thordata-sdk 1.1.0__tar.gz → 1.2.0__tar.gz

thordata_sdk-1.2.0/PKG-INFO

@@ -0,0 +1,208 @@
+Metadata-Version: 2.4
+Name: thordata-sdk
+Version: 1.2.0
+Summary: The Official Python SDK for Thordata - AI Data Infrastructure & Proxy Network.
+Author-email: Thordata Developer Team <support@thordata.com>
+License: MIT
+Project-URL: Homepage, https://www.thordata.com
+Project-URL: Documentation, https://github.com/Thordata/thordata-python-sdk#readme
+Project-URL: Source, https://github.com/Thordata/thordata-python-sdk
+Project-URL: Tracker, https://github.com/Thordata/thordata-python-sdk/issues
+Project-URL: Changelog, https://github.com/Thordata/thordata-python-sdk/blob/main/CHANGELOG.md
+Keywords: web scraping,proxy,residential proxy,datacenter proxy,ai,llm,data-mining,serp,thordata,web scraper,anti-bot bypass
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Internet :: WWW/HTTP
+Classifier: Topic :: Internet :: Proxy Servers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.25.0
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: PySocks>=1.7.1
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: pytest-httpserver>=1.0.0; extra == "dev"
+Requires-Dist: python-dotenv>=1.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+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"
+Dynamic: license-file
+
+# Thordata Python SDK
+
+<div align="center">
+
+<img src="https://img.shields.io/badge/Thordata-AI%20Infrastructure-blue?style=for-the-badge" alt="Thordata Logo">
+
+**The Official Python Client for Thordata APIs**
+
+*Proxy Network • SERP API • Web Unlocker • Web Scraper API*
+
+[![PyPI version](https://img.shields.io/pypi/v/thordata-sdk.svg?style=flat-square)](https://pypi.org/project/thordata-sdk/)
+[![Python Versions](https://img.shields.io/pypi/pyversions/thordata-sdk.svg?style=flat-square)](https://pypi.org/project/thordata-sdk/)
+[![License](https://img.shields.io/badge/license-MIT-green?style=flat-square)](LICENSE)
+[![CI Status](https://img.shields.io/github/actions/workflow/status/Thordata/thordata-python-sdk/ci.yml?branch=main&style=flat-square)](https://github.com/Thordata/thordata-python-sdk/actions)
+
+</div>
+
+---
+
+## 📖 Introduction
+
+This SDK provides a robust, high-performance interface to Thordata's AI data infrastructure. It is designed for high-concurrency scraping, reliable proxy tunneling, and seamless data extraction.
+
+**Key Features:**
+*   **🚀 Production Ready:** Built on `urllib3` connection pooling for low-latency proxy requests.
+*   **⚡ Async Support:** Native `aiohttp` client for high-concurrency SERP/Universal scraping.
+*   **🛡️ Robust:** Handles TLS-in-TLS tunneling, retries, and error parsing automatically.
+*   **✨ Developer Experience:** Fully typed (`mypy` compatible) with intuitive IDE autocomplete.
+*   **🧩 Lazy Validation:** Only validate credentials for the features you actually use.
+
+---
+
+## 📦 Installation
+
+```bash
+pip install thordata-sdk
+```
+
+---
+
+## 🔐 Configuration
+
+Set environment variables to avoid hardcoding credentials. You only need to set the variables for the features you use.
+
+```bash
+# [Required for SERP & Web Unlocker]
+export THORDATA_SCRAPER_TOKEN="your_token_here"
+
+# [Required for Proxy Network]
+export THORDATA_RESIDENTIAL_USERNAME="your_username"
+export THORDATA_RESIDENTIAL_PASSWORD="your_password"
+export THORDATA_PROXY_HOST="vpnXXXX.pr.thordata.net"
+
+# [Required for Task Management]
+export THORDATA_PUBLIC_TOKEN="public_token"
+export THORDATA_PUBLIC_KEY="public_key"
+```
+
+---
+
+## 🚀 Quick Start
+
+### 1. SERP Search (Google/Bing/Yandex)
+
+```python
+from thordata import ThordataClient, Engine
+
+client = ThordataClient()  # Loads THORDATA_SCRAPER_TOKEN from env
+
+# Simple Search
+print("Searching...")
+results = client.serp_search("latest AI trends", engine=Engine.GOOGLE_NEWS)
+
+for news in results.get("news_results", [])[:3]:
+    print(f"- {news['title']} ({news['source']})")
+```
+
+### 2. Universal Scrape (Web Unlocker)
+
+Bypass Cloudflare/Akamai and render JavaScript automatically.
+
+```python
+html = client.universal_scrape(
+    url="https://example.com/protected-page",
+    js_render=True,
+    wait_for=".content-loaded",
+    country="us"
+)
+print(f"Scraped {len(html)} bytes")
+```
+
+### 3. High-Performance Proxy
+
+Use Thordata's residential IPs with automatic connection pooling.
+
+```python
+from thordata import ProxyConfig, ProxyProduct
+
+# Config is optional if env vars are set, but allows granular control
+proxy = ProxyConfig(
+    product=ProxyProduct.RESIDENTIAL,
+    country="jp",
+    city="tokyo",
+    session_id="session-001",
+    session_duration=10  # Sticky IP for 10 mins
+)
+
+# Use the client to make requests (Reuses TCP connections)
+response = client.get("https://httpbin.org/ip", proxy_config=proxy)
+print(response.json())
+```
+
+---
+
+## ⚙️ Advanced Usage
+
+### Async Client (High Concurrency)
+
+For building AI agents or high-throughput spiders.
+
+```python
+import asyncio
+from thordata import AsyncThordataClient
+
+async def main():
+    async with AsyncThordataClient() as client:
+        # Fire off multiple requests in parallel
+        tasks = [
+            client.serp_search(f"query {i}") 
+            for i in range(5)
+        ]
+        results = await asyncio.gather(*tasks)
+        print(f"Completed {len(results)} searches")
+
+asyncio.run(main())
+```
+
+### Web Scraper API (Task Management)
+
+Create and manage large-scale scraping tasks asynchronously.
+
+```python
+# 1. Create a task
+task_id = client.create_scraper_task(
+    file_name="daily_scrape",
+    spider_id="universal",
+    spider_name="universal",
+    parameters={"url": "https://example.com"}
+)
+
+# 2. Wait for completion (Polling)
+status = client.wait_for_task(task_id)
+
+# 3. Get results
+if status == "ready":
+    url = client.get_task_result(task_id)
+    print(f"Download Data: {url}")
+```
+
+---
+
+## 📄 License
+
+MIT License. See [LICENSE](LICENSE) for details.

thordata_sdk-1.2.0/README.md

@@ -0,0 +1,164 @@
+# Thordata Python SDK
+
+<div align="center">
+
+<img src="https://img.shields.io/badge/Thordata-AI%20Infrastructure-blue?style=for-the-badge" alt="Thordata Logo">
+
+**The Official Python Client for Thordata APIs**
+
+*Proxy Network • SERP API • Web Unlocker • Web Scraper API*
+
+[![PyPI version](https://img.shields.io/pypi/v/thordata-sdk.svg?style=flat-square)](https://pypi.org/project/thordata-sdk/)
+[![Python Versions](https://img.shields.io/pypi/pyversions/thordata-sdk.svg?style=flat-square)](https://pypi.org/project/thordata-sdk/)
+[![License](https://img.shields.io/badge/license-MIT-green?style=flat-square)](LICENSE)
+[![CI Status](https://img.shields.io/github/actions/workflow/status/Thordata/thordata-python-sdk/ci.yml?branch=main&style=flat-square)](https://github.com/Thordata/thordata-python-sdk/actions)
+
+</div>
+
+---
+
+## 📖 Introduction
+
+This SDK provides a robust, high-performance interface to Thordata's AI data infrastructure. It is designed for high-concurrency scraping, reliable proxy tunneling, and seamless data extraction.
+
+**Key Features:**
+*   **🚀 Production Ready:** Built on `urllib3` connection pooling for low-latency proxy requests.
+*   **⚡ Async Support:** Native `aiohttp` client for high-concurrency SERP/Universal scraping.
+*   **🛡️ Robust:** Handles TLS-in-TLS tunneling, retries, and error parsing automatically.
+*   **✨ Developer Experience:** Fully typed (`mypy` compatible) with intuitive IDE autocomplete.
+*   **🧩 Lazy Validation:** Only validate credentials for the features you actually use.
+
+---
+
+## 📦 Installation
+
+```bash
+pip install thordata-sdk
+```
+
+---
+
+## 🔐 Configuration
+
+Set environment variables to avoid hardcoding credentials. You only need to set the variables for the features you use.
+
+```bash
+# [Required for SERP & Web Unlocker]
+export THORDATA_SCRAPER_TOKEN="your_token_here"
+
+# [Required for Proxy Network]
+export THORDATA_RESIDENTIAL_USERNAME="your_username"
+export THORDATA_RESIDENTIAL_PASSWORD="your_password"
+export THORDATA_PROXY_HOST="vpnXXXX.pr.thordata.net"
+
+# [Required for Task Management]
+export THORDATA_PUBLIC_TOKEN="public_token"
+export THORDATA_PUBLIC_KEY="public_key"
+```
+
+---
+
+## 🚀 Quick Start
+
+### 1. SERP Search (Google/Bing/Yandex)
+
+```python
+from thordata import ThordataClient, Engine
+
+client = ThordataClient()  # Loads THORDATA_SCRAPER_TOKEN from env
+
+# Simple Search
+print("Searching...")
+results = client.serp_search("latest AI trends", engine=Engine.GOOGLE_NEWS)
+
+for news in results.get("news_results", [])[:3]:
+    print(f"- {news['title']} ({news['source']})")
+```
+
+### 2. Universal Scrape (Web Unlocker)
+
+Bypass Cloudflare/Akamai and render JavaScript automatically.
+
+```python
+html = client.universal_scrape(
+    url="https://example.com/protected-page",
+    js_render=True,
+    wait_for=".content-loaded",
+    country="us"
+)
+print(f"Scraped {len(html)} bytes")
+```
+
+### 3. High-Performance Proxy
+
+Use Thordata's residential IPs with automatic connection pooling.
+
+```python
+from thordata import ProxyConfig, ProxyProduct
+
+# Config is optional if env vars are set, but allows granular control
+proxy = ProxyConfig(
+    product=ProxyProduct.RESIDENTIAL,
+    country="jp",
+    city="tokyo",
+    session_id="session-001",
+    session_duration=10  # Sticky IP for 10 mins
+)
+
+# Use the client to make requests (Reuses TCP connections)
+response = client.get("https://httpbin.org/ip", proxy_config=proxy)
+print(response.json())
+```
+
+---
+
+## ⚙️ Advanced Usage
+
+### Async Client (High Concurrency)
+
+For building AI agents or high-throughput spiders.
+
+```python
+import asyncio
+from thordata import AsyncThordataClient
+
+async def main():
+    async with AsyncThordataClient() as client:
+        # Fire off multiple requests in parallel
+        tasks = [
+            client.serp_search(f"query {i}") 
+            for i in range(5)
+        ]
+        results = await asyncio.gather(*tasks)
+        print(f"Completed {len(results)} searches")
+
+asyncio.run(main())
+```
+
+### Web Scraper API (Task Management)
+
+Create and manage large-scale scraping tasks asynchronously.
+
+```python
+# 1. Create a task
+task_id = client.create_scraper_task(
+    file_name="daily_scrape",
+    spider_id="universal",
+    spider_name="universal",
+    parameters={"url": "https://example.com"}
+)
+
+# 2. Wait for completion (Polling)
+status = client.wait_for_task(task_id)
+
+# 3. Get results
+if status == "ready":
+    url = client.get_task_result(task_id)
+    print(f"Download Data: {url}")
+```
+
+---
+
+## 📄 License
+
+MIT License. See [LICENSE](LICENSE) for details.

{thordata_sdk-1.1.0 → thordata_sdk-1.2.0}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "thordata-sdk"
-version = "1.1.0"
+version = "1.2.0"
 description = "The Official Python SDK for Thordata - AI Data Infrastructure & Proxy Network."
 readme = "README.md"
 requires-python = ">=3.9"
@@ -45,6 +45,7 @@ classifiers = [
 dependencies = [
     "requests>=2.25.0",
     "aiohttp>=3.9.0",
+    "PySocks>=1.7.1",
 ]
 
 [project.optional-dependencies]
@@ -83,6 +84,7 @@ include = '\.pyi?$'
 [tool.ruff]
 line-length = 88
 target-version = "py39"
+extend-exclude = ["sdk-spec"]
 
 [tool.ruff.lint]
 select = [
@@ -123,6 +125,7 @@ ignore_missing_imports = true
 testpaths = ["tests"]
 asyncio_mode = "auto"
 addopts = "-v --cov=thordata --cov-report=term-missing"
+markers = ["integration: live tests that require real credentials"]
 
 # Coverage setup
 [tool.coverage.run]
@@ -135,4 +138,4 @@ exclude_lines = [
     "def __repr__",
     "raise NotImplementedError",
     "if TYPE_CHECKING:",
-]
+]

{thordata_sdk-1.1.0 → thordata_sdk-1.2.0}/src/thordata/__init__.py

@@ -35,7 +35,7 @@ Async Usage:
     >>> asyncio.run(main())
 """
 
-__version__ = "1.1.0"
+__version__ = "1.2.0"
 __author__ = "Thordata Developer Team"
 __email__ = "support@thordata.com"
 

{thordata_sdk-1.1.0 → thordata_sdk-1.2.0}/src/thordata/async_client.py

@@ -60,6 +60,7 @@ from .models import (
     VideoTaskConfig,
 )
 from .retry import RetryConfig
+from .serp_engines import AsyncSerpNamespace
 
 logger = logging.getLogger(__name__)
 
@@ -85,7 +86,10 @@ class AsyncThordataClient:
         ...     public_token="pub_token",
         ...     public_key="pub_key"
         ... ) as client:
+        ...     # Old style
         ...     results = await client.serp_search("python")
+        ...     # New style (Namespaced)
+        ...     maps_results = await client.serp.google.maps("coffee", "@40.7,-74.0,14z")
     """
 
     # API Endpoints (same as sync client)
@@ -96,7 +100,7 @@ class AsyncThordataClient:
 
     def __init__(
         self,
-        scraper_token: str,
+        scraper_token: str | None = None,  # Change: Optional
         public_token: str | None = None,
         public_key: str | None = None,
         proxy_host: str = "pr.thordata.net",
@@ -111,8 +115,6 @@ class AsyncThordataClient:
         locations_base_url: str | None = None,
     ) -> None:
         """Initialize the Async Thordata Client."""
-        if not scraper_token:
-            raise ThordataConfigError("scraper_token is required")
 
         self.scraper_token = scraper_token
         self.public_token = public_token
@@ -195,7 +197,7 @@ class AsyncThordataClient:
         self._whitelist_url = f"{whitelist_base}/whitelisted-ips"
 
         proxy_api_base = os.getenv(
-            "THORDATA_PROXY_API_BASE_URL", "https://api.thordata.com/api"
+            "THORDATA_PROXY_API_BASE_URL", "https://openapi.thordata.com/api"
         )
         self._proxy_list_url = f"{proxy_api_base}/proxy/proxy-list"
         self._proxy_expiration_url = f"{proxy_api_base}/proxy/expiration-time"
@@ -203,6 +205,9 @@ class AsyncThordataClient:
         # Session initialized lazily
         self._session: aiohttp.ClientSession | None = None
 
+        # Namespaced Access (e.g. client.serp.google.maps(...))
+        self.serp = AsyncSerpNamespace(self)
+
     async def __aenter__(self) -> AsyncThordataClient:
         """Async context manager entry."""
         if self._session is None or self._session.closed:
@@ -386,6 +391,9 @@ class AsyncThordataClient:
         Returns:
             Parsed JSON results or dict with 'html' key.
         """
+        if not self.scraper_token:
+            raise ThordataConfigError("scraper_token is required for SERP API")
+
         session = self._get_session()
 
         engine_str = engine.value if isinstance(engine, Engine) else engine.lower()
@@ -405,7 +413,8 @@ class AsyncThordataClient:
         )
 
         payload = request.to_payload()
-        headers = build_auth_headers(self.scraper_token, mode=self._auth_mode)
+        token = self.scraper_token or ""
+        headers = build_auth_headers(token, mode=self._auth_mode)
 
         logger.info(f"Async SERP Search: {engine_str} - {query}")
 
@@ -451,6 +460,8 @@ class AsyncThordataClient:
         Execute an async SERP search using a SerpRequest object.
         """
         session = self._get_session()
+        if not self.scraper_token:
+            raise ThordataConfigError("scraper_token is required for SERP API")
 
         payload = request.to_payload()
         headers = build_auth_headers(self.scraper_token, mode=self._auth_mode)
@@ -545,6 +556,8 @@ class AsyncThordataClient:
         Async scrape using a UniversalScrapeRequest object.
         """
         session = self._get_session()
+        if not self.scraper_token:
+            raise ThordataConfigError("scraper_token is required for Universal API")
 
         payload = request.to_payload()
         headers = build_auth_headers(self.scraper_token, mode=self._auth_mode)
@@ -621,6 +634,8 @@ class AsyncThordataClient:
         """
         self._require_public_credentials()
         session = self._get_session()
+        if not self.scraper_token:
+            raise ThordataConfigError("scraper_token is required for Task Builder")
 
         payload = config.to_payload()
         # Builder needs 3 headers: token, key, Authorization Bearer
@@ -682,6 +697,10 @@ class AsyncThordataClient:
 
         self._require_public_credentials()
         session = self._get_session()
+        if not self.scraper_token:
+            raise ThordataConfigError(
+                "scraper_token is required for Video Task Builder"
+            )
 
         payload = config.to_payload()
         headers = build_builder_headers(
@@ -1527,8 +1546,8 @@ class AsyncThordataClient:
         self._require_public_credentials()
 
         params = {
-            "token": self.public_token,
-            "key": self.public_key,
+            "token": self.public_token or "",
+            "key": self.public_key or "",
         }
 
         for key, value in kwargs.items():