parse-everything 1.0.0__py3-none-any.whl

parse_everything/__init__.py

@@ -0,0 +1,9 @@
+"""
+Parse Everything — Python Client Library
+Official SDK for parse-everything.com Anti-Bot Bypass & Web Extraction API.
+"""
+
+from .client import ParseEverything, ParseEverythingError
+
+__version__ = "1.0.0"
+__all__ = ["ParseEverything", "ParseEverythingError"]

parse_everything/client.py

@@ -0,0 +1,140 @@
+import urllib.request
+import urllib.parse
+import json
+import time
+from typing import Optional, Dict, Any, List
+
+class ParseEverythingError(Exception):
+    """Base exception for Parse Everything API errors."""
+    def __init__(self, message: str, status_code: Optional[int] = None, response_body: Optional[str] = None):
+        super().__init__(message)
+        self.status_code = status_code
+        self.response_body = response_body
+
+class ParseEverything:
+    """
+    Client for Parse Everything Web Scraping & Anti-Bot Bypass API.
+    
+    Usage:
+        from parse_everything import ParseEverything
+        client = ParseEverything(api_key="pe_live_...")
+        res = client.scrape("https://nowsecure.nl")
+        print(res['data']['page_title'])
+    """
+    def __init__(self, api_key: str, base_url: str = "https://api.parse-everything.com"):
+        if not api_key:
+            raise ValueError("api_key is required. Get 1,000 free credits at https://parse-everything.com")
+        self.api_key = api_key.strip()
+        self.base_url = base_url.rstrip("/")
+
+    def scrape(
+        self,
+        target_url: str,
+        render_js: bool = False,
+        bypass_cloudflare: bool = True,
+        country_code: str = "US",
+        extract_text: bool = False,
+        selectors: Optional[Dict[str, str]] = None,
+        custom_headers: Optional[Dict[str, str]] = None,
+        cookies: Optional[Dict[str, str]] = None,
+        timeout: int = 40
+    ) -> Dict[str, Any]:
+        """
+        Extract web data from any protected target URL.
+        """
+        payload = {
+            "target_url": target_url,
+            "render_js": render_js,
+            "bypass_cloudflare": bypass_cloudflare,
+            "country_code": country_code,
+            "extract_text": extract_text,
+            "timeout": timeout
+        }
+        if selectors:
+            payload["selectors"] = selectors
+        if custom_headers:
+            payload["custom_headers"] = custom_headers
+        if cookies:
+            payload["cookies"] = cookies
+
+        url = f"{self.base_url}/api/v1/extract"
+        req = urllib.request.Request(
+            url,
+            data=json.dumps(payload).encode("utf-8"),
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {self.api_key}",
+                "User-Agent": "ParseEverything-PythonSDK/1.0"
+            },
+            method="POST"
+        )
+
+        try:
+            with urllib.request.urlopen(req, timeout=timeout + 5) as resp:
+                return json.loads(resp.read().decode("utf-8"))
+        except urllib.error.HTTPError as e:
+            body = e.read().decode("utf-8", errors="replace")
+            try:
+                err_json = json.loads(body)
+                msg = err_json.get("detail") or err_json.get("message") or str(e)
+            except Exception:
+                msg = body or str(e)
+            raise ParseEverythingError(f"API Error ({e.code}): {msg}", status_code=e.code, response_body=body)
+        except Exception as e:
+            raise ParseEverythingError(f"Request failed: {str(e)}")
+
+    def batch(
+        self,
+        target_urls: List[str],
+        render_js: bool = False,
+        country_code: str = "US",
+        webhook_url: Optional[str] = None
+    ) -> Dict[str, Any]:
+        """
+        Submit a batch of up to 100 URLs for background extraction.
+        """
+        payload = {
+            "target_urls": target_urls,
+            "render_js": render_js,
+            "country_code": country_code
+        }
+        if webhook_url:
+            payload["webhook_url"] = webhook_url
+
+        url = f"{self.base_url}/api/v1/batch"
+        req = urllib.request.Request(
+            url,
+            data=json.dumps(payload).encode("utf-8"),
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {self.api_key}",
+                "User-Agent": "ParseEverything-PythonSDK/1.0"
+            },
+            method="POST"
+        )
+
+        try:
+            with urllib.request.urlopen(req, timeout=30) as resp:
+                return json.loads(resp.read().decode("utf-8"))
+        except urllib.error.HTTPError as e:
+            body = e.read().decode("utf-8", errors="replace")
+            raise ParseEverythingError(f"Batch Error ({e.code}): {body}", status_code=e.code, response_body=body)
+
+    def get_batch(self, batch_id: str) -> Dict[str, Any]:
+        """
+        Poll progress and results for a batch job.
+        """
+        url = f"{self.base_url}/api/v1/batch/{batch_id}"
+        req = urllib.request.Request(
+            url,
+            headers={
+                "Authorization": f"Bearer {self.api_key}",
+                "User-Agent": "ParseEverything-PythonSDK/1.0"
+            }
+        )
+        try:
+            with urllib.request.urlopen(req, timeout=20) as resp:
+                return json.loads(resp.read().decode("utf-8"))
+        except urllib.error.HTTPError as e:
+            body = e.read().decode("utf-8", errors="replace")
+            raise ParseEverythingError(f"Batch poll failed ({e.code}): {body}", status_code=e.code, response_body=body)

parse_everything-1.0.0.dist-info/METADATA

@@ -0,0 +1,134 @@
+Metadata-Version: 2.4
+Name: parse-everything
+Version: 1.0.0
+Summary: Official Python SDK for Parse Everything — Bypass Cloudflare Turnstile, Akamai & DataDome with TLS JA3/JA4 impersonation.
+Home-page: https://parse-everything.com
+Author: Parse Everything
+Author-email: support@rawmind.app
+License: MIT
+Project-URL: Documentation, https://parse-everything.com/docs.php
+Project-URL: Source Code, https://github.com/parse-everything/parse-everything-python
+Keywords: cloudflare-bypass,turnstile-solver,akamai-bypass,datadome,web-scraping-api,ja3-spoofing,ja4-fingerprinting,anti-bot,flaresolverr-alternative,zenrows-alternative,scrapingbee-alternative,crawler,web-extraction
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Internet :: WWW/HTTP :: Dynamic Content
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+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: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: project-url
+Dynamic: requires-python
+Dynamic: summary
+
+# Parse Everything — Python SDK
+
+[![PyPI version](https://img.shields.io/badge/pypi-v1.0.0-blue.svg)](https://pypi.org/project/parse-everything/)
+[![Free Credits](https://img.shields.io/badge/Free%20Tier-1%2C000%20Requests-green.svg)](https://parse-everything.com)
+[![Python Versions](https://img.shields.io/badge/python-3.8%2B-blue.svg)](https://pypi.org/project/parse-everything/)
+
+Official lightweight Python client for [Parse Everything](https://parse-everything.com) — Enterprise Web Scraping & Anti-Bot Bypass API.
+
+Effortlessly bypass **Cloudflare Turnstile**, **Cloudflare WAF (403 Forbidden)**, **Akamai Bot Manager**, **DataDome**, and **DDoS-Guard** with authentic TLS JA3/JA4 fingerprint impersonation.
+
+---
+
+## 🚀 Quick Install
+
+```bash
+pip install parse-everything
+```
+
+*(Zero heavy browser or binary dependencies required. Uses built-in standard library).*
+
+---
+
+## 🔑 Get Your API Key
+
+Sign up at [parse-everything.com](https://parse-everything.com) to receive **1,000 free API credits** instantly.
+
+---
+
+## 💡 Usage Examples
+
+### 1. Simple Scrape (Bypass Cloudflare Turnstile & WAF)
+```python
+from parse_everything import ParseEverything
+
+client = ParseEverything(api_key="pe_live_YOUR_API_KEY")
+
+result = client.scrape(
+    target_url="https://nowsecure.nl",
+    bypass_cloudflare=True,
+    render_js=False  # Handled via ultra-fast TLS impersonation in ~300ms
+)
+
+print("HTTP Status:", result["data"]["http_status"])
+print("Page Title:", result["data"]["page_title"])
+print("Protection Bypassed:", result["data"]["protection_bypassed"])
+print("HTML:", result["data"]["full_html"][:200])
+```
+
+### 2. Extract Structured Data with CSS Selectors (LLM / RAG Ready)
+```python
+result = client.scrape(
+    target_url="https://example.com/products",
+    selectors={
+        "titles": "h2.product-title",
+        "prices": ".price",
+        "links": "a.buy-btn"
+    }
+)
+
+print(result["data"]["selectors_data"])
+```
+
+### 3. Extract Clean Text Only (Save 85% LLM Tokens)
+```python
+result = client.scrape(
+    target_url="https://news-site.com/article",
+    extract_text=True
+)
+
+print(result["data"]["clean_text"])
+```
+
+### 4. Asynchronous Batch Scraping (Up to 100 URLs)
+```python
+batch_job = client.batch(
+    target_urls=[
+        "https://example.com/page1",
+        "https://example.com/page2",
+        "https://example.com/page3"
+    ]
+)
+print("Batch ID:", batch_job["batch_id"])
+
+# Poll progress
+status = client.get_batch(batch_job["batch_id"])
+print(f"Status: {status['job_status']} ({status['completed_urls']}/{status['total_urls']})")
+```
+
+---
+
+## 📦 How to Publish to PyPI
+
+```bash
+cd AD/04_sdks_and_packages/python_pypi
+pip install build twine
+python -m build
+python -m twine upload dist/*
+```

parse_everything-1.0.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+parse_everything/__init__.py,sha256=E1dt6ECbkTmT3z0UQ51sTNkboE43kL2tC-rc2Dpkss4,263
+parse_everything/client.py,sha256=9kGhQrMT8fBChLRpqv7Ei_GTVeJpWtlogyUSZPO3gUE,5173
+parse_everything-1.0.0.dist-info/METADATA,sha256=H3RvsJzzdqPNHekVoXFqfNWfzx6XutikxUglm-mQOmk,4408
+parse_everything-1.0.0.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
+parse_everything-1.0.0.dist-info/top_level.txt,sha256=52mc273gfsXNfESvTcFJOwU1_rE-mnb2JCuzNTeLO2g,17
+parse_everything-1.0.0.dist-info/RECORD,,

parse_everything-1.0.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.2.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

parse_everything-1.0.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+parse_everything