def _re_extract(self, swf_body):
"""
Get the URLs using a regex
"""
re_extract = ReExtract(swf_body, self._base_url, self._encoding)
re_extract.parse()
self._re_urls.update(re_extract.get_references())
def _parse(self, resp_body):
"""
Get the URLs using a regex
"""
doc_string = pdf_to_text(resp_body)
re_extract = ReExtract(doc_string, self._base_url, self._encoding)
self._re_urls = re_extract.get_references()
def _re_extract(self, swf_body):
"""
Get the URLs using a regex
"""
re_extract = ReExtract(swf_body, self._base_url, self._encoding)
re_extract.parse()
self._re_urls.update(re_extract.get_references())
def _parse(self, resp_body):
"""
Get the URLs using a regex
"""
doc_string = pdf_to_text(resp_body)
re_extract = ReExtract(doc_string, self._base_url, self._encoding)
self._re_urls = re_extract.get_references()
def _parse(self, http_response):
"""
Get the URLs using a regex
"""
doc_string = http_response.get_body()
re_extract = ReExtract(doc_string, self._base_url, self._encoding,
require_quotes=True)
self._re_urls = re_extract.get_references()
def parse(self):
"""
Get the URLs using a regex
"""
doc_string = pdf_to_text(self.get_http_response().get_body())
re_extract = ReExtract(doc_string, self._base_url, self._encoding)
re_extract.parse()
self._re_urls = re_extract.get_references()
def parse(self):
"""
Get the URLs using a regex
"""
doc_string = pdf_to_text(self.get_http_response().get_body())
re_extract = ReExtract(doc_string, self._base_url, self._encoding)
re_extract.parse()
self._re_urls = re_extract.get_references()
def parse(self):
"""
Get the URLs using a regex
"""
re_extract = ReExtract(self.get_http_response().get_body(),
self._base_url, self._encoding,
require_quotes=True)
re_extract.parse()
self._re_urls = re_extract.get_references()
def parse(self):
"""
Get the URLs using a regex
"""
re_extract = ReExtract(self.get_http_response().get_body(),
self._base_url, self._encoding,
require_quotes=True)
re_extract.parse()
self._re_urls = re_extract.get_references()
def _parse(self, http_response):
"""
Get the URLs using a regex
"""
doc_string = http_response.get_body()
re_extract = ReExtract(doc_string,
self._base_url,
self._encoding,
require_quotes=True)
self._re_urls = re_extract.get_references()
def test_relative_regex(self):
doc_string = '123 ../../foobar/uploads/foo.png 465'
base_url = URL('https://w3af.org/abc/def/')
re_extract = ReExtract(doc_string, base_url, 'utf-8')
re_extract.parse()
references = re_extract.get_references()
self.assertEqual(references,
[URL('https://w3af.org/foobar/uploads/foo.png')])
def _handle_script_tag_start(self, tag, tag_name, attrs):
"""
Handle the script tags
"""
SGMLParser._handle_script_tag_start(self, tag, tag_name, attrs)
if tag.text is not None:
re_extract = ReExtract(tag.text.strip(), self._base_url,
self._encoding)
re_extract.parse()
self._re_urls.update(re_extract.get_references())
def data(self, data):
"""
Overriding parent's. Called by the main parser when a text node
is found
"""
if self._inside_textarea:
self._textarea_data = data.strip()
elif self._inside_script:
re_extract = ReExtract(data.strip(), self._base_url, self._encoding)
self._re_urls.update(re_extract.get_references())
def data(self, data):
"""
Overriding parent's. Called by the main parser when a text node
is found
"""
if self._inside_textarea:
self._textarea_data = data.strip()
elif self._inside_script:
re_extract = ReExtract(data.strip(), self._base_url, self._encoding)
self._re_urls.update(re_extract.get_references())
def _handle_script_tag_start(self, tag, tag_name, attrs):
"""
Handle the script tags
"""
SGMLParser._handle_script_tag_start(self, tag, tag_name, attrs)
if tag.text is not None:
re_extract = ReExtract(tag.text.strip(),
self._base_url,
self._encoding)
re_extract.parse()
self._re_urls.update(re_extract.get_references())
def _get_references_regex(self, mutant, mutant_response):
"""
Apply regular expressions to extract links from the HTTP response body.
:param mutant: The request used to upload the file
:param mutant_response: The HTTP response to parse
:return: References (links) found in the HTTP response that end with the
uploaded filename.
"""
# Quick performance improvement
if mutant.uploaded_file_name not in mutant_response.get_body():
return []
# Apply the regular expressions and extract links
re_extract = ReExtract(mutant_response.get_body(),
mutant_response.get_uri(),
mutant_response.get_charset())
re_extract.parse()
return re_extract.get_references()