new: Add support for user defined cookies, bump deps

lookyloo/helpers.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 import os
+from typing import List
 from pathlib import Path
 from .exceptions import MissingEnv, CreateDirectoryException
 from redis import Redis
@@ -10,6 +11,8 @@ import time
 from glob import glob
 import json
 import traceback
+from urllib.parse import urlparse
+from datetime import datetime, timedelta
 
 from bs4 import BeautifulSoup  # type: ignore
 try:
@@ -139,3 +142,23 @@ def get_user_agents() -> dict:
         paths = sorted(glob(ua_files_path), reverse=True)
     with open(paths[0]) as f:
         return json.load(f)
+
+def load_cookies() -> List[dict]:
+    if not (get_homedir() / 'cookies.json').exists():
+        return []
+
+    with (get_homedir() / 'cookies.json').open() as f:
+        cookies = json.load(f)
+    to_return = []
+    for cookie in cookies:
+        u = urlparse(cookie['Host raw']).netloc.split(':', 1)[0]
+        to_add = {'path': cookie['Path raw'],
+                  'name': cookie['Name raw'],
+                  'httpOnly': cookie['HTTP only raw'] == 'true',
+                  'secure': cookie['Send for'] == 'Encrypted connections only',
+                  'expires': (datetime.now() + timedelta(days=10)).strftime('%Y-%m-%dT%H:%M:%S') + 'Z',
+                  'domain': u,
+                  'value': cookie['Content raw']
+                 }
+        to_return.append(to_add)
+    return to_return

lookyloo/lookyloo.py

@@ -20,17 +20,17 @@ import base64
 from uuid import uuid4
 
 from pathlib import Path
-from .helpers import get_homedir, get_socket_path
+from .helpers import get_homedir, get_socket_path, load_cookies
 from .exceptions import NoValidHarFile
 from redis import Redis
 
-from typing import Union, Dict, List, Tuple
+from typing import Union, Dict, List, Tuple, Optional
 
 import logging
 
-from pysanejs import SaneJS  # type: ignore
-from scrapysplashwrapper import crawl  # type: ignore
-from har2tree import CrawledTree, Har2TreeError  # type: ignore
+from pysanejs import SaneJS
+from scrapysplashwrapper import crawl
+from har2tree import CrawledTree, Har2TreeError
 
 
 class Lookyloo():
@@ -50,7 +50,9 @@ class Lookyloo():
         # Try to reach sanejs
         self.sanejs = SaneJS()
         if not self.sanejs.is_up:
-            self.sanejs = None
+            self.use_sane_js = False
+        else:
+            self.use_sane_js = True
 
     def __init_logger(self, loglevel: int) -> None:
         self.logger = logging.getLogger(f'{self.__class__.__name__}')
@@ -156,11 +158,11 @@ class Lookyloo():
             return BytesIO(f.read())
 
     def sane_js_query(self, sha512: str) -> Dict:
-        if self.sanejs:
+        if self.use_sane_js:
             return self.sanejs.sha512(sha512)
         return {'response': []}
 
-    def scrape(self, url: str, cookies: List[dict]=[], depth: int=1, listing: bool=True, user_agent: str=None, perma_uuid: str=None,
+    def scrape(self, url: str, cookies: List[dict]=[], depth: int=1, listing: bool=True, user_agent: Optional[str]=None, perma_uuid: str=None,
                os: str=None, browser: str=None) -> Union[bool, str]:
         if not url.startswith('http'):
             url = f'http://{url}'
@@ -173,7 +175,7 @@ class Lookyloo():
                         return False
             else:
                 return False
-
+        cookies = load_cookies()
         items = crawl(self.splash_url, url, cookies=cookies, depth=depth, user_agent=user_agent, log_enabled=True, log_level='INFO')
         if not items:
             # broken

poetry.lock

@@ -239,7 +239,7 @@ lxml = "^4.4.2"
 six = "^1.14.0"
 
 [package.source]
-reference = "8b986b8b0db9736ca5e4ffae1cb2ba5ab7ae6589"
+reference = "3f7771a1467c27a45ebcc3ff00e3e6e834d54e72"
 type = "git"
 url = "https://github.com/viper-framework/har2tree.git"
 [[package]]
@@ -459,17 +459,17 @@ version = "2.1.2"
 
 [[package]]
 category = "main"
-description = "Python client for SaneJS"
+description = ""
 name = "pysanejs"
 optional = false
-python-versions = "*"
-version = "0.1"
+python-versions = "^3.6"
+version = "0.1.0"
 
 [package.dependencies]
-requests = "*"
+requests = "^2.22.0"
 
 [package.source]
-reference = "3dfe0530a24e4caff04f27830ad4a38c52c74a2c"
+reference = "bdc091fbae7019c39b47a149b12f8ac032eda2a3"
 type = "git"
 url = "https://github.com/CIRCL/PySaneJS.git"
 [[package]]
@@ -568,7 +568,7 @@ scrapy = "^1.8.0"
 scrapy-splash = "^0.7.2"
 
 [package.source]
-reference = "b1e96b1d3c871c6e621d5463a3515cfb652ea5db"
+reference = "6165ff2d4f95618d6be99c5bc44fc707685364e1"
 type = "git"
 url = "https://github.com/viper-framework/ScrapySplashWrapper.git"
 [[package]]
@@ -658,8 +658,8 @@ category = "main"
 description = "HTTP library with thread-safe connection pooling, file post, and more."
 name = "urllib3"
 optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4"
-version = "1.25.7"
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, <4"
+version = "1.25.8"
 
 [package.extras]
 brotli = ["brotlipy (>=0.6.0)"]
@@ -1135,8 +1135,8 @@ typing-extensions = [
     {file = "typing_extensions-3.7.4.1.tar.gz", hash = "sha256:091ecc894d5e908ac75209f10d5b4f118fbdb2eb1ede6a63544054bb1edb41f2"},
 ]
 urllib3 = [
-    {file = "urllib3-1.25.7-py2.py3-none-any.whl", hash = "sha256:a8a318824cc77d1fd4b2bec2ded92646630d7fe8619497b142c84a9e6f5a7293"},
-    {file = "urllib3-1.25.7.tar.gz", hash = "sha256:f3c5fd51747d450d4dcf6f923c81f78f811aab8205fda64b0aba34a4e48b0745"},
+    {file = "urllib3-1.25.8-py2.py3-none-any.whl", hash = "sha256:2f3db8b19923a873b3e5256dc9c2dedfa883e33d87c690d9c7913e1f40673cdc"},
+    {file = "urllib3-1.25.8.tar.gz", hash = "sha256:87716c2d2a7121198ebcb7ce7cccf6ce5e9ba539041cfbaeecfb641dc0bf6acc"},
 ]
 w3lib = [
     {file = "w3lib-1.21.0-py2.py3-none-any.whl", hash = "sha256:847704b837b2b973cddef6938325d466628e6078266bc2e1f7ac49ba85c34823"},