Merge branch 'new_popup'

config/generic.json.sample

@@ -3,10 +3,11 @@
   "splash_loglevel": "WARNING",
   "only_global_lookups": true,
   "splash_url": "http://127.0.0.1:8050",
+  "default_user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36",
   "cache_clean_user": {},
   "time_delta_on_index": {
-    "weeks": 0,
+    "weeks": 1,
-    "days": 1,
+    "days": 0,
     "hours": 0
   },
   "enable_mail_notification": false,
@@ -23,6 +24,7 @@
     "splash_loglevel": "(Splash) INFO is *very* verbose.",
     "only_global_lookups": "Set it to True if your instance is publicly available so users aren't able to scan your internal network",
     "splash_url": "URL to connect to splash",
+    "default_user_agent": "Ultimate fallback if the capture form, or the asynchronous submission, don't provide a UA",
     "cache_clean_user": "Format: {username: password}",
     "time_delta_on_index": "Time interval of the capture displayed on the index",
     "enable_mail_notification": "Enable email notification or not",

config/modules.json.sample

@@ -2,5 +2,8 @@
   "VirusTotal": {
     "apikey": "KEY",
     "autosubmit": false
+  },
+  "SaneJS": {
+    "enabled": true
   }
 }

doc/notes_papers.md

@@ -0,0 +1,43 @@
+# AdGraph
+
+## Implementation
+
+* https://github.com/uiowa-irl/AdGraph
+
+4000+ lines of patch on Chromium version 69.0.3441.0 (released 25 May 2018)
+
+## Paper
+
+* https://umariqbal.com/papers/adgraph-sp2020.pdf
+
+## Key points for lookyloo
+
+### Static, node by node
+
+* features of the node
+* keywords in URL
+* keywords in content
+* length & parameters of the URL
+* On image: OCR (?)
+
+* Domain => blocklists (ublock)
+
+* Javascript analysis:
+  * eval
+  * specific keywords (tracking, ads, fingerprint...)
+  * specific JS calls (track mouse, scrolling)
+  * Async calls are very often used by ads, recommandation: https://www.iab.com/wp-content/uploads/2017/08/IABNewAdPortfolio_FINAL_2017.pdf
+  * /!\ anything obfuscated is just under the radar
+
+### Dynamic, pased on the tree
+
+* size
+* position in the tree
+* parent features
+* siblings
+* number and type of children
+
+# Other ressources
+
+* Ads standards: https://github.com/InteractiveAdvertisingBureau - https://iabtechlab.com/standards/
+* Standard API for Ads bidding: https://github.com/prebid/

lookyloo/exceptions.py

@@ -20,3 +20,7 @@ class CreateDirectoryException(LookylooException):
 
 class ConfigError(LookylooException):
     pass
+
+
+class MissingUUID(LookylooException):
+    pass

lookyloo/lookyloo.py

@@ -18,14 +18,13 @@ from uuid import uuid4
 from zipfile import ZipFile
 
 from defang import refang  # type: ignore
-from har2tree import CrawledTree, Har2TreeError, HarFile
+from har2tree import CrawledTree, Har2TreeError, HarFile, HostNode, URLNode
-from pysanejs import SaneJS
 from redis import Redis
 from scrapysplashwrapper import crawl
 
-from .exceptions import NoValidHarFile
+from .exceptions import NoValidHarFile, MissingUUID
 from .helpers import get_homedir, get_socket_path, load_cookies, load_configs, safe_create_dir, get_email_template
-from .modules import VirusTotal
+from .modules import VirusTotal, SaneJavaScript
 
 
 class Lookyloo():
@@ -50,17 +49,14 @@ class Lookyloo():
                 self.vt = VirusTotal(self.configs['modules']['VirusTotal'])
                 if not self.vt.available:
                     self.logger.warning('Unable to setup the VirusTotal module')
+            if 'SaneJS' in self.configs['modules']:
+                self.sanejs = SaneJavaScript(self.configs['modules']['SaneJS'])
+                if not self.sanejs.available:
+                    self.logger.warning('Unable to setup the SaneJS module')
 
         if not self.redis.exists('cache_loaded'):
             self._init_existing_dumps()
 
-        # Try to reach sanejs
-        self.sanejs = SaneJS()
-        if not self.sanejs.is_up:
-            self.use_sane_js = False
-        else:
-            self.use_sane_js = True
-
     def rebuild_cache(self) -> None:
         self.redis.flushdb()
         self._init_existing_dumps()
@@ -88,6 +84,18 @@ class Lookyloo():
             sample_config = json.load(_c)
         return sample_config[entry]
 
+    def get_urlnode_from_tree(self, capture_dir: Path, node_uuid: str) -> URLNode:
+        ct = self._load_pickle(capture_dir / 'tree.pickle')
+        if not ct:
+            raise MissingUUID(f'Unable to find UUID {node_uuid} in {capture_dir}')
+        return ct.root_hartree.get_url_node_by_uuid(node_uuid)
+
+    def get_hostnode_from_tree(self, capture_dir: Path, node_uuid: str) -> HostNode:
+        ct = self._load_pickle(capture_dir / 'tree.pickle')
+        if not ct:
+            raise MissingUUID(f'Unable to find UUID {node_uuid} in {capture_dir}')
+        return ct.root_hartree.get_host_node_by_uuid(node_uuid)
+
     def get_statistics(self, capture_dir: Path) -> Dict[str, Any]:
         # We need the pickle
         ct = self._load_pickle(capture_dir / 'tree.pickle')
@@ -151,7 +159,7 @@ class Lookyloo():
             self.redis.hset('lookup_dirs', uuid, str(capture_dir))
             return
 
-        har = HarFile(har_files[0])
+        har = HarFile(har_files[0], uuid)
 
         redirects = har.initial_redirects
         incomplete_redirects = False
@@ -268,7 +276,7 @@ class Lookyloo():
         except Exception as e:
             logging.exception(e)
 
-    def load_tree(self, capture_dir: Path) -> Tuple[str, str, str, str, str, Dict[str, str]]:
+    def load_tree(self, capture_dir: Path) -> Tuple[str, str, str, str, Dict[str, str]]:
         har_files = sorted(capture_dir.glob('*.har'))
         pickle_file = capture_dir / 'tree.pickle'
         try:
@@ -284,7 +292,7 @@ class Lookyloo():
                 ct = CrawledTree(har_files, uuid)
                 with pickle_file.open('wb') as _p:
                     pickle.dump(ct, _p)
-            return str(pickle_file), ct.to_json(), ct.start_time.isoformat(), ct.user_agent, ct.root_url, meta
+            return ct.to_json(), ct.start_time.isoformat(), ct.user_agent, ct.root_url, meta
         except Har2TreeError as e:
             raise NoValidHarFile(e.message)
 
@@ -312,11 +320,6 @@ class Lookyloo():
     def get_capture(self, capture_dir: Path) -> BytesIO:
         return self._get_raw(capture_dir)
 
-    def sane_js_query(self, sha512: str) -> Dict[str, Any]:
-        if self.use_sane_js:
-            return self.sanejs.sha512(sha512)
-        return {'response': []}
-
     def scrape(self, url: str, cookies_pseudofile: Optional[BufferedIOBase]=None,
                depth: int=1, listing: bool=True, user_agent: Optional[str]=None,
                perma_uuid: str=None, os: str=None, browser: str=None) -> Union[bool, str]:
@@ -339,7 +342,12 @@ class Lookyloo():
                 return False
 
         cookies = load_cookies(cookies_pseudofile)
-        items = crawl(self.splash_url, url, cookies=cookies, depth=depth, user_agent=user_agent,
+        if not user_agent:
+            # Catch case where the UA is broken on the UI, and the async submission.
+            ua: str = self.get_config('default_user_agent')  # type: ignore
+        else:
+            ua = user_agent
+        items = crawl(self.splash_url, url, cookies=cookies, depth=depth, user_agent=ua,
                       log_enabled=True, log_level=self.get_config('splash_loglevel'))
         if not items:
             # broken

lookyloo/modules.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
-from typing import Dict, Any, Optional
+from typing import Dict, Any, Optional, List, Union
 from datetime import date
 import hashlib
 import json
@@ -13,6 +13,104 @@ from .helpers import get_homedir
 from .exceptions import ConfigError
 
 import vt  # type: ignore
+from pysanejs import SaneJS
+
+
+class SaneJavaScript():
+
+    skip_lookup: Dict[str, str] = {
+        "717ea0ff7f3f624c268eccb244e24ec1305ab21557abb3d6f1a7e183ff68a2d28f13d1d2af926c9ef6d1fb16dd8cbe34cd98cacf79091dddc7874dcee21ecfdc": "This is a 1*1 pixel GIF",
+        "e508d5d17e94d14b126164082342a9ca4774f404e87a3dd56c26812493ee18d9c3d6daacca979134a94a003066aca24116de874596d00d1e52130c1283d54209": "This is a 1*1 pixel GIF",
+        "2d073e10ae40fde434eb31cbedd581a35cd763e51fb7048b88caa5f949b1e6105e37a228c235bc8976e8db58ed22149cfccf83b40ce93a28390566a28975744a": "This is a 1*1 pixel GIF",
+        "84e24a70b78e9de9c9d0dfeb49f3f4247dbc1c715d8844471ee40669270682e199d48f5fbec62bd984c9c0270534b407c4d2561dd6c05adec3c83c1534f32d5c": "This is a 1*1 pixel GIF",
+        "d5da26b5d496edb0221df1a4057a8b0285d15592a8f8dc7016a294df37ed335f3fde6a2252962e0df38b62847f8b771463a0124ef3f84299f262ed9d9d3cee4c": "This is a 1*1 pixel GIF",
+        "f7a5f748f4c0d3096a3ca972886fe9a9dff5dce7792779ec6ffc42fa880b3815e2e4c3bdea452352f3844b81864c9bfb7861f66ac961cfa66cb9cb4febe568e8": "This is a 1*1 pixel GIF",
+        "b2ca25a3311dc42942e046eb1a27038b71d689925b7d6b3ebb4d7cd2c7b9a0c7de3d10175790ac060dc3f8acf3c1708c336626be06879097f4d0ecaa7f567041": "This is a 1*1 pixel GIF",
+        "b8d82d64ec656c63570b82215564929adad167e61643fd72283b94f3e448ef8ab0ad42202f3537a0da89960bbdc69498608fc6ec89502c6c338b6226c8bf5e14": "This is a 1*1 pixel GIF",
+        "2991c3aa1ba61a62c1cccd990c0679a1fb8dccd547d153ec0920b91a75ba20820de1d1c206f66d083bf2585d35050f0a39cd7a3e11c03882dafec907d27a0180": "This is a 1*1 pixel GIF",
+        "b1a6cfa7b21dbb0b281d241af609f3ba7f3a63e5668095bba912bf7cfd7f0320baf7c3b0bfabd0f8609448f39902baeb145ba7a2d8177fe22a6fcea03dd29be1": "This is a 1*1 pixel GIF",
+        "ebfe0c0df4bcc167d5cb6ebdd379f9083df62bef63a23818e1c6adf0f64b65467ea58b7cd4d03cf0a1b1a2b07fb7b969bf35f25f1f8538cc65cf3eebdf8a0910": "This is a 1*1 pixel GIF",
+        "1d68b92e8d822fe82dc7563edd7b37f3418a02a89f1a9f0454cca664c2fc2565235e0d85540ff9be0b20175be3f5b7b4eae1175067465d5cca13486aab4c582c": "This is a 1*1 pixel GIF",
+        "ac44da7f455bfae52b883639964276026fb259320902aa813d0333e021c356a7b3e3537b297f9a2158e588c302987ce0854866c039d1bb0ffb27f67560739db2": "This is a 1*1 pixel GIF",
+        "921944dc10fbfb6224d69f0b3ac050f4790310fd1bcac3b87c96512ad5ed9a268824f3f5180563d372642071b4704c979d209baf40bc0b1c9a714769aba7dfc7": "This is a 1*1 pixel GIF",
+        "89dfc38ec77cf258362e4db7c8203cae8a02c0fe4f99265b0539ec4f810c84f8451e22c9bef1ebc59b4089af7e93e378e053c542a5967ec4912d4c1fc5de22f0": "This is a 1*1 pixel GIF",
+        "280ea4383ee6b37051d91c5af30a5ce72aa4439340fc6d31a4fbe7ba8a8156eb7893891d5b2371b9fc4934a78f08de3d57e5b63fa9d279a317dcbefb8a07a6b0": "This is a 1*1 pixel GIF",
+        "3844065e1dd778a05e8cc39901fbf3191ded380d594359df137901ec56ca52e03d57eb60acc2421a0ee74f0733bbb5d781b7744685c26fb013a236f49b02fed3": "This is a 1*1 pixel GIF",
+        "bd9ab35dde3a5242b04c159187732e13b0a6da50ddcff7015dfb78cdd68743e191eaf5cddedd49bef7d2d5a642c217272a40e5ba603fe24ca676a53f8c417c5d": "This is a 1*1 pixel GIF",
+        "d052ecec2839340876eb57247cfc2e777dd7f2e868dc37cd3f3f740c8deb94917a0c9f2a4fc8229987a0b91b04726de2d1e9f6bcbe3f9bef0e4b7e0d7f65ea12": "This is a 1*1 pixel GIF",
+        "8717074ddf1198d27b9918132a550cb4ba343794cc3d304a793f9d78c9ff6c4929927b414141d40b6f6ad296725520f4c63edeb660ed530267766c2ab74ee4a9": "This is a 1*1 pixel GIF",
+        "6834f1548f26b94357fcc3312a3491e8c87080a84f678f990beb2c745899a01e239964521e64a534d7d5554222f728af966ec6ec8291bc64d2005861bcfd78ec": "This is a 1*1 pixel GIF",
+        "3be8176915593e79bc280d08984a16c29c495bc53be9b439276094b8dcd3764a3c72a046106a06b958e08e67451fe02743175c621a1faa261fe7a9691cc77141": "This is a 1*1 pixel GIF",
+        "826225fc21717d8861a05b9d2f959539aad2d2b131b2afed75d88fbca535e1b0d5a0da8ac69713a0876a0d467848a37a0a7f926aeafad8cf28201382d16466ab": "This is a 1*1 pixel GIF",
+        "202612457d9042fe853daab3ddcc1f0f960c5ffdbe8462fa435713e4d1d85ff0c3f197daf8dba15bda9f5266d7e1f9ecaeee045cbc156a4892d2f931fe6fa1bb": "This is a 1*1 pixel GIF",
+        "b82c6aa1ae927ade5fadbbab478cfaef26d21c1ac441f48e69cfc04cdb779b1e46d7668b4368b933213276068e52f9060228907720492a70fd9bc897191ee77c": "This is a 1*1 pixel GIF",
+        "763de1053a56a94eef4f72044adb2aa370b98ffa6e0add0b1cead7ee27da519e223921c681ae1db3311273f45d0dd3dc022d102d42ce210c90cb3e761b178438": "This is a 1*1 pixel GIF",
+        "69e2da5cdc318fc237eaa243b6ea7ecc83b68dbdea8478dc69154abdda86ecb4e16c35891cc1facb3ce7e0cf19d5abf189c50f59c769777706f4558f6442abbc": "This is a 1*1 pixel GIF",
+        "16dd1560fdd43c3eee7bcf622d940be93e7e74dee90286da37992d69cea844130911b97f41c71f8287b54f00bd3a388191112f490470cf27c374d524f49ba516": "This is a 1*1 pixel GIF",
+        "01211111688dc2007519ff56603fbe345d057337b911c829aaee97b8d02e7d885e7a2c2d51730f54a04aebc1821897c8041f15e216f1c973ed313087fa91a3fb": "This is a 1*1 pixel GIF",
+        "71db01662075fac031dea18b2c766826c77dbab01400a8642cdc7059394841d5df9020076554c3beca6f808187d42e1a1acc98fad9a0e1ad32ae869145f53746": "This is a 1*1 pixel GIF",
+        # "": "This is a 1*1 pixel GIF",
+        "f1c33e72643ce366fd578e3b5d393799e8c9ea27b180987826af43b4fc00b65a4eaae5e6426a23448956fee99e3108c6a86f32fb4896c156e24af0571a11c498": "This is a 1*1 pixel PNG",
+        "dc7c40381b3d22919e32c1b700ccb77b1b0aea2690642d01c1ac802561e135c01d5a4d2a0ea18efc0ec3362e8c549814a10a23563f1f56bd62aee0ced7e2bd99": "This is a 1*1 pixel PNG",
+        "c2c239cb5cdd0b670780ad6414ef6be9ccd4c21ce46bb93d1fa3120ac812f1679445162978c3df05cb2e1582a1844cc4c41cf74960b8fdae3123999c5d2176cc": "This is a 1*1 pixel PNG",
+        # "": "This is a 1*1 pixel PNG",
+        "cf83e1357eefb8bdf1542850d66d8007d620e4050b5715dc83f4a921d36ce9ce47d0d13c5d85f2b0ff8318d2877eec2f63b931bd47417a81a538327af927da3e": "This is an empty file"
+    }
+
+    def __init__(self, config: Dict[str, Any]):
+        if not ('enabled' in config or config['enabled']):
+            self.available = False
+            return
+        self.client = SaneJS()
+        if not self.client.is_up:
+            self.available = False
+            return
+        self.available = True
+        self.storage_dir = get_homedir() / 'sanejs'
+        self.storage_dir.mkdir(parents=True, exist_ok=True)
+
+    def hashes_lookup(self, sha512: Union[List[str], str], force: bool=False) -> Dict[str, Any]:
+        if isinstance(sha512, str):
+            hashes = [sha512]
+        else:
+            hashes = sha512
+
+        today_dir = self.storage_dir / date.today().isoformat()
+        today_dir.mkdir(parents=True, exist_ok=True)
+        sanejs_unknowns = today_dir / 'unknown'
+        unknown_hashes = []
+        if sanejs_unknowns.exists():
+            with sanejs_unknowns.open() as f:
+                unknown_hashes = [line.strip() for line in f.readlines()]
+
+        to_return = {h: details for h, details in self.skip_lookup.items() if h in sha512}
+
+        to_lookup = [h for h in hashes if h not in self.skip_lookup]
+        if not force:
+            to_lookup = [h for h in to_lookup if (h not in unknown_hashes
+                                                  and not (today_dir / h).exists())]
+        for h in to_lookup:
+            response = self.client.sha512(h)
+            if 'error' in response:
+                # Server not ready
+                break
+            if 'response' in response and response['response']:
+                cached_path = today_dir / h
+                with cached_path.open('w') as f:
+                    json.dump(response['response'], f)
+                to_return[h] = response['response']
+            else:
+                unknown_hashes.append(h)
+
+        for h in hashes:
+            cached_path = today_dir / h
+            if h in unknown_hashes or h in to_return:
+                continue
+            elif cached_path.exists():
+                with cached_path.open() as f:
+                    to_return[h] = json.load(f)
+
+        return to_return
 
 
 class VirusTotal():

website/web/__init__.py

@@ -1,15 +1,14 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
-import json
-import pickle
 from zipfile import ZipFile, ZIP_DEFLATED
 from io import BytesIO
 import os
 from pathlib import Path
 from datetime import datetime, timedelta
+import json
 
-from flask import Flask, render_template, request, session, send_file, redirect, url_for, Response, flash
+from flask import Flask, render_template, request, send_file, redirect, url_for, Response, flash
 from flask_bootstrap import Bootstrap  # type: ignore
 from flask_httpauth import HTTPDigestAuth  # type: ignore
 
@@ -18,7 +17,7 @@ from lookyloo.lookyloo import Lookyloo
 from lookyloo.exceptions import NoValidHarFile
 from .proxied import ReverseProxied
 
-from typing import Tuple, Optional, Dict, Any
+from typing import Optional, Dict, Any
 
 import logging
 
@@ -48,6 +47,19 @@ time_delta_on_index = lookyloo.get_config('time_delta_on_index')
 logging.basicConfig(level=lookyloo.get_config('loglevel'))
 
 
+# Method to make sizes in bytes human readable
+# Source: https://stackoverflow.com/questions/1094841/reusable-library-to-get-human-readable-version-of-file-size
+def sizeof_fmt(num, suffix='B'):
+    for unit in ['', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi']:
+        if abs(num) < 1024.0:
+            return "%3.1f%s%s" % (num, unit, suffix)
+        num /= 1024.0
+    return "%.1f%s%s" % (num, 'Yi', suffix)
+
+
+app.jinja_env.globals.update(sizeof_fmt=sizeof_fmt)
+
+
 @auth.get_password
 def get_pw(username: str) -> Optional[str]:
     if username in user:
@@ -79,14 +91,6 @@ def rebuild_tree(tree_uuid: str):
     return redirect(url_for('index'))
 
 
-# keep
-def load_tree(capture_dir: Path) -> Tuple[str, str, str, str, Dict[str, Any]]:
-    session.clear()
-    temp_file_name, tree_json, tree_time, tree_ua, tree_root_url, meta = lookyloo.load_tree(capture_dir)
-    session["tree"] = temp_file_name
-    return tree_json, tree_time, tree_ua, tree_root_url, meta
-
-
 @app.route('/submit', methods=['POST', 'GET'])
 def submit():
     to_query = request.get_json(force=True)
@@ -116,11 +120,12 @@ def scrape_web():
     return render_template('scrape.html', user_agents=user_agents)
 
 
-@app.route('/tree/hostname/<string:node_uuid>/text', methods=['GET'])
+@app.route('/tree/<string:tree_uuid>/hostname/<string:node_uuid>/text', methods=['GET'])
-def hostnode_details_text(node_uuid: str):
+def hostnode_details_text(tree_uuid: str, node_uuid: str):
-    with open(session["tree"], 'rb') as f:
+    capture_dir = lookyloo.lookup_capture_dir(tree_uuid)
-        ct = pickle.load(f)
+    if not capture_dir:
-    hostnode = ct.root_hartree.get_host_node_by_uuid(node_uuid)
+        return
+    hostnode = lookyloo.get_hostnode_from_tree(capture_dir, node_uuid)
     urls = []
     for url in hostnode.urls:
         urls.append(url.name)
@@ -134,27 +139,85 @@ def hostnode_details_text(node_uuid: str):
                      as_attachment=True, attachment_filename='file.md')
 
 
-@app.route('/tree/hostname/<string:node_uuid>', methods=['GET'])
+@app.route('/tree/<string:tree_uuid>/hostname_popup/<string:node_uuid>', methods=['GET'])
-def hostnode_details(node_uuid: str):
+def hostnode_popup(tree_uuid: str, node_uuid: str):
-    with open(session["tree"], 'rb') as f:
+    capture_dir = lookyloo.lookup_capture_dir(tree_uuid)
-        ct = pickle.load(f)
+    if not capture_dir:
-    hostnode = ct.root_hartree.get_host_node_by_uuid(node_uuid)
+        return
+    hostnode = lookyloo.get_hostnode_from_tree(capture_dir, node_uuid)
+    keys_response = {
+        'js': "/static/javascript.png",
+        'exe': "/static/exe.png",
+        'css': "/static/css.png",
+        'font': "/static/font.png",
+        'html': "/static/html.png",
+        'json': "/static/json.png",
+        'iframe': "/static/ifr.png",
+        'image': "/static/img.png",
+        'unknown_mimetype': "/static/wtf.png",
+        'video': "/static/video.png",
+        'response_cookie': "/static/cookie_received.png",
+        'redirect': "/static/redirect.png",
+        'redirect_to_nothing': "/static/cookie_in_url.png"
+    }
+    keys_request = {
+        'request_cookie': "/static/cookie_read.png",
+    }
+
     urls = []
+    if lookyloo.sanejs.available:
+        to_lookup = [url.body_hash for url in hostnode.urls if hasattr(url, 'body_hash')]
+        lookups = lookyloo.sanejs.hashes_lookup(to_lookup)
     for url in hostnode.urls:
-        if hasattr(url, 'body_hash'):
+        if lookyloo.sanejs.available and hasattr(url, 'body_hash') and url.body_hash in lookups:
-            sane_js_r = lookyloo.sane_js_query(url.body_hash)
+            url.add_feature('sane_js_details', lookups[url.body_hash])
-            if sane_js_r.get('response'):
+            if lookups[url.body_hash]:
-                url.add_feature('sane_js_details', sane_js_r['response'])
+                if isinstance(lookups[url.body_hash], list):
-                print('######## SANEJS ##### ', url.sane_js_details)
+                    libname, version, path = lookups[url.body_hash][0].split("|")
-        urls.append(url.to_json())
+                    other_files = len(lookups[url.body_hash])
-    return json.dumps(urls)
+                    url.add_feature('sane_js_details_to_print', (libname, version, path, other_files))
+                else:
+                    # Predefined generic file
+                    url.add_feature('sane_js_details_to_print', lookups[url.body_hash])
+        urls.append(url)
+    return render_template('hostname_popup.html',
+                           tree_uuid=tree_uuid,
+                           hostname_uuid=node_uuid,
+                           hostname=hostnode.name,
+                           urls=urls,
+                           keys_response=keys_response,
+                           keys_request=keys_request)
 
 
-@app.route('/tree/url/<string:node_uuid>', methods=['GET'])
+@app.route('/tree/<string:tree_uuid>/url/<string:node_uuid>/posted_data', methods=['GET'])
-def urlnode_details(node_uuid: str):
+def urlnode_post_request(tree_uuid: str, node_uuid: str):
-    with open(session["tree"], 'rb') as f:
+    capture_dir = lookyloo.lookup_capture_dir(tree_uuid)
-        ct = pickle.load(f)
+    if not capture_dir:
-    urlnode = ct.root_hartree.get_url_node_by_uuid(node_uuid)
+        return
+    urlnode = lookyloo.get_urlnode_from_tree(capture_dir, node_uuid)
+    if not urlnode.posted_data:
+        return
+    if isinstance(urlnode.posted_data, (dict, list)):
+        # JSON blob, pretty print.
+        posted = json.dumps(urlnode.posted_data, indent=2)
+    else:
+        posted = urlnode.posted_data
+
+    if isinstance(posted, bytes):
+        to_return = BytesIO(posted)
+    else:
+        to_return = BytesIO(posted.encode())
+    to_return.seek(0)
+    return send_file(to_return, mimetype='text/plain',
+                     as_attachment=True, attachment_filename='posted_data.txt')
+
+
+@app.route('/tree/<string:tree_uuid>/url/<string:node_uuid>', methods=['GET'])
+def urlnode_details(tree_uuid: str, node_uuid: str):
+    capture_dir = lookyloo.lookup_capture_dir(tree_uuid)
+    if not capture_dir:
+        return
+    urlnode = lookyloo.get_urlnode_from_tree(capture_dir, node_uuid)
     to_return = BytesIO()
     got_content = False
     if hasattr(urlnode, 'body'):
@@ -300,7 +363,7 @@ def tree(tree_uuid: str):
             enable_mail_notification = True
         else:
             enable_mail_notification = False
-        tree_json, start_time, user_agent, root_url, meta = load_tree(capture_dir)
+        tree_json, start_time, user_agent, root_url, meta = lookyloo.load_tree(capture_dir)
         return render_template('tree.html', tree_json=tree_json, start_time=start_time,
                                user_agent=user_agent, root_url=root_url, tree_uuid=tree_uuid,
                                meta=meta, enable_mail_notification=enable_mail_notification)

website/web/static/tree.js

@@ -92,163 +92,22 @@ d3.selection.prototype.moveToBack = function() {
     });
 };
 
-// What happen when clicking on a domain (load a modal display)
+function hostnode_click_popup(d) {
-function hostnode_click(d) {
+    window.open('/tree/' + treeUUID + '/hostname_popup/' + d.data.uuid, '_blank', 'width=1024,height=768,left=200,top=100');
-    // Move the node to the front (end of the list)
+};
-    var cur_node = d3.select("#node_" + d.data.uuid).moveToFront();
-    // Avoid duplicating overlays
-    cur_node.selectAll('.overlay').remove();
-    // Insert new svg element at this position
-    var overlay_hostname = cur_node.append('g')
-                                .attr('class', 'overlay');
 
-    cur_node.append('line')
+function ProcessChildMessage(message) {
-                .attr('id', 'overlay_link')
+    var element = document.getElementById("node_" + message);
-                .style("opacity", "0.95")
+    element.scrollIntoView({behavior: "smooth", block: "center", inline: "nearest"});
-                .attr("stroke-width", "2")
-                .style("stroke", "gray");
 
-    var top_margin = 15;
+    var to_blink = d3.select("#node_" + message).select('text');
-    var overlay_header_height = 50;
+    to_blink
-    var left_margin = 30;
+        .transition().duration(500)  //Set transition
-
+        .style('fill', 'red')
-    overlay_hostname
+        .style('font-size', '20px')
-        .datum({x: 0, y: 0, overlay_uuid: d.data.uuid})
+        .transition().duration(500)  //Set transition
-        .attr('id', 'overlay_' + d.data.uuid)
+        .style('fill', 'black')
-        .attr("transform", "translate(" + 10 + "," + 15 + ")")
+        .style('font-size', '16px');
-        .call(d3.drag().on("drag", function(d, i) {
-            if (typeof d.x === 'undefined') { d.x = 0; }  // Any real JS dev would kill me fo that, right?
-            if (typeof d.y === 'undefined') { d.y = 0; }  // Maybe even twice.
-            d.x += d3.event.dx
-            d.y += d3.event.dy
-            d3.select(this)
-                .attr("transform", "translate(" + d.x + "," + d.y + ")");
-            cur_node.select('#overlay_link')
-                .attr("x2", d.x + left_margin + 10)
-                .attr("y2", d.y + top_margin + 15);
-        }));
-
-    overlay_hostname.append('rect')
-        .attr("rx", 6)
-        .attr("ry", 6)
-        .attr('x', 15)
-        .attr('y', 10)
-        .style("opacity", "0.95")
-        .attr("stroke", "black")
-        .attr('stroke-opacity', "0.8")
-        .attr("stroke-width", "2")
-        .attr("stroke-linecap", "round")
-        .attr("fill", "white");
-
-    // Modal display
-    var url = "/tree/hostname/" + d.data.uuid;
-    d3.json(url, {credentials: 'same-origin'}).then(urls => {
-        overlay_hostname
-            .append('circle')
-            .attr('id', 'overlay_circle_' + d.data.uuid)
-            .attr('height', overlay_header_height)
-            .attr('cx', left_margin + 10)
-            .attr('cy', top_margin + 15)
-            .attr('r', 2);
-
-        overlay_hostname
-            .append('text')
-            .attr('id', 'overlay_close_' + d.data.uuid)
-            .attr('height', overlay_header_height)
-            .attr('x', left_margin + 500)  // Value updated based on the size of the rectangle max: max_overlay_width
-            .attr('y', top_margin + 25)
-            .style("font-size", '30px')
-            .text('\u2716')
-            .attr('cursor', 'pointer')
-            .on("click", () => {
-                    main_svg.selectAll('#overlay_' + d.data.uuid).remove();
-                    cur_node.select('#overlay_link').remove();
-                }
-            );
-
-        overlay_hostname.append('line')
-            .attr('id', 'overlay_separator_header' + d.data.uuid)
-            .style("stroke", "black")
-            .style('stroke-width', "1px")
-            .attr('x1', 20)
-            .attr('y1', overlay_header_height)
-            .attr('x2', 500)
-            .attr('y2', overlay_header_height);
-
-        var url_entries = overlay_hostname.append('svg');
-
-        var interval_entries = 10;
-        urls.forEach((url, index, array) => {
-            var jdata = JSON.parse(url);
-            var url_data = url_entries.append('svg')
-                                      .attr('class', 'url_data');
-            url_data.datum({'data': jdata});
-            url_data.append(d => text_entry(left_margin, top_margin + overlay_header_height + (interval_entries * index), urlnode_click, d));
-            url_data.append(d => icon_list(left_margin + 5, top_margin + 20 + overlay_header_height + (interval_entries * index), d, url_view=true));
-        });
-
-        var cur_url_data_height = 0;
-        url_entries.selectAll('.url_data').each(function(p, j){
-            d3.select(this).attr('y', cur_url_data_height);
-            cur_url_data_height += d3.select(this).node().getBBox().height;
-            var cur_icon_list_len = 0;
-            // set position of icons based of their length
-            d3.select(this).selectAll('.icon').each(function(p, j){
-                d3.select(this).attr('x', cur_icon_list_len);
-                cur_icon_list_len += d3.select(this).node().getBBox().width;
-            });
-        });
-
-        var overlay_bbox = overlay_hostname.node().getBBox()
-        overlay_hostname.append('line')
-            .attr('id', 'overlay_separator_footer' + d.data.uuid)
-            .style("stroke", "black")
-            .style('stroke-width', "1px")
-            .attr('x1', 20)
-            .attr('y1', overlay_bbox.height + 20)
-            .attr('x2', 500)
-            .attr('y2', overlay_bbox.height + 20);
-
-        var overlay_bbox = overlay_hostname.node().getBBox()
-        overlay_hostname
-            .append('text')
-            .attr('id', 'overlay_download_' + d.data.uuid)
-            .attr('height', overlay_header_height - 10)
-            .attr('x', left_margin)
-            .attr('y', overlay_bbox.height + overlay_header_height)
-            .style("font-size", '20px')
-            .text('Download URLs as text')
-            .attr('cursor', 'pointer')
-            .on("click", () => {
-                var url = "/tree/hostname/" + d.data.uuid + '/text';
-                d3.blob(url, {credentials: 'same-origin'}).then(data => {
-                    saveAs(data, 'file.md');
-                });
-            });
-
-        var overlay_bbox = overlay_hostname.node().getBBox();
-        overlay_hostname.select('rect')
-            .attr('width', () => {
-                optimal_size = overlay_bbox.width + left_margin
-                return optimal_size < max_overlay_width ? optimal_size : max_overlay_width;
-            })
-            .attr('height', overlay_bbox.height + overlay_header_height);
-
-        overlay_hostname.select('#overlay_close_' + d.data.uuid)
-            .attr('x', overlay_hostname.select('rect').node().getBBox().width - 20);
-
-        overlay_hostname.select('#overlay_separator_header' + d.data.uuid)
-            .attr('x2', overlay_hostname.select('rect').node().getBBox().width + 10);
-        overlay_hostname.select('#overlay_separator_footer' + d.data.uuid)
-            .attr('x2', overlay_hostname.select('rect').node().getBBox().width + 10);
-
-
-        cur_node.select('#overlay_link')
-                    .attr("x1", 10)
-                    .attr("y1", 0)
-                    .attr("x2", left_margin + 3)
-                    .attr("y2", top_margin + 7);
-    });
 };
 
 function icon(key, icon_path, d, icon_size){
@@ -483,7 +342,7 @@ function update(root, computed_node_width=0) {
 
             // Set Hostname text
             node_data
-              .append(d => text_entry(15, 5, hostnode_click, d));
+              .append(d => text_entry(15, 5, hostnode_click_popup, d));  // Popup
             // Set list of icons
             node_data
               .append(d => icon_list(17, 35, d));

website/web/templates/hostname_popup.html

@@ -0,0 +1,78 @@
+{% extends "main.html" %}
+
+{% block title %}Details for {{ hostname }} {% endblock %}
+
+{% block scripts %}
+  <script>
+      function whereAmI() {
+          window.opener.ProcessChildMessage("{{ hostname_uuid }}");
+      };
+  </script>
+{% endblock %}
+
+{% block content %}
+  <center>
+    <h3>{{ hostname }}</h3>
+    <button type="button" class="btn btn-secondary" onclick="whereAmI()">Locate node on tree</button>
+    <a href="{{ url_for('hostnode_details_text', tree_uuid=tree_uuid, node_uuid=hostname_uuid) }}" class="btn btn-info" role="button">Get URLs as text</a>
+  </center>
+  <p>Click on the URL to get the content of the response</p>
+  <ul class="list-group-flush">
+    {% for url in urls %}
+    <li class="list-group-item">
+      <p class="h3">{{ url.name }}</p>
+      <ul class="list-group">
+        <li class="list-group-item">
+          <p class="h4">Response</p>
+          <div>
+          {% for key, path in keys_response.items() %}
+            {% if url[key] %}
+              <img src="{{ path }}" alt="{{ key }}" width="21" height="21"/>
+            {%endif%}
+          {% endfor %}
+          </div>
+          {% if not url.empty_response %}
+          <div>
+            <a href="{{ url_for('urlnode_details', tree_uuid=tree_uuid, node_uuid=url.uuid) }}">
+              Download response body.
+            </a></br>
+            Body size: {{ sizeof_fmt(url.body.getbuffer().nbytes) }}
+          </div>
+          {% else %}
+            Empty body.
+          {%endif%}
+          {% if url.sane_js_details_to_print %}
+          <div>
+            {% if url.sane_js_details_to_print is string %}
+              {{ url.sane_js_details_to_print }}
+            {% else %}
+              This file is known as part of <b>{{ url.sane_js_details_to_print[0] }}</b>
+              version <b>{{ url.sane_js_details_to_print[1] }}</b>: <b>{{ url.sane_js_details_to_print[2] }}</b>.
+              {% if url.sane_js_details_to_print[3] > 1%}
+              It is also present in <b>{{ url.sane_js_details_to_print[3] -1 }}</b> other libraries.
+              {%endif%}
+            {%endif%}
+          </div>
+          {% endif %}
+        </li>
+        <li class="list-group-item">
+          <p class="h4">Request</p>
+          <div>
+          {% for key, path in keys_request.items() %}
+            {% if url[key] %}
+              <img src="{{ path }}" alt="{{ key }}" width="21" height="21"/>
+            {%endif%}
+          {% endfor %}
+          </div>
+          {% if url.posted_data %}
+          <a href="{{ url_for('urlnode_post_request', tree_uuid=tree_uuid, node_uuid=url.uuid) }}">
+              Download posted data
+          </a></br>
+          Posted data size: {{ sizeof_fmt(url.posted_data|length) }}
+          {% endif %}
+        </li>
+      </ul>
+    </li>
+    {% endfor %}
+  </ul>
+{% endblock %}

website/web/templates/scrape.html

@@ -9,6 +9,14 @@
   </center>
   </br>
     <form role="form" action="scrape" method=post enctype=multipart/form-data>
+    <div class="form-group row">
+      <div class="col-sm-10">
+        <div class="form-check">
+          <input class="form-check-input"type="checkbox" name="listing" checked="true"></input>
+          <label for="listing" class="form-check-label">Display results on public page</label>
+        </div>
+      </div>
+    </div>
       <div class="form-group row">
         <label for="url" class="col-sm-2 col-form-label">URL:</label>
         <div class="col-sm-10">
@@ -33,14 +41,6 @@
         </div>
       </div>
 
-      <div class="form-group row">
-        <div class="col-sm-10">
-          <div class="form-check">
-            <input class="form-check-input"type="checkbox" name="listing" checked="true"></input>
-            <label for="listing" class="form-check-label">Display on main page</label>
-          </div>
-        </div>
-      </div>
       <div class="form-group row">
         <label for="cookies" class="col-sm-6">Cookies (JSON export from the Firefox plugin Cookie Quick Manager)</label>
         <div class="col-sm-4">
@@ -89,7 +89,7 @@
           {% endfor%}
       {% endfor%}
       <div class="dropdown-divider"></div>
-      <center><button type="submit" class="btn btn-default">Start looking!</button></center>
+      <center><button type="submit" class="btn btn-primary">Start looking!</button></center>
   </form>
 </div>
 {% endblock %}

website/web/templates/statistics.html

@@ -4,7 +4,6 @@
     <dl class="row">
       <dt class="col-sm-3">{{ key }}</dt>
       <dd class="col-sm-3">{{ value }}</dd>
-    </center>
     </dl>
   {% endfor %}
 {% endif%}

website/web/templates/tree.html

@@ -40,6 +40,7 @@
 {% block content %}
 {{super()}}
 <script>
+  var treeUUID = "{{ tree_uuid }}";
   var treeData = {{ tree_json | safe }};
 </script>