def search_commit(self, query: str) -> list:
commit_temp_list = []
if self.orchestra['commit']:
print(f"{Color.information} Searching for data in Commits")
commit_search = self.conn.search_commit(query)
for unit_commit in commit_search:
commit_url = unit_commit.html_url
temp_x = "Repo:{} Commit:{}\n".format(colored("/".join(commit_url.split('/')[3:5]), color='cyan'), colored(commit_url.split('/')[6:][-1]), color='cyan')
print(Color.good + " " + temp_x.rstrip('\n'))
commit_temp_list.append(temp_x.lstrip(' '))
self.git_rate_limit()
commit_response = get(commit_url)
commit_soup = BeautifulSoup(commit_response.content, 'html.parser')
commit_data = commit_soup.find_all("span")
line_searced = False
for commit_line in commit_data:
for regex in search_regex:
if search(regex, commit_line):
temp_x = f"{colored(commit_line, color='red')}"
temp_x += "<--- File from commit regex \n".rjust(148-len(temp_x))
commit_temp_list.append(temp_x.lstrip(' '))
line_searched = True
if line_searched:
line_searched = False
continue
for commit_word in commit_line.split(' '):
temp_x = f"{colored(commit_word, color='red')} "
temp_x += "<--- From commit entropy! \n".rjust(148-len(temp_x))
if shannon_entropy(commit_word, base64char) >= float(4.6):
code_temp_list.append(temp_x.lstrip(' '))
if shannon_entropy(commit_word, hexchar) >= float(4.1):
code_temp_list.append(temp_x.lstrip(' '))
self.orchestra['commit'] = False
return commit_temp_list
def search_code(self, query: str) -> list:
code_temp_list = []
if self.orchestra['code']:
print(f"{Color.information} Searching for data in Codes")
code_search = self.conn.search_code(query)
for unit_code in code_search:
temp_x = "Name:{}, Repo:{}, URL: {}\n".format(colored(unit_code.name, color='cyan'), colored(unit_code.repository.full_name, color='cyan'), colored(unit_code.download_url, color='cyan'))
print("{} Searching for code in {} from repository {}".format(Color.good, colored(unit_code.name, color='cyan'), colored(unit_code.repository.full_name, color='cyan')))
code_temp_list.append(temp_x.lstrip(' '))
self.git_rate_limit()
code = b64decode(unit_code.content).decode('UTF-8').split('\n')
line_searched = False
for code_line in code:
for regex in search_regex:
if search(regex, code_line):
temp_x = f"{colored(code_line, color='red')} "
temp_x += " <--- File from code regex \n".rjust(150-len(temp_x))
code_temp_list.append(temp_x.lstrip(' '))
line_searched = True
if line_searched:
line_searched = False
continue
for code_word in code_line.split(' '):
temp_x = f"{colored(code_word, color='red')} "
temp_x += "<--- From code entropy! \n".rjust(150-len(temp_x))
if shannon_entropy(code_word, base64char) >= float(4.6):
code_temp_list.append(temp_x.lstrip(' '))
if shannon_entropy(code_word, hexchar) >= float(4):
code_temp_list.append(temp_x.lstrip(' '))
self.orchestra['code'] = False
return code_temp_list
def search_repo(self, query: str) -> list:
repo_temp_list = []
if self.orchestra['repo']:
print(f"{Color.information} Searching for data in Repositories!")
repo_search = self.conn.search_repositories(query)
self.git_rate_limit()
for unit_repo in repo_search:
repo = self.conn.get_repo(unit_repo.full_name)
temp_x = "Fetching data from this repo: {}\n".format(colored(repo.full_name, color='cyan'))
repo_temp_list.append(temp_x.lstrip(' '))
print(Color.good + " " + temp_x.rstrip('\n'))
repo_list = repo.get_contents("")
while repo_list:
repo_file = repo_list.pop(0)
if repo_file.type == "dir":
repo_list.extend(repo.get_contents(repo_file.path))
else:
try:
repo_file_lines = b64decode(repo_file.content).decode('UTF-8').split('\n')
except Exception as E:
print(E,E.__class__)
continue
temp_x = "File: {}\n".format(colored(repo_file, color='cyan'))
repo_temp_list.append(temp_x.lstrip(' '))
line_searched = False
for repoline in repo_file_lines:
for regex in search_regex:
if search(regex, repoline):
temp_x = f"{colored(repoline, color='red')} "
temp_x += "<--- File from repo regex \n".rjust(150-len(temp_x))
repo_temp_list.append(temp_x.lstrip(' '))
line_searched = True
if line_searched:
line_searched = False
continue
for repoword in repoline.split(' '):
temp_x = f"{colored(repoword, color='red')} "
temp_x += "<--- From Repo entropy! \n".rjust(150-len(temp_x))
if shannon_entropy(repoword, base64char) >= float(4.5):
repo_temp_list.append(temp_x.lstrip(' '))
if shannon_entropy(repoword, hexchar) >= float(4.1):
repo_temp_list.append(temp_x.lstrip(' '))
self.orchestra['repo'] = False
return repo_temp_list
def shannon_extract(self, line: str) -> list:
output_list = []
if self.argv.enable_entropy:
for word in line.split(' '):
if len(word) > 5:
if float(shannon_entropy(
word, base64char)) > float(3.43) or float(
shannon_entropy(word, hexchar)) > float(3.5):
word = self.reduce_string(word.rstrip(';'),
args=['"', "'"])
print(
f"{Color.good} Suspicious data: {colored(word, color='red', attrs=['bold'])}"
)
output_list = [
manage_output(f"{word} <--- Entropy \n"), "Entropy"
]
self.jstext_continuer = 1
return output_list
return []