acidvegas/httpz
acidvegas/httpz
1
Fork 0
Code Issues Pull Requests Releases 3 Activity

fixed chunk output

Browse Source
This commit is contained in:
Dionysus 2025-02-12 00:50:02 -05:00
parent 6dacafeee5
commit 7fe571ddad
Signed by: acidvegas
GPG Key ID: EF4B922DB85DC9DE
4 changed files with 128 additions and 95 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
httpz_scanner/__init__.py
View File

@ -6,4 +6,4 @@ from .colors import Colors
from .scanner import HTTPZScanner
__version__ = '2.1.3'
__version__ = '2.1.4'

6
httpz_scanner/cli.py
View File

@ -88,6 +88,9 @@ async def main():
# Add shard argument
parser.add_argument('-sh','--shard', type=parse_shard, help='Shard index and total shards (e.g., 1/3)')
# Add this to the argument parser section
parser.add_argument('-pa', '--paths', help='Additional paths to check (comma-separated, e.g., ".git/config,.env")')
# If no arguments provided, print help and exit
if len(sys.argv) == 1:
parser.print_help()
@ -143,7 +146,8 @@ async def main():
show_fields=show_fields,
match_codes=args.match_codes,
exclude_codes=args.exclude_codes,
shard=args.shard
shard=args.shard,
paths=args.paths.split(',') if args.paths else None
)
count = 0

81
httpz_scanner/scanner.py
View File

@ -4,6 +4,7 @@
import asyncio
import random
import urllib.parse
try:
import aiohttp
@ -23,7 +24,7 @@ from .utils import debug, USER_AGENTS, input_generator
class HTTPZScanner:
'''Core scanner class for HTTP domain checking'''
def __init__(self, concurrent_limit = 100, timeout = 5, follow_redirects = False, check_axfr = False, resolver_file = None, output_file = None, show_progress = False, debug_mode = False, jsonl_output = False, show_fields = None, match_codes = None, exclude_codes = None, shard = None):
def __init__(self, concurrent_limit = 100, timeout = 5, follow_redirects = False, check_axfr = False, resolver_file = None, output_file = None, show_progress = False, debug_mode = False, jsonl_output = False, show_fields = None, match_codes = None, exclude_codes = None, shard = None, paths = None):
'''
Initialize the HTTPZScanner class
@ -40,6 +41,7 @@ class HTTPZScanner:
:param match_codes: Status codes to match
:param exclude_codes: Status codes to exclude
:param shard: Tuple of (shard_index, total_shards) for distributed scanning
:param paths: List of additional paths to check on each domain
'''
self.concurrent_limit = concurrent_limit
@ -52,6 +54,7 @@ class HTTPZScanner:
self.debug_mode = debug_mode
self.jsonl_output = jsonl_output
self.shard = shard
self.paths = paths or []
self.show_fields = show_fields or {
'status_code' : True,
@ -81,35 +84,63 @@ class HTTPZScanner:
:param session: aiohttp.ClientSession
:param domain: str
'''
# Get random nameserver
nameserver = random.choice(self.resolvers) if self.resolvers else None
# Parse domain
base_domain, port, protocols = parse_domain_url(domain)
# Initialize result dictionary
result = {
'domain' : base_domain,
'status' : 0,
'url' : protocols[0],
'port' : port,
}
results = []
# Try each protocol
for url in protocols:
# For each protocol (http/https)
for base_url in protocols:
try:
# Check base URL first
if result := await self._check_url(session, base_url):
results.append(result)
# Check additional paths
for path in self.paths:
path = path.strip('/')
url = f'{base_url}/{path}'
if result := await self._check_url(session, url):
results.append(result)
if results: # If we got any successful results, return them
break
except Exception as e:
debug(f'Error checking {base_url}: {str(e)}')
continue
return results[0] if results else None # Return first successful result or None
async def _check_url(self, session: aiohttp.ClientSession, url: str):
'''
Check a single URL and return results
:param session: aiohttp.ClientSession
:param url: URL to check
'''
try:
# Set random user agent for each request
headers = {'User-Agent': random.choice(USER_AGENTS)}
async with session.get(url, timeout=self.timeout, allow_redirects=self.follow_redirects, max_redirects=10 if self.follow_redirects else 0, headers=headers) as response:
result['status'] = response.status
async with session.get(url, timeout=self.timeout,
allow_redirects=self.follow_redirects,
max_redirects=10 if self.follow_redirects else 0,
headers=headers) as response:
# Bail immediately if it's a failed lookup - no point processing further
# Properly parse the URL
parsed_url = urllib.parse.urlparse(url)
parsed_domain = parsed_url.hostname
result = {
'domain': parsed_domain,
'status': response.status,
'url': str(response.url),
'port': parsed_url.port or ('443' if parsed_url.scheme == 'https' else '80')
}
# Early exit conditions
if result['status'] == -1:
return None
# Early exit if status code doesn't match criteria
if self.match_codes and result['status'] not in self.match_codes:
return result
if self.exclude_codes and result['status'] in self.exclude_codes:
@ -135,7 +166,7 @@ class HTTPZScanner:
# Do DNS lookups only if we're going to use the result
ips, cname, nameservers, _ = await resolve_all_dns(
base_domain, self.timeout, nameserver, self.check_axfr
parsed_domain, self.timeout, None, self.check_axfr
)
# Only add DNS fields if they have values
@ -172,13 +203,11 @@ class HTTPZScanner:
if favicon_hash := await get_favicon_hash(session, url, html):
result['favicon_hash'] = favicon_hash
break
return result
except Exception as e:
debug(f'Error checking {url}: {str(e)}')
continue # Just continue to next protocol without setting status = -1
# Return None if we never got a valid status
return None if result['status'] == 0 else result
return None
async def scan(self, input_source):

2
setup.py
View File

@ -10,7 +10,7 @@ with open('README.md', 'r', encoding='utf-8') as f:
setup(
name='httpz_scanner',
version='2.1.3',
version='2.1.4',
author='acidvegas',
author_email='acid.vegas@acid.vegas',
description='Hyper-fast HTTP Scraping Tool',