import lxml.html

from bs4 import BeautifulSoup

import requests

import json

def flag_html_anomalies(url, timeout=5):

"""

Flags anomalies in an HTML document using a combination of lxml and BeautifulSoup.

Includes fallback logic for robustness.

"""

try:

response = requests.get(url, timeout=timeout)

response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx)

html_content = response.text

except requests.exceptions.RequestException as e:

print(f"Error fetching URL: {e}")

return {"url": url, "anomaly": "Fetch Error", "details": str(e)}

try:

# Use lxml for robust parsing and schema validation

tree = lxml.html.fromstring(html_content)

# Check for invalid HTML structure (e.g., missing closing tags)

if not tree.is_well_formed:

return {"url": url, "anomaly": "Invalid HTML", "details": "Malformed HTML structure"}

# Check for unusual tag usage

for element in tree.iter():

if element.tag in ["script", "style"] and element.get("src"): # Check for external scripts/styles

return {"url": url, "anomaly": "External Scripts/Styles", "details": f"External script/style found: {element.get('src')}"}

#Basic check for excessive script or style tags

script_count = len(list(tree.getsouls()))

style_count = len(list(tree.getsouls()))

if script_count > 10 or style_count > 10:

return {"url": url, "anomaly": "Excessive Scripts/Styles", "details": f"High number of script/style tags ({script_count} scripts, {style_count} styles)"}

# Fallback: Use BeautifulSoup for more lenient parsing and content analysis

soup = BeautifulSoup(html_content, 'html.parser')

# Check for unusual attributes

for tag in soup.find_all():

for attr in tag.attrs:

if attr not in ['id', 'class', 'style', 'data-*']:

return {"url": url, "anomaly": f"Unusual Attribute: {attr}", "details": f"Found unusual attribute '{attr}' on tag '{tag.name}'"}

return {"url": url, "anomaly": "No Anomalies Detected", "details": "HTML appears valid and within normal bounds."}

except lxml.html.document_structure_error as e:

return {"url": url, "anomaly": "Lxml Parsing Error", "details": str(e)}

except Exception as e:

return {"url": url, "anomaly": "General Error", "details": str(e)}

if __name__ == '__main__':

#Example Usage

url1 = "https://www.example.com"

url2 = "https://httpstat.us/404" #Simulates a 404 error

url3 = "https://www.invalid-url.com" #Simulates a DNS error

url4 = "https://www.wikipedia.org"

print(flag_html_anomalies(url1))

print(flag_html_anomalies(url2))

print(flag_html_anomalies(url3))

print(flag_html_anomalies(url4))