deep-markdown-crawler 1.0.0__tar.gz

deep_markdown_crawler-1.0.0/PKG-INFO

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: deep-markdown-crawler
+Version: 1.0.0
+Summary: Universal Website to Clean Markdown Crawler SDK.
+Home-page: https://github.com/meanusarcanus/deep-markdown-crawler-api
+Author: Meanus Arcanus
+Author-email: meanusarcanus@gmail.com
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.25.0
+Requires-Dist: beautifulsoup4>=4.12.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: home-page
+Dynamic: requires-python
+
+# 📄 DeepCrawl AI — Universal Website to Markdown Crawler SDK
+
+Official Python SDK for **DeepCrawl AI** (Open-Source Firecrawl Alternative).
+
+---
+
+## ⚡ Quickstart
+
+```bash
+pip install deep-markdown-crawler
+```
+
+```python
+from deep_markdown_crawler import scrape_url_to_markdown, crawl_domain_to_markdown
+
+# 1. Scrape Single URL to Clean Markdown
+doc = scrape_url_to_markdown("https://fastapi.tiangolo.com/tutorial/")
+print(f"Title: {doc['title']} | Tokens: ~{doc['token_count']}")
+print(doc['markdown'][:500])
+
+# 2. Deep Crawl Entire Documentation Domain
+crawl = crawl_domain_to_markdown(
+    start_url="https://fastapi.tiangolo.com/tutorial/",
+    max_pages=5,
+    max_depth=2
+)
+
+print(f"Crawled {crawl['total_pages_crawled']} pages ({crawl['total_tokens_estimated']} tokens).")
+```

deep_markdown_crawler-1.0.0/README.md

@@ -0,0 +1,29 @@
+# 📄 DeepCrawl AI — Universal Website to Markdown Crawler SDK
+
+Official Python SDK for **DeepCrawl AI** (Open-Source Firecrawl Alternative).
+
+---
+
+## ⚡ Quickstart
+
+```bash
+pip install deep-markdown-crawler
+```
+
+```python
+from deep_markdown_crawler import scrape_url_to_markdown, crawl_domain_to_markdown
+
+# 1. Scrape Single URL to Clean Markdown
+doc = scrape_url_to_markdown("https://fastapi.tiangolo.com/tutorial/")
+print(f"Title: {doc['title']} | Tokens: ~{doc['token_count']}")
+print(doc['markdown'][:500])
+
+# 2. Deep Crawl Entire Documentation Domain
+crawl = crawl_domain_to_markdown(
+    start_url="https://fastapi.tiangolo.com/tutorial/",
+    max_pages=5,
+    max_depth=2
+)
+
+print(f"Crawled {crawl['total_pages_crawled']} pages ({crawl['total_tokens_estimated']} tokens).")
+```

deep_markdown_crawler-1.0.0/deep_markdown_crawler/__init__.py

@@ -0,0 +1,9 @@
+"""
+DeepCrawl AI — Universal Website to Markdown Crawler SDK
+Official Python client for deep website and documentation crawling into clean Markdown.
+"""
+
+from .client import DeepMarkdownCrawler, scrape_url_to_markdown, crawl_domain_to_markdown
+
+__version__ = "1.0.0"
+__all__ = ["DeepMarkdownCrawler", "scrape_url_to_markdown", "crawl_domain_to_markdown"]

deep_markdown_crawler-1.0.0/deep_markdown_crawler/client.py

@@ -0,0 +1,31 @@
+import requests
+from typing import Dict, Any, Optional
+
+def scrape_url_to_markdown(url: str, base_url: str = "https://deep-markdown-crawler-api.vercel.app") -> Dict[str, Any]:
+    """Scrape a single URL into clean Markdown."""
+    endpoint = f"{base_url.rstrip('/')}/api/v1/scrape"
+    try:
+        res = requests.post(endpoint, json={"url": url}, timeout=25)
+        return res.json()
+    except Exception as e:
+        return {"status": "error", "message": str(e)}
+
+def crawl_domain_to_markdown(start_url: str, max_pages: int = 5, max_depth: int = 2, base_url: str = "https://deep-markdown-crawler-api.vercel.app") -> Dict[str, Any]:
+    """Crawl a full domain or doc portal into clean Markdown."""
+    endpoint = f"{base_url.rstrip('/')}/api/v1/crawl"
+    try:
+        res = requests.post(endpoint, json={"start_url": start_url, "max_pages": max_pages, "max_depth": max_depth}, timeout=45)
+        return res.json()
+    except Exception as e:
+        return {"status": "error", "message": str(e)}
+
+class DeepMarkdownCrawler:
+    def __init__(self, api_key: Optional[str] = None, base_url: str = "https://deep-markdown-crawler-api.vercel.app"):
+        self.api_key = api_key
+        self.base_url = base_url.rstrip("/")
+
+    def scrape(self, url: str) -> Dict[str, Any]:
+        return scrape_url_to_markdown(url, base_url=self.base_url)
+
+    def crawl(self, start_url: str, max_pages: int = 5, max_depth: int = 2) -> Dict[str, Any]:
+        return crawl_domain_to_markdown(start_url, max_pages=max_pages, max_depth=max_depth, base_url=self.base_url)

deep_markdown_crawler-1.0.0/deep_markdown_crawler.egg-info/PKG-INFO

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: deep-markdown-crawler
+Version: 1.0.0
+Summary: Universal Website to Clean Markdown Crawler SDK.
+Home-page: https://github.com/meanusarcanus/deep-markdown-crawler-api
+Author: Meanus Arcanus
+Author-email: meanusarcanus@gmail.com
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.25.0
+Requires-Dist: beautifulsoup4>=4.12.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: home-page
+Dynamic: requires-python
+
+# 📄 DeepCrawl AI — Universal Website to Markdown Crawler SDK
+
+Official Python SDK for **DeepCrawl AI** (Open-Source Firecrawl Alternative).
+
+---
+
+## ⚡ Quickstart
+
+```bash
+pip install deep-markdown-crawler
+```
+
+```python
+from deep_markdown_crawler import scrape_url_to_markdown, crawl_domain_to_markdown
+
+# 1. Scrape Single URL to Clean Markdown
+doc = scrape_url_to_markdown("https://fastapi.tiangolo.com/tutorial/")
+print(f"Title: {doc['title']} | Tokens: ~{doc['token_count']}")
+print(doc['markdown'][:500])
+
+# 2. Deep Crawl Entire Documentation Domain
+crawl = crawl_domain_to_markdown(
+    start_url="https://fastapi.tiangolo.com/tutorial/",
+    max_pages=5,
+    max_depth=2
+)
+
+print(f"Crawled {crawl['total_pages_crawled']} pages ({crawl['total_tokens_estimated']} tokens).")
+```

deep_markdown_crawler-1.0.0/deep_markdown_crawler.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+setup.py
+deep_markdown_crawler/__init__.py
+deep_markdown_crawler/client.py
+deep_markdown_crawler.egg-info/PKG-INFO
+deep_markdown_crawler.egg-info/SOURCES.txt
+deep_markdown_crawler.egg-info/dependency_links.txt
+deep_markdown_crawler.egg-info/requires.txt
+deep_markdown_crawler.egg-info/top_level.txt

deep_markdown_crawler-1.0.0/deep_markdown_crawler.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

deep_markdown_crawler-1.0.0/deep_markdown_crawler.egg-info/requires.txt

@@ -0,0 +1,2 @@
+requests>=2.25.0
+beautifulsoup4>=4.12.0

deep_markdown_crawler-1.0.0/deep_markdown_crawler.egg-info/top_level.txt

@@ -0,0 +1 @@
+deep_markdown_crawler

deep_markdown_crawler-1.0.0/pyproject.toml

@@ -0,0 +1,14 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "deep-markdown-crawler"
+version = "1.0.0"
+description = "Universal Website to Clean Markdown Crawler SDK."
+readme = "README.md"
+requires-python = ">=3.8"
+dependencies = [
+    "requests>=2.25.0",
+    "beautifulsoup4>=4.12.0"
+]

deep_markdown_crawler-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

deep_markdown_crawler-1.0.0/setup.py

@@ -0,0 +1,23 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="deep-markdown-crawler",
+    version="1.0.0",
+    description="Universal Website to Clean Markdown Crawler SDK (Firecrawl Alternative).",
+    long_description=open("README.md").read() if open("README.md") else "",
+    long_description_content_type="text/markdown",
+    author="Meanus Arcanus",
+    author_email="meanusarcanus@gmail.com",
+    url="https://github.com/meanusarcanus/deep-markdown-crawler-api",
+    packages=find_packages(),
+    install_requires=[
+        "requests>=2.25.0",
+        "beautifulsoup4>=4.12.0",
+    ],
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires=">=3.8",
+)