prehistoric-systems/Zeus-Scanner
1
0
Fork 0
mirror of https://github.com/Ekultek/Zeus-Scanner.git synced 2026-03-11 08:55:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

skips google play and google maps, also extracts correctly from webcache with out error (issue #55)

Browse source
This commit is contained in:
ekultek 2017-10-09 16:09:50 -05:00
parent a10d8d5825
commit e43ee8a0ca
2 changed files with 41 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
lib/settings.py
View file

@ -22,7 +22,7 @@ except NameError:
# clone link # clone link
CLONE = "https://github.com/ekultek/zeus-scanner.git" CLONE = "https://github.com/ekultek/zeus-scanner.git"
# current version <major.minor.commit.patch ID> # current version <major.minor.commit.patch ID>
VERSION = "1.0.32" VERSION = "1.0.33.1770"
# colors to output depending on the version # colors to output depending on the version
VERSION_TYPE_COLORS = {"dev": 33, "stable": 92, "other": 30} VERSION_TYPE_COLORS = {"dev": 33, "stable": 92, "other": 30}
# version string formatting # version string formatting

67
var/google_search/search.py
View file

@ -68,12 +68,15 @@ def bypass_ip_block(url, content_sep=("continue=", "Fid", "%")):
return __add_https(url[0:content_list_end[-1][-1] - 1]) return __add_https(url[0:content_list_end[-1][-1] - 1])
def extract_webcache_url(webcache_url, splitter=("%2Bext", ":")): def extract_webcache_url(webcache_url, splitter="+"):
webcache_regex = re.compile(r"(?<=q=).*?(?=[&\"])") webcache_url = unquote(webcache_url)
data = "".join(webcache_regex.findall(webcache_url)) webcache_regex = re.compile(r":\w+:")
to_extract = data.split(splitter[0])[0] data = webcache_regex.split(webcache_url)
found = "http:" + to_extract.split(splitter[1])[3] to_extract = data[1].split(splitter)
return unquote(found) extracted_to_test = to_extract[0]
if URL_REGEX.match(extracted_to_test):
return extracted_to_test
return None
def get_urls(query, url, verbose=False, warning=True, user_agent=None, proxy=None, **kwargs): def get_urls(query, url, verbose=False, warning=True, user_agent=None, proxy=None, **kwargs):
@ -270,31 +273,41 @@ def parse_search_results(
logger.info(set_color(user_agent_info)) logger.info(set_color(user_agent_info))
req.headers.update(headers) req.headers.update(headers)
found_urls = URL_REGEX.findall(req.text) found_urls = URL_REGEX.findall(req.text)
url_skip_schema = ("maps.google", "play.google", "youtube")
for urls in list(found_urls): for urls in list(found_urls):
for url in list(urls): for url in list(urls):
url = unquote(url) url = unquote(url)
if URL_QUERY_REGEX.match(url) and not any(l in url for l in exclude): if not any(u in url for u in url_skip_schema):
if isinstance(url, unicode): if URL_QUERY_REGEX.match(url) and not any(l in url for l in exclude):
url = str(url).encode("utf-8") if isinstance(url, unicode):
if "webcache" in url: url = str(url).encode("utf-8")
logger.info(set_color( if "webcache" in url:
"received webcache URL, extracting URL from webcache..." logger.info(set_color(
)) "received webcache URL, extracting URL from webcache..."
url = extract_webcache_url(url)
if verbose:
try:
logger.debug(set_color(
"found '{}'...".format(url.split(splitter)[0]), level=10
)) ))
except TypeError: webcache_url = url
logger.debug(set_color( url = extract_webcache_url(webcache_url)
"found '{}'...".format(str(url).split(splitter)[0]), level=10 if url is None:
)) logger.warning(set_color(
except AttributeError: "unable to extract url from given webcache URL '{}'...".format(
logger.debug(set_color( webcache_url
"found '{}...".format(str(url)), level=10 ), level=30
)) ))
retval.add(url.split("&amp;")[0]) if verbose:
try:
logger.debug(set_color(
"found '{}'...".format(url.split(splitter)[0]), level=10
))
except TypeError:
logger.debug(set_color(
"found '{}'...".format(str(url).split(splitter)[0]), level=10
))
except AttributeError:
logger.debug(set_color(
"found '{}...".format(str(url)), level=10
))
if url is not None:
retval.add(url.split("&amp;")[0])
logger.info(set_color( logger.info(set_color(
"found a total of {} URL's with a GET parameter...".format(len(retval)) "found a total of {} URL's with a GET parameter...".format(len(retval))
)) ))