def analyze_url(url, time):
m = re.fullmatch("https?://(.+)", url)
if not m:
url = "http://" + url
if not validators.url(url):
print("The target url is malformed:", url)
return
if results_coll.find_one({"url": url}):
print("Already analyzed", url)
return
print("URL Target: " + colored(url, 'cyan') + " Visiting for " +
colored(str(time), 'cyan') + " sec")
os.makedirs(config['out'], exist_ok=True)
wasm_save_dir = pathlib.Path(config["out"]) / "final"
wasm_save_dir.mkdir(exist_ok=True)
print("[S1] Website Analysis...")
target = hash_string(url)
wasm_dir = os.path.join(config['out'], target)
cpu_stat_f = os.path.join(config['out'], target + ".txt")
os.makedirs(wasm_dir, exist_ok=True)
# ./chrome-build/chrome coinhive.com --no-sandbox --js-flags="--dump-wasm-module --dump-wasm-module-path=./data"
command = config['chrome'] + ' ' + url + \
' --no-sandbox --headless --js-flags="--dump-wasm-module --dump-wasm-module-path=' + wasm_dir + '"'
print(command)
run.crawl(command, cpu_stat_f, url, time)
wasm_files = []
print("[S2] Looking for a wasm module...")
for file in pathlib.Path(wasm_dir).iterdir():
if file.name.endswith('.wasm'):
wasm_files.append(file)
break
if not wasm_files:
print("[S2] No Wasm module found... Moving to S4")
print("[>] Hint: try to increase the timeout -tm [seconds]")
else:
print(
"\033[0;31m[*] Wasm module(s) found: {}, count: {} \033[0m".format(
[str(item) for item in wasm_files], len(wasm_files)))
for f in wasm_files:
shutil.copy(f, wasm_save_dir / f.name)
results_coll.insert_one({"url": url, "count": len(wasm_files)})
shutil.rmtree(wasm_dir)
os.unlink(cpu_stat_f)
if not os.path.exists(config['out']):
os.makedirs(config['out'])
print "[S1] Website Analysis..."
md5_target = md5.new(target).hexdigest()
outwasm = os.path.join(config['out'], md5_target)
cpu_stat_f = os.path.join(config['out'], md5_target + ".txt")
if not os.path.exists(outwasm):
os.makedirs(outwasm)
#./chrome-build/chrome coinhive.com --no-sandbox --js-flags="--dump-wasm-module --dump-wasm-module-path=./data"
command = config['chrome'] + ' ' + target + \
' --no-sandbox --remote-debugging-port=9222 --js-flags="--dump-wasm-module --dump-wasm-module-path=' + outwasm + '"'
run.crawl(command, cpu_stat_f , target, time)
###############################################################################
# Stage 2: Wasm analysis
###############################################################################
wasm_f = ""
stat_f = ""
print "[S2] Looking for a wasm module..."
for fname in os.listdir(outwasm):
if fname.endswith('.wasm'):
# do stuff on the file
wasm_f = fname
break
if not wasm_f:
colored(str(time), 'cyan') + " sec")
###############################################################################
# Stage 1: Website analysis
###############################################################################
if not os.path.exists(config['out']):
os.makedirs(config['out'])
print("[S1] Website Analysis...")
wasm_dir = os.path.join(config['out'], target)
cpu_stat_f = os.path.join(config['out'], target + ".txt")
os.makedirs(wasm_dir, exist_ok=True)
# ./chrome-build/chrome coinhive.com --no-sandbox --js-flags="--dump-wasm-module --dump-wasm-module-path=./data"
command = config['chrome'] + ' ' + url + \
' --no-sandbox --headless --js-flags="--dump-wasm-module --dump-wasm-module-path=' + wasm_dir + '"'
# print cpu_stat_f
print(command)
run.crawl(command, cpu_stat_f, url, time)
###############################################################################
# Stage 2: Wasm analysis
###############################################################################
wasm_files = []
print("[S2] Looking for a wasm module...")
for file in pathlib.Path(wasm_dir).iterdir():
if file.name.endswith('.wasm'):
wasm_files.append(file)
break
if not wasm_files:
print("[S2] No Wasm module found... Moving to S4")
print("[>] Hint: try to increase the timeout -tm [seconds]")