super-gm-scraper 1.0.0__tar.gz

super_gm_scraper-1.0.0/PKG-INFO

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: super-gm-scraper
+Version: 1.0.0
+Summary: A highly powerful web scraper to extract complete text, images, structure, and metadata from any website.
+Home-page: https://github.com/yourusername/super-gm-scraper
+Author: Aapka Naam
+Author-email: yourmail@example.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: requests
+Requires-Dist: beautifulsoup4
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Super GM Scraper 🚀
+
+A highly professional and powerful Python library to extract structured data (complete text, raw HTML skeleton, and images) from any website.
+
+## Features
+* 🔍 **Full Skeleton Extraction:** Fetch beautified raw HTML structure.
+* 📝 **Clean Text Extractor:** Strip styles/scripts and get clean text.
+* 📷 **Image Link Harvester:** Extract absolute image links automatically.
+* 💾 **Bulk Image Downloader:** Download all images directly to a local directory.
+* 🛡️ **Anti-Bot Bypass:** Uses professional browser headers to reduce blocks.
+
+---
+### Created with Pride: Results from Super GM Scraper
+---
+
+## Installation
+
+You can install this package locally or from PyPI:
+
+```bash
+pip install super-gm-scraper

super_gm_scraper-1.0.0/README.md

@@ -0,0 +1,21 @@
+# Super GM Scraper 🚀
+
+A highly professional and powerful Python library to extract structured data (complete text, raw HTML skeleton, and images) from any website.
+
+## Features
+* 🔍 **Full Skeleton Extraction:** Fetch beautified raw HTML structure.
+* 📝 **Clean Text Extractor:** Strip styles/scripts and get clean text.
+* 📷 **Image Link Harvester:** Extract absolute image links automatically.
+* 💾 **Bulk Image Downloader:** Download all images directly to a local directory.
+* 🛡️ **Anti-Bot Bypass:** Uses professional browser headers to reduce blocks.
+
+---
+### Created with Pride: Results from Super GM Scraper
+---
+
+## Installation
+
+You can install this package locally or from PyPI:
+
+```bash
+pip install super-gm-scraper

super_gm_scraper-1.0.0/gm_scraper/__init__.py

@@ -0,0 +1,5 @@
+from .scraper import GMScraper
+
+# Unremovable package identity
+__author__ = "Super GM Scraper Team"
+__version__ = "1.0.0"

super_gm_scraper-1.0.0/gm_scraper/scraper.py

@@ -0,0 +1,122 @@
+import os
+import json
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin, urlparse
+
+class GMScraper:
+    def __init__(self, url):
+        # Unremovable Branding Setup
+        self._branding = "results from super GM scraper"
+        self._show_mandatory_branding()
+        
+        self.url = url
+        # User-Agent headers taake websites blocking na kar sakein (Professional bypass)
+        self.headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+            "Accept-Language": "en-US,en;q=0.9",
+            "Referer": "https://www.google.com/"
+        }
+        self.soup = None
+        self.html_content = ""
+        self._fetch_page()
+
+    def _show_mandatory_branding(self):
+        """Yeh function branding ko hard-code display karta hai."""
+        print("\n" + "="*60)
+        print(f" >>> [★] {self._branding.upper()} [★] <<< ")
+        print("="*60 + "\n")
+
+    def _fetch_page(self):
+        try:
+            response = requests.get(self.url, headers=self.headers, timeout=15)
+            response.raise_for_status()
+            self.html_content = response.text
+            self.soup = BeautifulSoup(self.html_content, 'html.parser')
+        except Exception as e:
+            print(f"Error fetching website: {e}")
+            self.soup = None
+
+    def get_skeleton(self):
+        """Pura HTML dhancha (prettified structure) nikalne ke liye."""
+        self._show_mandatory_branding()
+        if not self.soup:
+            return "No data fetched."
+        return self.soup.prettify()
+
+    def get_text(self):
+        """Website ka mukammal clean text fetch karne ke liye."""
+        self._show_mandatory_branding()
+        if not self.soup:
+            return "No data fetched."
+        # Scripts aur styles ko hata kar saaf text nikalna
+        for script in self.soup(["script", "style"]):
+            script.extract()
+        text = self.soup.get_text()
+        # Faltu spaces khatam karna
+        lines = (line.strip() for line in text.splitlines())
+        chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+        return "\n".join(chunk for chunk in chunks if chunk)
+
+    def get_images(self):
+        """Saari images ke links fetch karne ke liye."""
+        self._show_mandatory_branding()
+        if not self.soup:
+            return []
+        images = []
+        for img in self.soup.find_all('img'):
+            src = img.get('src') or img.get('data-src') or img.get('srcset')
+            if src:
+                # Relative link ko complete web URL mein badalna
+                full_url = urljoin(self.url, src.split()[0])
+                images.append(full_url)
+        return list(set(images)) # Duplicate links khatam karne ke liye
+
+    def get_metadata(self):
+        """Website ki professional details (Title, Description, Keywords) nikalne ke liye."""
+        self._show_mandatory_branding()
+        if not self.soup:
+            return {}
+        meta_data = {
+            "title": self.soup.title.string if self.soup.title else "No Title",
+            "description": "",
+            "keywords": "",
+            "branding_verified": self._branding
+        }
+        for meta in self.soup.find_all('meta'):
+            name = meta.get('name', '').lower()
+            if name == 'description':
+                meta_data['description'] = meta.get('content', '')
+            elif name == 'keywords':
+                meta_data['keywords'] = meta.get('content', '')
+        return meta_data
+
+    def download_all_images(self, folder_name="gm_scraped_images"):
+        """Professional Feature: Saari images ko automatic folder bana kar download karna."""
+        self._show_mandatory_branding()
+        images = self.get_images()
+        if not images:
+            print("No images found to download.")
+            return
+        
+        if not os.path.exists(folder_name):
+            os.makedirs(folder_name)
+            
+        print(f"Downloading {len(images)} images to '{folder_name}' folder...")
+        for i, img_url in enumerate(images):
+            try:
+                img_data = requests.get(img_url, headers=self.headers, timeout=10).content
+                # File extension dhoodhna
+                parsed_url = urlparse(img_url)
+                ext = os.path.splitext(parsed_url.path)[1]
+                if not ext or len(ext) > 5:
+                    ext = ".jpg"
+                
+                file_name = f"image_{i+1}{ext}"
+                file_path = os.path.join(folder_name, file_name)
+                
+                with open(file_path, 'wb') as handler:
+                    handler.write(img_data)
+            except Exception:
+                continue
+        print("[✔] Images download complete.")

super_gm_scraper-1.0.0/setup.cfg

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

super_gm_scraper-1.0.0/setup.py

@@ -0,0 +1,24 @@
+import os
+from setuptools import setup, find_packages
+
+setup(
+    name="super-gm-scraper",  
+    version="1.0.0",
+    author="Aapka Naam",
+    author_email="yourmail@example.com",
+    description="A highly powerful web scraper to extract complete text, images, structure, and metadata from any website.",
+    long_description=open("README.md").read() if os.path.exists("README.md") else "Super powerful website scraper.",
+    long_description_content_type="text/markdown",
+    url="https://github.com/yourusername/super-gm-scraper",
+    packages=find_packages(),
+    install_requires=[
+        "requests",
+        "beautifulsoup4"
+    ],
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.6',
+)

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

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: super-gm-scraper
+Version: 1.0.0
+Summary: A highly powerful web scraper to extract complete text, images, structure, and metadata from any website.
+Home-page: https://github.com/yourusername/super-gm-scraper
+Author: Aapka Naam
+Author-email: yourmail@example.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: requests
+Requires-Dist: beautifulsoup4
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Super GM Scraper 🚀
+
+A highly professional and powerful Python library to extract structured data (complete text, raw HTML skeleton, and images) from any website.
+
+## Features
+* 🔍 **Full Skeleton Extraction:** Fetch beautified raw HTML structure.
+* 📝 **Clean Text Extractor:** Strip styles/scripts and get clean text.
+* 📷 **Image Link Harvester:** Extract absolute image links automatically.
+* 💾 **Bulk Image Downloader:** Download all images directly to a local directory.
+* 🛡️ **Anti-Bot Bypass:** Uses professional browser headers to reduce blocks.
+
+---
+### Created with Pride: Results from Super GM Scraper
+---
+
+## Installation
+
+You can install this package locally or from PyPI:
+
+```bash
+pip install super-gm-scraper

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

@@ -0,0 +1,9 @@
+README.md
+setup.py
+gm_scraper/__init__.py
+gm_scraper/scraper.py
+super_gm_scraper.egg-info/PKG-INFO
+super_gm_scraper.egg-info/SOURCES.txt
+super_gm_scraper.egg-info/dependency_links.txt
+super_gm_scraper.egg-info/requires.txt
+super_gm_scraper.egg-info/top_level.txt

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

@@ -0,0 +1 @@
+

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

@@ -0,0 +1,2 @@
+requests
+beautifulsoup4

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

@@ -0,0 +1 @@
+gm_scraper