chg: [Crawler] change BDD, save i2p links

pull/260/head
Terrtia 2018-08-21 15:54:53 +02:00
parent ed559d9f4a
commit e9580d6775
No known key found for this signature in database
GPG Key ID: 1E1B1F50D84613D0
9 changed files with 567 additions and 64 deletions

View File

@ -18,18 +18,19 @@ from pubsublogger import publisher
def signal_handler(sig, frame):
sys.exit(0)
def crawl_onion(url, domain, date):
def crawl_onion(url, domain, date, date_month):
if not r_onion.sismember('onion_up:'+date , domain) and not r_onion.sismember('onion_down:'+date , domain):
#if not r_onion.sismember('full_onion_up', domain) and not r_onion.sismember('onion_down:'+date , domain):
super_father = r_serv_metadata.hget('paste_metadata:'+paste, 'super_father')
if super_father is None:
super_father=paste
try:
r = requests.get(splash_url , timeout=0.010)
r = requests.get(splash_url , timeout=30.0)
except Exception:
## FIXME: # TODO: relaunch docker
## FIXME: # TODO: relaunch docker or send error message
print('--------------------------------------')
print(' DOCKER SPLASH DOWN')
exit(0)
if r.status_code == 200:
@ -97,11 +98,23 @@ if __name__ == '__main__':
message = p.get_from_set()
# Recovering the streamed message informations.
#message = r_onion.spop('mess_onion')
print(message)
if message is None:
print('get ardb message')
message = r_onion.spop('mess_onion')
if message is not None:
splitted = message.split(';')
if len(splitted) == 2:
url, paste = splitted
if not '.onion' in url:
print('not onion')
continue
url_list = re.findall(url_regex, url)[0]
if url_list[1] == '':
url= 'http://{}'.format(url)
@ -117,15 +130,23 @@ if __name__ == '__main__':
print('domain: {}'.format(domain))
print('domain_url: {}'.format(domain_url))
'''if not r_onion.sismember('full_onion_up', domain):
r_onion.sadd('mess_onion', message)
print('added ..............')'''
if not r_onion.sismember('banned_onion', domain):
date = datetime.datetime.now().strftime("%Y%m%d")
date_month = datetime.datetime.now().strftime("%Y%m")
crawl_onion(url, domain, date)
if not r_onion.sismember('month_onion_up:{}'.format(date_month), domain) and not r_onion.sismember('onion_down:'+date , domain):
crawl_onion(url, domain, date, date_month)
if url != domain_url:
crawl_onion(domain_url, domain, date)
crawl_onion(domain_url, domain, date, date_month)
# save dowm onion
# save down onion
if not r_onion.sismember('onion_up:'+date , domain):
r_onion.sadd('onion_down:'+date , domain)
r_onion.sadd('onion_down_link:'+date , url)
@ -142,14 +163,11 @@ if __name__ == '__main__':
# check external onions links (full_scrawl)
external_domains = set()
for link in r_onion.smembers('domain_onion_external_links:{}'.format(domain)):
print(link)
external_domain = re.findall(url_regex, link)
print(external_domain)
if len(external_domain) > 0:
external_domain = external_domain[0][4]
else:
continue
print(external_domain)
# # TODO: add i2p
if '.onion' in external_domain and external_domain != domain:
external_domains.add(external_domain)
@ -157,6 +175,10 @@ if __name__ == '__main__':
r_onion.sadd('onion_potential_source', domain)
r_onion.delete('domain_onion_external_links:{}'.format(domain))
print(r_onion.smembers('domain_onion_external_links:{}'.format(domain)))
r_onion.lpush('last_onions', domain)
r_onion.ltrim('last_onions', 0, 15)
else:
continue
else:

View File

@ -29,6 +29,7 @@ import os
import base64
import subprocess
import redis
import re
from Helper import Process
@ -96,6 +97,12 @@ if __name__ == "__main__":
db=p.config.getint("Redis_Cache", "db"),
decode_responses=True)
r_onion = redis.StrictRedis(
host=p.config.get("ARDB_Onion", "host"),
port=p.config.getint("ARDB_Onion", "port"),
db=p.config.getint("ARDB_Onion", "db"),
decode_responses=True)
# FUNCTIONS #
publisher.info("Script subscribed to channel onion_categ")
@ -109,6 +116,9 @@ if __name__ == "__main__":
# Thanks to Faup project for this regex
# https://github.com/stricaud/faup
url_regex = "((http|https|ftp)?(?:\://)?([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&%\$\-]+)*@)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|localhost|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.onion)(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&%\$#\=~_\-]+))*)"
i2p_regex = "((http|https|ftp)?(?:\://)?([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&%\$\-]+)*@)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|localhost|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.i2p)(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&%\$#\=~_\-]+))*)"
re.compile(url_regex)
while True:
if message is not None:
@ -127,9 +137,23 @@ if __name__ == "__main__":
url, s, credential, subdomain, domain, host, port, \
resource_path, query_string, f1, f2, f3, f4 = x
if '.onion' in url:
print(url)
domains_list.append(domain)
urls.append(url)
for x in PST.get_regex(i2p_regex):
# Extracting url with regex
url, s, credential, subdomain, domain, host, port, \
resource_path, query_string, f1, f2, f3, f4 = x
if '.i2p' in url:
print('add i2p')
print(domain)
if not r_onion.sismember('i2p_domain', domain):
r_onion.sadd('i2p_domain', domain)
r_onion.sadd('i2p_link', url)
# Saving the list of extracted onion domains.
PST.__setattr__(channel, domains_list)
PST.save_attribute_redis(channel, domains_list)
@ -157,7 +181,18 @@ if __name__ == "__main__":
msg = 'infoleak:automatic-detection="onion";{}'.format(PST.p_path)
p.populate_set_out(msg, 'Tags')
'''
date_month = datetime.datetime.now().strftime("%Y%m")
date = datetime.datetime.now().strftime("%Y%m%d")
for url in urls:
domain = re.findall(url_regex, url)
if len(domain) > 0:
domain = domain[0][4]
else:
continue
if not r_onion.sismember('month_onion_up:{}'.format(date_month), domain) and not r_onion.sismember('onion_down:'+date , domain):
msg = '{};{}'.format(url,PST.p_path)
print('send to crawler')
p.populate_set_out(msg, 'Crawler')

79
bin/packages/HiddenServices.py Executable file
View File

@ -0,0 +1,79 @@
#!/usr/bin/python3
"""
The ``hiddenServices Class``
===================
Use it to create an object from an existing paste or other random file.
Conditions to fulfill to be able to use this class correctly:
-------------------------------------------------------------
1/ The paste need to be saved on disk somewhere (have an accessible path)
2/ The paste need to be gziped.
3/ The filepath need to look like something like this:
/directory/source/year/month/day/paste.gz
"""
import os
import gzip
import redis
import configparser
import sys
sys.path.append(os.path.join(os.environ['AIL_BIN'], 'packages/'))
from Date import Date
class HiddenServices(object):
"""
This class representing a hiddenServices as an object.
When created, the object will have by default some "main attributes"
:Example:
PST = HiddenServices("xxxxxxxx.onion", "onion")
"""
def __init__(self, domain, type):
configfile = os.path.join(os.environ['AIL_BIN'], 'packages/config.cfg')
if not os.path.exists(configfile):
raise Exception('Unable to find the configuration file. \
Did you set environment variables? \
Or activate the virtualenv.')
cfg = configparser.ConfigParser()
cfg.read(configfile)
self.r_serv_onion = redis.StrictRedis(
host=cfg.get("ARDB_Onion", "host"),
port=cfg.getint("ARDB_Onion", "port"),
db=cfg.getint("ARDB_Onion", "db"),
decode_responses=True)
self.domain = domain
self.type = type
if type == 'onion':
self.paste_directory = os.path.join(os.environ['AIL_HOME'], cfg.get("Directories", "pastes"), cfg.get("Directories", "crawled"))
self.screenshot_directory = os.path.join(os.environ['AIL_HOME'], cfg.get("Directories", "crawled_screenshot"))
elif type == 'i2p':
self.paste_directory = os.path.join(os.environ['AIL_HOME'], cfg.get("Directories", "crawled_screenshot"))
self.screenshot_directory = os.path.join(os.environ['AIL_HOME'], cfg.get("Directories", "crawled_screenshot"))
else:
## TODO: # FIXME: add error
pass
def get_last_crawled_pastes(self):
last_check = self.r_serv_onion.hget('onion_metadata:{}'.format(self.domain), 'last_check')
return self.get_crawled_pastes_by_date(last_check)
def get_crawled_pastes_by_date(self, date):
pastes_path = os.path.join(self.paste_directory, date[0:4], date[4:6], date[6:8])
l_crawled_pastes = [f for f in os.listdir(pastes_path) if self.domain in f]
print(len(l_crawled_pastes))
print(l_crawled_pastes)
return l_crawled_pastes

View File

@ -55,6 +55,7 @@ class TorSplashCrawler():
self.domains = [domain]
date = datetime.datetime.now().strftime("%Y/%m/%d")
self.full_date = datetime.datetime.now().strftime("%Y%m%d")
self.date_month = datetime.datetime.now().strftime("%Y%m")
config_section = 'Crawler'
self.p = Process(config_section)
@ -120,6 +121,7 @@ class TorSplashCrawler():
self.r_serv_onion.sadd('onion_up:'+self.full_date , self.domains[0])
self.r_serv_onion.sadd('full_onion_up', self.domains[0])
self.r_serv_onion.sadd('month_onion_up:{}'.format(self.date_month), self.domains[0])
# create onion metadata
if not self.r_serv_onion.exists('onion_metadata:{}'.format(self.domains[0])):

View File

@ -1 +1,2 @@
onion
i2p

View File

@ -0,0 +1,99 @@
#!/usr/bin/env python3
# -*-coding:UTF-8 -*
'''
Flask functions and routes for the trending modules page
'''
import redis
import datetime
from flask import Flask, render_template, jsonify, request, Blueprint
import HiddenServices
from Date import Date
# ============ VARIABLES ============
import Flask_config
app = Flask_config.app
cfg = Flask_config.cfg
r_serv_onion = Flask_config.r_serv_onion
hiddenServices = Blueprint('hiddenServices', __name__, template_folder='templates')
# ============ FUNCTIONS ============
def one():
return 1
def get_date_range(num_day):
curr_date = datetime.date.today()
date = Date( '{}{}{}'.format(str(curr_date.year), str(curr_date.month).zfill(2), str(curr_date.day).zfill(2)) )
date_list = []
for i in range(0, num_day):
date_list.append(date.substract_day(i))
return list(reversed(date_list))
def get_onion_status(domain, date):
if r_serv_onion.sismember('onion_up:'+date , domain):
return True
else:
return False
# ============= ROUTES ==============
@hiddenServices.route("/hiddenServices/", methods=['GET'])
def hiddenServices_page():
last_onions = r_serv_onion.lrange('last_onions', 0 ,-1)
list_onion = []
for onion in last_onions:
metadata_onion = {}
metadata_onion['domain'] = onion
metadata_onion['last_check'] = r_serv_onion.hget('onion_metadata:{}'.format(onion), 'last_check')
metadata_onion['first_seen'] = r_serv_onion.hget('onion_metadata:{}'.format(onion), 'first_seen')
if get_onion_status(onion, metadata_onion['last_check']):
metadata_onion['status_text'] = 'UP'
metadata_onion['status_color'] = 'Green'
metadata_onion['status_icon'] = 'fa-check-circle'
else:
metadata_onion['status_text'] = 'DOWN'
metadata_onion['status_color'] = 'Red'
metadata_onion['status_icon'] = 'fa-times-circle'
list_onion.append(metadata_onion)
return render_template("hiddenServices.html", last_onions=list_onion)
@hiddenServices.route("/hiddenServices/onion_domain", methods=['GET'])
def onion_domain():
onion_domain = request.args.get('onion_domain')
if onion_domain is None or not r_serv_onion.exists('onion_metadata:{}'.format(onion_domain)):
pass
# # TODO: FIXME return 404
last_check = r_serv_onion.hget('onion_metadata:{}'.format(onion_domain), 'last_check')
first_seen = r_serv_onion.hget('onion_metadata:{}'.format(onion_domain), 'first_seen')
date_crawled = r_serv_onion.smembers('onion_history:{}'.format(onion_domain))
return render_template("showDomain.html", domain=onion_domain, last_check=last_check, first_seen=first_seen)
# ============= JSON ==============
@hiddenServices.route("/hiddenServices/domain_crawled_7days_json", methods=['GET'])
def domain_crawled_7days_json():
type = 'onion'
## TODO: # FIXME: 404 error
date_range = get_date_range(7)
json_domain_stats = []
#try:
for date in date_range:
nb_domain_up = r_serv_onion.scard('{}_up:{}'.format(type, date))
nb_domain_down = r_serv_onion.scard('{}_up:{}'.format(type, date))
date = date[0:4] + '-' + date[4:6] + '-' + date[6:8]
json_domain_stats.append({ 'date': date, 'value': int( nb_domain_up ), 'nb_domain_down': int( nb_domain_down )})
#except:
#return jsonify()
return jsonify(json_domain_stats)
# ========= REGISTRATION =========
app.register_blueprint(hiddenServices)

View File

@ -0,0 +1 @@
<li id='page-hiddenServices'><a href="{{ url_for('hiddenServices.hiddenServices_page') }}"><i class="fa fa-user-secret"></i> hidden Services </a></li>

View File

@ -0,0 +1,188 @@
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Hidden Service - AIL</title>
<!-- Core CSS -->
<link href="{{ url_for('static', filename='css/bootstrap.min.css') }}" rel="stylesheet">
<link href="{{ url_for('static', filename='font-awesome/css/font-awesome.css') }}" rel="stylesheet">
<link href="{{ url_for('static', filename='css/sb-admin-2.css') }}" rel="stylesheet">
<!-- JS -->
<script language="javascript" src="{{ url_for('static', filename='js/jquery.js')}}"></script>
<script language="javascript" src="{{ url_for('static', filename='js/d3.min.js') }}"></script>
<style>
div.tooltip {
position: absolute;
text-align: center;
padding: 2px;
font: 12px sans-serif;
background: #ebf4fb;
border: 2px solid #b7ddf2;
border-radius: 8px;
pointer-events: none;
color: #000000;
}
.line_graph {
fill: none;
stroke: steelblue;
stroke-width: 2px;
stroke-linejoin: round;
stroke-linecap: round;
stroke-width: 1.5;
}
</style>
</head>
<body>
{% include 'navbar.html' %}
<div id="page-wrapper">
<div class="row">
<div class="col-md-6">
<div class="panel panel-primary">
<div class="panel-heading">ONION</div>
<div class="panel-body">
<table class="table table-striped">
<thead>
<tr>
<th>Domain</th>
<th>First Seen</th>
<th>Last Check</th>
<th>Status</th>
</tr>
</thead>
<tbody>
{% for metadata_onion in last_onions %}
<tr>
<td><a target="_blank" href="{{ url_for('hiddenServices.onion_domain') }}?onion_domain={{ metadata_onion['domain'] }}">{{ metadata_onion['domain'] }}</a></td>
<td>{{'{}/{}/{}'.format(metadata_onion['first_seen'][0:4], metadata_onion['first_seen'][4:6], metadata_onion['first_seen'][6:8])}}</td>
<td>{{'{}/{}/{}'.format(metadata_onion['last_check'][0:4], metadata_onion['last_check'][4:6], metadata_onion['last_check'][6:8])}}</td>
<td><div style="color:{{metadata_onion['status_color']}}; display:inline-block">
<i class="fa {{metadata_onion['status_icon']}} fa-2x"></i>
{{metadata_onion['status_text']}}
</div>
</td>
</tr>
{% endfor %}
</tbody>
</table>
<div id="graph_line">
</div>
</div>
</div>
<div class="col-md-6">
</div>
</div>
</div>
<!-- /#page-wrapper -->
<script>
var all_graph = {};
$(document).ready(function(){
activePage = "page-hiddenServices"
$("#"+activePage).addClass("active");
all_graph.line_chart = create_line_chart('graph_line', '/hiddenServices/domain_crawled_7days_json?type=onion');
});
$(window).on("resize", function() {
all_graph.onResize();
});
</script>
<script>
all_graph.onResize = function () {
var aspect = 1000 / 500, all_graph = $("#graph_div");
var targetWidth = all_graph.parent().width();
all_graph.attr("width", targetWidth);
all_graph.attr("height", targetWidth / aspect);
}
window.all_graph = all_graph;
function create_line_chart(id, url){
var width = 650;
var height = Math.round(width / 6);
var margin = {top: 20, right: 55, bottom: 50, left: 40};
var x = d3.scaleTime().range([0, width]);
var y = d3.scaleLinear().rangeRound([height, 0]);
var xAxis = d3.axisBottom(x);
var yAxis = d3.axisLeft(y);
var parseTime = d3.timeParse("%Y-%m-%d");
var line = d3.line()
.x(function(d) {
return x(d.date);
}).y(function(d) {
return y(d.value);
});
var svg_line = d3.select('#'+id).append('svg')
.attr("id", "graph_div")
.attr("width", width + margin.left + margin.right)
.attr("height", height + margin.top + margin.bottom)
.append('g')
.attr('transform', "translate("+ margin.left +","+ margin.top +")");
var div = d3.select('body').append('div')
.attr('class', 'tooltip')
.style('opacity', 0);
//add div tooltip
d3.json(url)
.then(function(data){
data.forEach(function(d) {
d.date_label = d.date;
d.date = parseTime(d.date);
d.value = +d.value;
});
// fit the data
x.domain(d3.extent(data, function(d) { return d.date; }));
//x.domain(data.map(function (d) { return d.date; })); //E
y.domain([0, d3.max(data, function(d){ return d.value ; })]);
//line
svg_line.append("path")
.data([data])
.attr("class", "line_graph")
.attr("d", line);
// add X axis
svg_line.append("g")
.attr("transform", "translate(0," + height + ")")
.call(d3.axisBottom(x))
.selectAll("text")
.style("text-anchor", "end")
.attr("transform", "rotate(-45)" );
// Add the Y Axis
svg_line.append("g")
.call(d3.axisLeft(y));
//add a dot circle
svg_line.selectAll('dot')
.data(data).enter()
.append('circle')
.attr('r', 2)
.attr('cx', function(d) { return x(d.date); })
.attr('cy', function(d) { return y(d.value); })
.on('mouseover', function(d) {
div.transition().style('opacity', .9);
div.html('' + d.date_label+ '<br/>' + d.value).style('left', (d3.event.pageX) + 'px')
.style("left", (d3.event.pageX) + "px")
.style("top", (d3.event.pageY - 28) + "px");
})
.on('mouseout', function(d)
{
div.transition().style('opacity', 0);
});
});
}
</script>
</body>
</html>

View File

@ -0,0 +1,76 @@
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Show Domain - AIL</title>
<!-- Core CSS -->
<link href="{{ url_for('static', filename='css/bootstrap.min.css') }}" rel="stylesheet">
<link href="{{ url_for('static', filename='font-awesome/css/font-awesome.css') }}" rel="stylesheet">
<link href="{{ url_for('static', filename='css/sb-admin-2.css') }}" rel="stylesheet">
<link href="{{ url_for('static', filename='css/dygraph_gallery.css') }}" rel="stylesheet" type="text/css" />
<!-- JS -->
<script type="text/javascript" src="{{ url_for('static', filename='js/dygraph-combined.js') }}"></script>
<script language="javascript" src="{{ url_for('static', filename='js/jquery.js')}}"></script>
<script src="{{ url_for('static', filename='js/jquery.flot.js') }}"></script>
<script src="{{ url_for('static', filename='js/jquery.flot.pie.js') }}"></script>
<script src="{{ url_for('static', filename='js/jquery.flot.time.js') }}"></script>
</head>
<body>
{% include 'navbar.html' %}
<div id="page-wrapper">
<div class="row">
<div class="col-md-5">
<div class="row">
<div class="panel panel-default">
<div class="panel-heading">
<i id="flash-tld" class="glyphicon glyphicon-flash " flash-tld=""></i> Graph
</div>
<table class="table table-hover table-striped">
<tbody>
<tr>
<td>Domain</td>
<td>{{ domain }}</td>
</tr>
<tr>
<td>First Seen</td>
<td>{{ first_seen }}</td>
</tr>
<tr>
<td>Last Check</td>
<td>{{ last_check }}</td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
<div class="col-md-7">
<img src="{{ url_for('showsavedpastes.screenshot', filename='ds') }}" onError="this.onerror=null;this.src='{{ url_for('static', filename='image/AIL.png') }}';" style="width:100%;" />
</div>
</div>
</div>
<!-- /#page-wrapper -->
<script>
$(document).ready(function(){
activePage = "page-hiddenServices"
$("#"+activePage).addClass("active");
});
</script>
</body>
</html>