str, str | bytes]:
         if not self.scraper_token:
-            raise ThordataConfigError("scraper_token required")
+            raise ThordataConfigError("scraper_token is required for Universal API")
         payload = request.to_payload()
         headers = build_auth_headers(self.scraper_token, mode=self._auth_mode)
 
@@ -327,9 +337,17 @@ class AsyncThordataClient:
         try:
             resp_json = await response.json()
         except ValueError:
-            if request.output_format.lower() == "png":
-                return await response.read()
-            return await response.text()
+            # If not JSON, return raw content based on format
+            if isinstance(request.output_format, list) or (
+                isinstance(request.output_format, str) and "," in request.output_format
+            ):
+                return {"raw": await response.read()}
+            fmt = (
+                request.output_format.lower()
+                if isinstance(request.output_format, str)
+                else str(request.output_format).lower()
+            )
+            return await response.read() if fmt == "png" else await response.text()
 
         if isinstance(resp_json, dict):
             code = resp_json.get("code")
@@ -337,6 +355,27 @@ class AsyncThordataClient:
                 msg = extract_error_message(resp_json)
                 raise_for_code(f"Universal Error: {msg}", code=code, payload=resp_json)
 
+        # Handle multiple output formats
+        if isinstance(request.output_format, list) or (
+            isinstance(request.output_format, str) and "," in request.output_format
+        ):
+            result: dict[str, str | bytes] = {}
+            formats = (
+                request.output_format
+                if isinstance(request.output_format, list)
+                else [f.strip() for f in request.output_format.split(",")]
+            )
+
+            for fmt in formats:
+                fmt_lower = fmt.lower()
+                if fmt_lower == "html" and "html" in resp_json:
+                    result["html"] = resp_json["html"]
+                elif fmt_lower == "png" and "png" in resp_json:
+                    result["png"] = decode_base64_image(resp_json["png"])
+
+            if result:
+                return result
+
         if "html" in resp_json:
             return resp_json["html"]
         if "png" in resp_json:
@@ -411,7 +450,7 @@ class AsyncThordataClient:
     async def create_scraper_task_advanced(self, config: ScraperTaskConfig) -> str:
         self._require_public_credentials()
         if not self.scraper_token:
-            raise ThordataConfigError("scraper_token required")
+            raise ThordataConfigError("scraper_token is required for Task Builder")
         payload = config.to_payload()
         headers = build_builder_headers(
             self.scraper_token, str(self.public_token), str(self.public_key)
@@ -449,7 +488,9 @@ class AsyncThordataClient:
     async def create_video_task_advanced(self, config: VideoTaskConfig) -> str:
         self._require_public_credentials()
         if not self.scraper_token:
-            raise ThordataConfigError("scraper_token required")
+            raise ThordataConfigError(
+                "scraper_token is required for Video Task Builder"
+            )
         payload = config.to_payload()
         headers = build_builder_headers(
             self.scraper_token, str(self.public_token), str(self.public_key)
@@ -1067,3 +1108,28 @@ class AsyncThordataClient:
         safe_user = quote(final_user, safe="")
         safe_pass = quote(pwd, safe="")
         return f"wss://{safe_user}:{safe_pass}@ws-browser.thordata.com"
+
+    @property
+    def browser(self):
+        """Get a browser session for automation.
+
+        Requires playwright: pip install thordata[browser]
+
+        Returns:
+            BrowserSession instance
+
+        Example:
+            async with AsyncThordataClient() as client:
+                session = client.browser
+                await session.navigate("https://example.com")
+                snapshot = await session.snapshot()
+        """
+        try:
+            from .browser import BrowserSession
+
+            return BrowserSession(self)
+        except ImportError as e:
+            raise ImportError(
+                "Playwright is required for browser automation. "
+                "Install it with: pip install thordata[browser]"
+            ) from e

thordata_sdk-1.8.0/src/thordata/browser/__init__.py

@@ -0,0 +1,16 @@
+"""Browser automation module for Thordata Scraping Browser.
+
+This module provides high-level browser automation capabilities using Playwright.
+Requires optional dependency: pip install thordata[browser]
+"""
+
+from __future__ import annotations
+
+try:
+    from .exceptions import BrowserConnectionError, BrowserError
+    from .session import BrowserSession
+
+    __all__ = ["BrowserSession", "BrowserError", "BrowserConnectionError"]
+except ImportError:
+    # Playwright not installed
+    __all__ = []

thordata_sdk-1.8.0/src/thordata/browser/exceptions.py

@@ -0,0 +1,23 @@
+"""Browser automation exceptions."""
+
+from __future__ import annotations
+
+from ..exceptions import ThordataError
+
+
+class BrowserError(ThordataError):
+    """Base exception for browser automation errors."""
+
+    pass
+
+
+class BrowserConnectionError(BrowserError):
+    """Raised when browser connection fails."""
+
+    pass
+
+
+class BrowserSessionError(BrowserError):
+    """Raised when browser session operations fail."""
+
+    pass