thordata-sdk 1.0.1__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-1.0.1 → thordata_sdk-1.2.0}/pyproject.toml

@@ -1,10 +1,11 @@
+# thordata-python-sdk/pyproject.toml
 [build-system]
 requires = ["setuptools>=61.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "thordata-sdk"
-version = "1.0.1"
+version = "1.2.0"
 description = "The Official Python SDK for Thordata - AI Data Infrastructure & Proxy Network."
 readme = "README.md"
 requires-python = ">=3.9"
@@ -44,6 +45,7 @@ classifiers = [
 dependencies = [
     "requests>=2.25.0",
     "aiohttp>=3.9.0",
+    "PySocks>=1.7.1",
 ]
 
 [project.optional-dependencies]
@@ -82,6 +84,7 @@ include = '\.pyi?$'
 [tool.ruff]
 line-length = 88
 target-version = "py39"
+extend-exclude = ["sdk-spec"]
 
 [tool.ruff.lint]
 select = [
@@ -90,11 +93,12 @@ select = [
     "F",   # pyflakes
     "I",   # isort (import sorting)
     "B",   # flake8-bugbear
+    "UP",  # pyupgrade
+    "SIM", # flake8-simplify
 ]
 ignore = [
     "E501",  # line too long (handled by black)
     "E731",  # do not assign a lambda expression
-    "F401",  # imported but unused (we have some intentional re-exports)
 ]
 
 [tool.ruff.lint.isort]
@@ -121,6 +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]
@@ -133,4 +138,4 @@ exclude_lines = [
     "def __repr__",
     "raise NotImplementedError",
     "if TYPE_CHECKING:",
-]
+]

{thordata_sdk-1.0.1 → thordata_sdk-1.2.0}/src/thordata/__init__.py

@@ -35,7 +35,7 @@ Async Usage:
     >>> asyncio.run(main())
 """
 
-__version__ = "1.0.1"
+__version__ = "1.2.0"
 __author__ = "Thordata Developer Team"
 __email__ = "support@thordata.com"
 

{thordata_sdk-1.0.1 → thordata_sdk-1.2.0}/src/thordata/_example_utils.py

@@ -2,8 +2,9 @@ from __future__ import annotations
 
 import json
 import os
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Any, Iterable, Optional
+from typing import Any
 
 try:
     from dotenv import load_dotenv
@@ -23,7 +24,7 @@ def env(name: str) -> str:
     return (os.getenv(name) or "").strip()
 
 
-def skip_if_missing(required: Iterable[str], *, tip: Optional[str] = None) -> bool:
+def skip_if_missing(required: Iterable[str], *, tip: str | None = None) -> bool:
     missing = [k for k in required if not env(k)]
     if not missing:
         return False

{thordata_sdk-1.0.1 → thordata_sdk-1.2.0}/src/thordata/_utils.py

@@ -10,7 +10,7 @@ import base64
 import json
 import logging
 import platform
-from typing import Any, Dict
+from typing import Any
 
 logger = logging.getLogger(__name__)
 
@@ -71,7 +71,7 @@ def decode_base64_image(png_str: str) -> bytes:
         raise ValueError(f"Failed to decode base64 image: {e}") from e
 
 
-def build_auth_headers(token: str, mode: str = "bearer") -> Dict[str, str]:
+def build_auth_headers(token: str, mode: str = "bearer") -> dict[str, str]:
     """
     Build authorization headers for API requests.
 
@@ -105,7 +105,7 @@ def build_builder_headers(
     scraper_token: str,
     public_token: str,
     public_key: str,
-) -> Dict[str, str]:
+) -> dict[str, str]:
     """
     Build headers for Web Scraper builder API.
 
@@ -130,7 +130,7 @@ def build_builder_headers(
     }
 
 
-def build_public_api_headers(public_token: str, public_key: str) -> Dict[str, str]:
+def build_public_api_headers(public_token: str, public_key: str) -> dict[str, str]:
     """
     Build headers for public API requests (task status, locations, etc.)