#!/usr/bin/env python
import os
import sys
import html
import re
import logging
from bs4 import BeautifulSoup
# Set up logging
logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")
def get_content_stats(file_path, root_dir):
"""HTML फाइल से शब्दों, कैरेक्टर और अन्य जानकारी निकालता है, साथ में फोल्डर का नाम भी जोड़ता है।"""
# Skip search.html
if os.path.basename(file_path) == "search.html":
logging.info(f"Skipping {file_path}")
return None
content = None
for encoding in ['utf-8', 'latin-1', 'iso-8859-1']:
try:
with open(file_path, 'r', encoding=encoding) as file:
content = file.read()
break
except UnicodeDecodeError:
continue
if content is None:
logging.warning(f"Could not decode {file_path}. Skipping this file.")
return None
try:
soup = BeautifulSoup(content, 'html.parser')
# Handle missing
title_tag = soup.title
title = title_tag.string.strip() if title_tag and title_tag.string else "Untitled"
# Get content from p and div tags
text_content = " ".join(tag.get_text(strip=True) for tag in soup.find_all(['p', 'div']))
# Calculate stats
words = len(text_content.split())
chars_with_spaces = len(text_content)
chars_without_spaces = len(re.sub(r'\s+', '', text_content))
bytes_size = os.path.getsize(file_path)
# Extract folder name (excluding root_dir)
relative_path = os.path.relpath(file_path, root_dir)
folder_name = os.path.dirname(relative_path)
if folder_name == "":
folder_name = "Root"
return {
'title': html.escape(title),
'words': words,
'chars_with_spaces': chars_with_spaces,
'chars_no_spaces': chars_without_spaces,
'bytes': bytes_size,
'filename': html.escape(os.path.basename(file_path)),
'folder': html.escape(folder_name)
}
except Exception as e:
logging.error(f"Error processing {file_path}: {str(e)}")
return None
def generate_stats_html(root_dir):
"""पूरे डायरेक्टरी से HTML फाइलों का स्टैट निकालकर stats.html में सेव करता है।"""
html_content = """
<!DOCTYPE html>
<html lang="hi">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Website Statistics
वेबसाइट सांख्यिकी
फ़ोल्डर
फ़ाइल नाम
शीर्षक
शब्द
कैरेक्टर (स्पेस सहित)
कैरेक्टर (स्पेस रहित)
बाइट्स
"""
# Process all HTML files
processed_files = 0
for root, dirs, files in os.walk(root_dir):
for file in files:
if file.endswith('.html'):
file_path = os.path.join(root, file)
stats = get_content_stats(file_path, root_dir)
if stats:
html_content += f"""