def run_local(self, url):
log.last_url = None
log.last_url_fetched = None
log.ThugLogging.set_url(url)
log.ThugOpts.local = True
log.HTTPSession = HTTPSession()
content = open(url, 'r').read()
extension = os.path.splitext(url)
encoding = cchardet.detect(content)
if len(extension) > 1 and extension[1].lower() in (
'.js',
'.jse',
):
if not content.lstrip().startswith('<script'):
html = tostring(
E.HTML(
E.HEAD(),
E.BODY(E.SCRIPT(content.decode(
encoding['encoding'])))))
else:
soup = BeautifulSoup(content, "html.parser")
try:
soup.html.unwrap()
except AttributeError:
pass
try:
soup.head.unwrap()
except AttributeError:
pass
try:
soup.body.unwrap()
except AttributeError:
pass
html = tostring(
E.HTML(E.HEAD(), E.BODY(E.SCRIPT(soup.script.get_text()))))
else:
html = content
if log.ThugOpts.features_logging:
log.ThugLogging.Features.add_characters_count(len(html))
log.ThugLogging.Features.add_whitespaces_count(
len([a for a in html if a.isspace()]))
doc = w3c.parseString(html)
window = Window('about:blank', doc, personality=log.ThugOpts.useragent)
window.open()
self.__run(window)
def run_local(self, url):
log.last_url = None
log.last_url_fetched = None
log.ThugLogging.set_url(url)
log.ThugOpts.local = True
log.HTTPSession = HTTPSession()
content = open(url, 'r', encoding="utf-8").read()
extension = os.path.splitext(url)
if len(extension) > 1 and extension[1].lower() in (
'.js',
'.jse',
):
if not content.lstrip().startswith('<script'):
html = tostring(E.HTML(E.HEAD(), E.BODY(E.SCRIPT(content))))
else:
soup = bs4.BeautifulSoup(content, "html.parser")
try:
soup.html.unwrap()
except AttributeError:
pass
try:
soup.head.unwrap()
except AttributeError:
pass
try:
soup.body.unwrap()
except AttributeError:
pass
code = soup.script.get_text(types=(NavigableString, CData,
Script))
html = tostring(E.HTML(E.HEAD(), E.BODY(E.SCRIPT(code))))
else:
html = content
if log.ThugOpts.features_logging:
log.ThugLogging.Features.add_characters_count(len(html))
whitespaces_count = len([
a for a in html
if isinstance(a, six.string_types) and a.isspace()
])
log.ThugLogging.Features.add_whitespaces_count(whitespaces_count)
doc = w3c.parseString(html)
window = Window('about:blank', doc, personality=log.ThugOpts.useragent)
window.open()
self.__run(window)
def run_remote(self, url):
log.last_url = None
log.last_url_fetched = None
log.ThugOpts.local = False
try:
scheme = urlparse.urlparse(url).scheme
except ValueError as e:
log.warning("[WARNING] Analysis not performed (%s)", e.message)
return
if not scheme or not scheme.startswith('http'):
url = 'http://%s' % (url, )
log.ThugLogging.set_url(url)
log.HTTPSession = HTTPSession()
doc = w3c.parseString('')
window = Window(log.ThugOpts.referer,
doc,
personality=log.ThugOpts.useragent)
window = window.open(url)
if window:
self.__run(window)
def run_local(self, url):
log.last_url = None
log.last_url_fetched = None
log.ThugLogging.set_url(url)
log.ThugOpts.local = True
log.HTTPSession = HTTPSession()
content = open(url, 'r').read()
extension = os.path.splitext(url)
encoding = cchardet.detect(content)
if len(extension) > 1 and extension[1].lower() in ('.js', '.jse', ):
if not content.lstrip().startswith('<script'):
html = tostring(E.HTML(E.HEAD(), E.BODY(E.SCRIPT(content.decode(encoding['encoding'])))))
else:
soup = BeautifulSoup(content, "html.parser")
try:
soup.html.unwrap()
except AttributeError:
pass
try:
soup.head.unwrap()
except AttributeError:
pass
try:
soup.body.unwrap()
except AttributeError:
pass
html = tostring(E.HTML(E.HEAD(), E.BODY(E.SCRIPT(soup.script.get_text()))))
else:
html = content
if log.ThugOpts.features_logging:
log.ThugLogging.Features.add_characters_count(len(html))
log.ThugLogging.Features.add_whitespaces_count(len([a for a in html if a.isspace()]))
doc = w3c.parseString(html)
window = Window('about:blank', doc, personality = log.ThugOpts.useragent)
window.open()
self.__run(window)
def run_local(self, url):
log.ThugLogging.set_url(url)
log.ThugOpts.local = True
log.HTTPSession = HTTPSession()
content = open(url, 'r').read()
extension = os.path.splitext(url)
if len(extension) > 1 and extension[1].lower() in ('.js'):
html = tostring(E.HTML(E.BODY(E.SCRIPT(content))))
else:
html = content
doc = w3c.parseString(html)
window = Window('about:blank', doc, personality=log.ThugOpts.useragent)
window.open()
self.run(window)
def run_local(self, url):
log.ThugLogging.set_url(url)
log.ThugOpts.local = True
log.HTTPSession = HTTPSession()
content = open(url, 'r').read()
extension = os.path.splitext(url)
if len(extension) > 1 and extension[1].lower() in ('.js', '.jse', ):
html = tostring(E.HTML(E.BODY(E.SCRIPT(content))))
else:
html = content
doc = w3c.parseString(html)
window = Window('about:blank', doc, personality = log.ThugOpts.useragent)
window.open()
self.__run(window)
def run_local(self, url):
log.ThugLogging.set_url(url)
log.ThugOpts.local = True
log.HTTPSession = HTTPSession()
content = open(url, 'r').read()
extension = os.path.splitext(url)
if len(extension) > 1 and extension[1].lower() in (
'.js',
'.jse',
):
if not content.lstrip().startswith('<script'):
html = tostring(E.HTML(E.HEAD(), E.BODY(E.SCRIPT(content))))
else:
soup = BeautifulSoup(content, "html.parser")
try:
soup.html.unwrap()
except AttributeError:
pass
try:
soup.head.unwrap()
except AttributeError:
pass
try:
soup.body.unwrap()
except AttributeError:
pass
html = tostring(
E.HTML(E.HEAD(), E.BODY(E.SCRIPT(soup.script.get_text()))))
else:
html = content
doc = w3c.parseString(html)
window = Window('about:blank', doc, personality=log.ThugOpts.useragent)
window.open()
self.__run(window)
def run_local(self, url):
log.ThugLogging.set_url(url)
log.ThugOpts.local = True
log.HTTPSession = HTTPSession()
content = open(url, 'r').read()
extension = os.path.splitext(url)
if len(extension) > 1 and extension[1].lower() in ('.js', '.jse', ):
if not content.lstrip().startswith('<script'):
html = tostring(E.HTML(E.BODY(E.SCRIPT(content))))
else:
soup = BeautifulSoup(content, "html.parser")
try:
soup.html.unwrap()
except AttributeError:
pass
try:
soup.head.unwrap()
except AttributeError:
pass
try:
soup.body.unwrap()
except AttributeError:
pass
html = tostring(E.HTML(E.BODY(E.SCRIPT(soup.script.get_text()))))
else:
html = content
doc = w3c.parseString(html)
window = Window('about:blank', doc, personality = log.ThugOpts.useragent)
window.open()
self.__run(window)
def run_remote(self, url):
scheme = urlparse.urlparse(url).scheme
if not scheme or not scheme.startswith('http'):
url = 'http://%s' % (url, )
log.ThugLogging.set_url(url)
log.HTTPSession = HTTPSession()
doc = w3c.parseString('')
window = Window(log.ThugOpts.referer, doc, personality = log.ThugOpts.useragent)
window = window.open(url)
if window:
self.__run(window)
def run_remote(self, url):
scheme = urlparse.urlparse(url).scheme
if not scheme or not scheme.startswith('http'):
url = 'http://%s' % (url, )
log.ThugLogging.set_url(url)
log.HTTPSession = HTTPSession()
doc = w3c.parseString('')
window = Window(log.ThugOpts.referer, doc, personality = log.ThugOpts.useragent)
window = window.open(url)
if window:
self.__run(window)
def run_remote(self, url):
log.last_url = None
log.last_url_fetched = None
log.ThugOpts.local = False
try:
scheme = urlparse.urlparse(url).scheme
except ValueError as e:
log.warning("[WARNING] Analysis not performed (%s)", e.message)
return
if not scheme or not scheme.startswith('http'):
url = 'http://%s' % (url, )
log.ThugLogging.set_url(url)
log.HTTPSession = HTTPSession()
doc = w3c.parseString('')
window = Window(log.ThugOpts.referer, doc, personality = log.ThugOpts.useragent)
window = window.open(url)
if window:
self.__run(window)
