import re
import pandas as pd

# Function to parse the log file
def parse_log_file(file_path):
    with open(file_path, 'r') as file:
        log_entries = file.readlines()
    
    log_data = []
    for entry in log_entries:
        timestamp_match = re.match(r'(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2},\d{3})', entry)
        if timestamp_match:
            timestamp = timestamp_match.group(1)
            log_level = re.search(r'- (\w+) -', entry)
            url_match = re.search(r'HTTP Request: POST (.*?)"', entry)
            status_code = re.search(r'"HTTP/1.1 (\d{3})', entry)
            
            if log_level and url_match and status_code:
                log_level = log_level.group(1)
                url = url_match.group(1)
                status_code = status_code.group(1)
                
                if status_code == '429':
                    h1_tag = re.search(r'<h1>(\d+)</h1>', entry)
                    h1_error_code = h1_tag.group(1) if h1_tag else 'N/A'
                    log_data.append({
                        'Timestamp': timestamp,
                        'Log Level': log_level,
                        'URL': url,
                        'Status Code': status_code,
                        'H1 Error Code': h1_error_code
                    })
    
    return pd.DataFrame(log_data)

# Parse the provided log file
file_path = 'paste.txt'
parsed_log_df = parse_log_file(file_path)

# Display the DataFrame
parsed_log_df