def main(option):
if option == '--aes':
banner.head()
password = input('[*] Pick a password: '******'[*] Enter the text to be encrypted: ')
encrypted_text = func.aes(f'{text_to_aes}', password)
print('\n[*]', encrypted_text)
elif option == '--caesar':
banner.head()
text_to_binary = input('[*] Enter the text to be encrypted: ')
while True:
try:
s = int(input("[*] Enter the shift: ")
) #how many shifts to encode in caesar
break
except ValueError:
print('[!] Please enter a numerical value.')
continue
encrypt_text = func.caesar(text_to_binary, s)
print('\n[*] Encrypted value:', "{}".format(encrypt_text))
elif option == '--md5':
func.md5()
elif option == '--rot13':
func.rot13()
elif option == '--base64':
func.base64()
elif option == '--sha256':
func.sha256()
elif option == '--hex':
func.hex()
elif option == '--help' or option == '-h':
banner.usage()
def urls_add(self):
add_url_list = list(set(self.__request_json['urls_add'])) # 去重
# 已存在queue中的
exist_queue_url_list = []
res = Mongo.get()['queue_' + self.project_name].find({'url_md5': {'$in': [md5(l) for l in add_url_list]}},
{'url': 1})
for doc in res:
exist_queue_url_list.append(doc['url'])
# 已存在parsed中的
exist_parsed_url_list = []
res = Mongo.get()['parsed_' + self.project_name].find({'url_md5': {'$in': [md5(l) for l in add_url_list]}},
{'url': 1})
for doc in res: # todo 需要判断存在的时间, 允许重复抓取
exist_parsed_url_list.append(doc['url'])
# 加入队列
add_urls_data = []
for url in add_url_list:
if url not in exist_queue_url_list and url not in exist_parsed_url_list: # 不存在queue不存在parsed中才加入队列
add_urls_data.append(
{'domain': get_domain(url),
'url': url,
'url_md5': md5(url),
'flag_time': 0,
'add_time': int(time.time()),
'slave_ip': self.__request_address[0]})
add_urls_data and Mongo.get()['queue_' + self.project_name].insert(add_urls_data)
def add_fails_record(self, ip, fails=()):
"""
根据失败的url抓取记录且一定时间达到一定数量则将url加入该slave (IP)的禁止名单中
"""
self.__init_key(ip)
start_time = int(time.time()) - 30 * 60 # 半小时前
start_time_clean = int(time.time()) - 120 * 60 # 两个小时前
# 判断时间清理掉一段时间之前的禁止名单
deny_domains = []
deny_domains_temp = copy.deepcopy(self.slave_record[ip]['deny_domains']) # 深复制
for item in deny_domains_temp:
deny_domains.append(item['domain'])
if item['add_time'] < start_time_clean: # 如果是指定时间之前添加的则清除掉该slave (IP)禁止名单
self.slave_record[ip]['deny_domains'].remove(item)
for item in fails:
domain = item[0]
http_code = int(item[1])
add_time = item[2]
if http_code == 403 and domain not in deny_domains:
self.deny_urls_temp.setdefault(ip, {})
res = self.deny_urls_temp[ip].setdefault(domain, {'count': 0, 'time': []})
self.deny_urls_temp[ip][domain]['count'] += 1
self.deny_urls_temp[ip][domain]['time'].append(add_time)
# 403 一定时间达到一定次数就加禁止入名单
if res['count'] == 10:
# 半小时内达到一定次数
time_count = 0
for t in self.deny_urls_temp[ip][domain]['time']:
if t > start_time:
time_count += 1
if time_count < 10: # 未达到次数下限
continue
# 加入禁止名单和清空临时数据
self.slave_record[ip]['deny_domains'].append({'domain': domain, 'add_time': int(time.time())})
del self.deny_urls_temp[ip]
continue
# 其他非403的处理
if http_code != 403:
domain_md5 = md5(domain) # mongoDB不支持带.的key
self.slave_record[ip]['error_domains'].setdefault(domain_md5, {})
self.slave_record[ip]['error_domains'][domain_md5].setdefault('domain', domain)
self.slave_record[ip]['error_domains'][domain_md5].setdefault('add_time', int(time.time()))
self.slave_record[ip]['error_domains'][domain_md5]['update_time'] = int(time.time())
self.slave_record[ip]['error_domains'][domain_md5].setdefault('http_code', {})
self.slave_record[ip]['error_domains'][domain_md5]['http_code'].setdefault(str(http_code), 0)
self.slave_record[ip]['error_domains'][domain_md5]['http_code'][str(http_code)] += 1
continue
def urls_parsed(self):
urls_data = []
url_list = []
for url in self.__request_json['urls_parsed']:
self.__slave_record.add_parsed_record(self.__request_address[0])
url_list.append(url)
urls_data.append(
{'url': url, 'url_md5': md5(url), 'add_time': int(time.time()), 'slave_ip': self.__request_address[0]})
Mongo.get()['queue_' + self.project_name].remove({'url_md5': {'$in': [md5(l) for l in url_list]}},
multi=True) # 删除抓取完毕的队列
try:
urls_data and Mongo.get()['parsed_' + self.project_name].insert(urls_data)
except:
try:
for single_url in urls_data:
single_url and Mongo.get()['parsed_' + self.project_name].insert_one(single_url)
except Exception, error:
print traceback.format_exc()
print error
print u'下面链接重复抓取的并重复保存到parsed_*中的记录'
print single_url, '\r\n\r\n'
def save_project():
return jsonify({'success': False, 'msg': '禁止修改!'})
form_data = json.loads(request.data) # todo 需要验证表单数据
name_r = re.compile(r'^[0-9a-zA-Z_-]+$')
if not name_r.search(form_data['name']):
return jsonify({'success': False, 'msg': '计划名称必须满足正则规则: ^[0-9a-zA-Z_-]+$ '})
exists_project = list(Mongo.get()['projects'].find({'name': form_data['name']}, {'_id': 1, 'add_time': 1}).limit(1))
if 'edit' not in form_data and exists_project:
return jsonify({'success': False, 'msg': '计划名称已经存在!'})
# 新增计划或更新计划
data = {
'name': form_data['name'],
'init_url': form_data['init_url'],
'desc': form_data['desc'] if 'desc' in form_data else '',
'code': form_data['code'],
'static': '暂停中',
'update_time': int(time.time()),
'add_time': exists_project[0]['add_time'] if exists_project else int(time.time()),
}
Mongo.get()['projects'].update({'name': form_data['name']}, data, True)
# 当是新计划时的初始化
if 'edit' not in form_data:
Mongo.get()['queue_' + form_data['name']].insert(
{
'url': form_data['init_url'],
'url_md5': md5(form_data['init_url']),
'flag_time': 0,
'add_time': int(time.time()),
'slave_ip': '0.0.0.0'
})
# 在没创建集合前设置索引mongodb会自动创建该集合并赋索引
Mongo.get()['parsed_' + form_data['name']].ensure_index('url_md5', unique=True)
Mongo.get()['queue_' + form_data['name']].ensure_index('url_md5', unique=True)
# 有新计划加入, 重启全部slave
restart_slave_list = GlobalHelper.get('restart_slave_list') or []
for slave_record in Mongo.get()['slave_record'].find():
restart_slave_list.append(slave_record['ip'])
GlobalHelper.set('restart_slave_list', list(set(restart_slave_list)))
return jsonify({'success': True, 'msg': '保存成功!'})
def save_project():
form_data = json.loads(request.data) # todo 需要验证表单数据
name_r = re.compile(r"^[0-9a-zA-Z_-]+$")
if not name_r.search(form_data["name"]):
return jsonify({"success": False, "msg": "计划名称必须满足正则规则: ^[0-9a-zA-Z_-]+$ "})
exists_project = list(Mongo.get()["projects"].find({"name": form_data["name"]}, {"_id": 1, "add_time": 1}).limit(1))
if "edit" not in form_data and exists_project:
return jsonify({"success": False, "msg": "计划名称已经存在!"})
# 新增计划或更新计划
data = {
"name": form_data["name"],
"init_url": form_data["init_url"],
"desc": form_data["desc"] if "desc" in form_data else "",
"code": form_data["code"],
"static": "暂停中",
"update_time": int(time.time()),
"add_time": exists_project[0]["add_time"] if exists_project else int(time.time()),
}
Mongo.get()["projects"].update({"name": form_data["name"]}, data, True)
# 当是新计划时的初始化
if "edit" not in form_data:
Mongo.get()["queue_" + form_data["name"]].insert(
{
"url": form_data["init_url"],
"url_md5": md5(form_data["init_url"]),
"flag_time": 0,
"add_time": int(time.time()),
"slave_ip": "0.0.0.0",
}
)
# 在没创建集合前设置索引mongodb会自动创建该集合并赋索引
Mongo.get()["parsed_" + form_data["name"]].ensure_index("url_md5", unique=True)
Mongo.get()["queue_" + form_data["name"]].ensure_index("url_md5", unique=True)
# 有新计划加入, 重启全部slave
restart_slave_list = GlobalHelper.get("restart_slave_list") or []
for slave_record in Mongo.get()["slave_record"].find():
restart_slave_list.append(slave_record["ip"])
GlobalHelper.set("restart_slave_list", list(set(restart_slave_list)))
return jsonify({"success": True, "msg": "保存成功!"})
def get_mol_data(self, data={}):
'''
get_mol_data([data]) -- Returns a dict.
calculats the mol data
args:
data: dict, in which the data stores.
'''
desc = self.mol.calcdesc()
ob_can_smi = self.gen_openbabel_can_smiles()
data.update({
'TPSA': desc['TPSA'],
'LogP': desc['logP'],
'MR': desc['MR'],
'FORMULA': self.mol.formula,
'MOLWEIGHT': self.mol.molwt,
'EXACTMASS': self.mol.exactmass,
'CHARGE': self.mol.charge,
'OPENBABEL_CAN_SMILES': ob_can_smi,
'MD5_OPENBABEL_CAN_SMILES': md5(ob_can_smi)
})
return data
def get_mol_data(self, data = {}):
'''
get_mol_data([data]) -- Returns a dict.
calculats the mol data
args:
data: dict, in which the data stores.
'''
desc = self.mol.calcdesc()
ob_can_smi = self.gen_openbabel_can_smiles()
data.update( {
'TPSA': desc['TPSA'],
'LogP': desc['logP'],
'MR': desc['MR'],
'FORMULA': self.mol.formula,
'MOLWEIGHT': self.mol.molwt,
'EXACTMASS': self.mol.exactmass,
'CHARGE': self.mol.charge,
'OPENBABEL_CAN_SMILES': ob_can_smi,
'MD5_OPENBABEL_CAN_SMILES': md5(ob_can_smi)
} )
return data
def scanfile(api_key, url):
#Prompt user for file path
file_path = input(
"Enter full file path (Use use forward slashes for Windows): ")
#Parse Input and perform error checking
while True:
try:
md5sum = md5(file_path)
except:
print("There was an error, please check your input")
file_path = input(
"Enter full file path (Use use forward slashes for Windows): ")
else:
break
filename = file_name(file_path)
#Input user information into JSON
data = {
"request": [{
"md5": md5sum,
"features": ["te", "av"],
"te": {
"reports": ["xml", "pdf"]
}
}]
}
#Assemble the header
headers = {
"User-Agent": "python-api-wrapper",
"Accept": "*/*",
"Content-Type": "application/json",
"Content-Length": str(len(data)),
"Authorization": api_key
}
#Send the request and parse the reply
try:
#Define Global variable
global status_code
print("\n")
print("Scanning Now...")
response = requests.post(url + "query",
json=data,
headers=headers,
verify=False)
response_json = json.loads(response.content)
status_code = response_json['response'][0]['status']['code']
print("\n")
print("Message: " + response_json['response'][0]['status']['message'])
print("\n")
print("Threat Emulation Results:")
print("Verdict: " + response_json['response'][0]['te']['images'][0]
['report']['verdict'])
print("Status: " +
response_json['response'][0]['te']['images'][0]['status'])
print("\n")
print("Anti-Virus Results:")
print("Message: " +
response_json['response'][0]['av']['status']['message'])
av_label = response_json['response'][0]['av']['status']['label']
print("Label: " + av_label)
if av_label == "FOUND":
print("Signature Name: " + response_json['response'][0]['av']
['malware_info']['signature_name'])
print("Severity: " + str(response_json['response'][0]['av']
['malware_info']['severity']))
print("Confidence: " + str(response_json['response'][0]['av']
['malware_info']['confidence']))
print("\n")
except:
print("Query Failed. Please try again.")
#Checking to see if user wants to upload file.
if status_code == 1004:
while True:
print("Would you like to upload your file for emulation?")
print("""
1. Upload file for emulation
2. Do not upload file
""")
selection = input("Select a task number: ")
if selection == "1":
print("\nUploading File...")
upload(api_key, url, file_path, md5sum, filename)
return
elif selection == "2":
print("\n")
return_to_menu()
return
selection = None
else:
print("\n Not Valid Choice Try again")
print("\n")
return_to_menu()
def add_fails_record(self, ip, fails=()):
"""
根据失败的url抓取记录且一定时间达到一定数量则将url加入该slave (IP)的禁止名单中
"""
self.__init_key(ip)
start_time = int(time.time()) - 30 * 60 # 半小时前
start_time_clean = int(time.time()) - 120 * 60 # 两个小时前
# 判断时间清理掉一段时间之前的禁止名单
deny_domains = []
deny_domains_temp = copy.deepcopy(
self.slave_record[ip]['deny_domains']) # 深复制
for item in deny_domains_temp:
deny_domains.append(item['domain'])
if item['add_time'] < start_time_clean: # 如果是指定时间之前添加的则清除掉该slave (IP)禁止名单
self.slave_record[ip]['deny_domains'].remove(item)
for item in fails:
domain = item[0]
http_code = int(item[1])
add_time = item[2]
if http_code == 403 and domain not in deny_domains:
self.deny_urls_temp.setdefault(ip, {})
res = self.deny_urls_temp[ip].setdefault(
domain, {
'count': 0,
'time': []
})
self.deny_urls_temp[ip][domain]['count'] += 1
self.deny_urls_temp[ip][domain]['time'].append(add_time)
# 403 一定时间达到一定次数就加禁止入名单
if res['count'] == 10:
# 半小时内达到一定次数
time_count = 0
for t in self.deny_urls_temp[ip][domain]['time']:
if t > start_time:
time_count += 1
if time_count < 10: # 未达到次数下限
continue
# 加入禁止名单和清空临时数据
self.slave_record[ip]['deny_domains'].append({
'domain':
domain,
'add_time':
int(time.time())
})
del self.deny_urls_temp[ip]
continue
# 其他非403的处理
if http_code != 403:
domain_md5 = md5(domain) # mongoDB不支持带.的key
self.slave_record[ip]['error_domains'].setdefault(
domain_md5, {})
self.slave_record[ip]['error_domains'][domain_md5].setdefault(
'domain', domain)
self.slave_record[ip]['error_domains'][domain_md5].setdefault(
'add_time', int(time.time()))
self.slave_record[ip]['error_domains'][domain_md5][
'update_time'] = int(time.time())
self.slave_record[ip]['error_domains'][domain_md5].setdefault(
'http_code', {})
self.slave_record[ip]['error_domains'][domain_md5][
'http_code'].setdefault(str(http_code), 0)
self.slave_record[ip]['error_domains'][domain_md5][
'http_code'][str(http_code)] += 1
continue
def scan_directory(api_key, url, file_path, report_path, rname):
#Open file and write to report
f = open(report_path + rname, "a")
#Parse Input and perform error checking
while True:
try:
md5sum = md5(file_path)
except:
f.write(file_path + " does not exist or has a problem with it.")
else:
break
filename = file_name(file_path)
#Input user information into JSON
data = {
"request": [{
"md5": md5sum,
"features": ["te", "av"],
"te": {
"reports": ["xml", "pdf"]
}
}]
}
#Assemble the header
headers = {
"User-Agent": "python-api-wrapper",
"Accept": "*/*",
"Content-Type": "application/json",
"Content-Length": str(len(data)),
"Authorization": api_key
}
#Send the request and parse the reply
try:
#Define Global variable
global status_code
print("\n")
print("Scanning " + file_path)
response = requests.post(url + "query",
json=data,
headers=headers,
verify=False)
response_json = json.loads(response.content)
status_code = response_json['response'][0]['status']['code']
av_label = response_json['response'][0]['av']['status']['label']
f.write("Results for " + file_path + "\n")
f.write('Message: ' +
response_json['response'][0]['status']['message'] + '\n')
f.write('Threat Emulation Results: \n\n')
f.write('Verdict: ' + response_json['response'][0]['te']['images'][0]
['report']['verdict'] + '\n')
f.write('Status: ' +
response_json['response'][0]['te']['images'][0]['status'] +
'\n')
f.write('Anti-Virus Results: \n\n')
f.write('Message: ' +
response_json['response'][0]['av']['status']['message'] + '\n')
f.write('Label: ' + av_label + '\n')
if av_label == "FOUND":
f.write('Signature Name: ' + response_json['response'][0]['av']
['malware_info']['signature_name'] + '\n')
f.write('Severity: ' + str(response_json['response'][0]['av']
['malware_info']['severity']) + '\n')
f.write('Confidence: ' + str(response_json['response'][0]['av']
['malware_info']['confidence']) +
'\n')
f.write("Info to check results: " + file_path + " " + md5sum +
'\n\n\n')
except:
f.write(file_path +
' Encountered and error. Results not available" \n')
f.write('\n')
f.write('\n')
#Checking to see if user wants to upload file.
if status_code == 1004:
#Retrieve Extension
file_ext = file_extension(filename)
#Input variables into JSON
data = {
"request": {
"md5": md5sum,
"file_name": filename,
"file_type": file_ext,
"features": ["te"],
"te": {
"reports": ["pdf", "xml"],
"images": [{
"id": "7e6fe36e-889e-4c25-8704-56378f0830df",
"revision": 1
}, {
"id": "e50e99f3-5963-4573-af9e-e3f4750b55e2",
"revision": 1
}]
}
}
}
files = {
'json': (None, json.dumps(data), 'application/json'),
'file': (filename, open(file_path,
'rb'), 'application/octet-stream')
}
#Assemble the header
headers = {"Authorization": api_key}
#send request
try:
response = requests.post(url + "upload",
headers=headers,
files=files)
response_json = json.loads(response.content)
f.write('Upload_Status: ' +
response_json['response']['status']['message'] + '\n')
except:
f.write('There was a problem when uploading the file')
f.close()
def gen_search_sql_tuple(self, smiles, search_type="1", out_put_type=1):
'''
gen_search_sql_tuple(smiles[, search_type[, out_put_type]]) -- Returns a tuple
args:
smiles: str, smiles that represents a molecule.
search_type: str. values:
'1': full march,
'2': target structure contains substructure,
'3': target structure dosen't contains substructure
'4': target structure contains superstructure,
'5': target structure dosen't contains superstructure
out_put_type: int. values:
1 or not 2: without the mol_stat part.
2: contains the mol_stat part
generates the search sql string according to the smiles string.
returns a tuple contains two elements:
0: stat, some statistic of the mol such as number of C, number of rings and etc.
1: the sql part, sql not fully generated, only a part like this " FROM ... WHERE ... "
'''
fp_sql = ""
stat = {}
head_flag = '('
end_flag = ')'
stat_part = ''
md5_ob_can_smi_key = self.env['MD5_OPENBABEL_CAN_SMI_KEY']
fp_bits_key = self.env['FP_BITS_KEY']
sign_mol_stat = ' >= '
try:
num_H_key = self.env['NUM_H_KEY']
except:
num_H_key = 'NUM_H'
bool_op = " AND "
mol_fp = {}
mol = mymol('smi', smiles)
mol.get_fps(mol_fp)
if search_type == "1":
if md5_ob_can_smi_key in self.recorded_fields_dict.keys():
return ({}, self.recorded_fields_dict[md5_ob_can_smi_key] +
" = '" +
md5(mymol('smi', smiles).gen_openbabel_can_smiles()) +
"'")
else:
return ({}, '')
elif search_type in ("2", "4"):
mol_stat = {}
tmp_stat = {}
mol.get_mol_stat(mol_stat)
if mol_stat.has_key(num_H_key):
mol_stat.pop(num_H_key)
tmp_stat[str(fp_bits_key)] = mol_fp[fp_bits_key]
tmp_stat.update(mol_stat)
if search_type == '2':
sign_mol_stat = ' >= '
stat['sub'] = tmp_stat
elif search_type == '4':
sign_mol_stat = ' <= '
stat['sup'] = tmp_stat
bool_op = ' AND '
elif search_type in ("3", "5"):
bool_op = ' AND '
head_flag = ' NOT ('
fps_keys = mol_fp.items()
fps_keys.sort()
for i, j in fps_keys:
if self.recorded_fields_dict.has_key(
i) and i != fp_bits_key and j != 0:
if search_type in ('2', '3'):
fp_sql += self.recorded_fields_dict[i] + " & " + str(
j) + ' = ' + str(j) + bool_op
elif search_type in ('4', '5'):
field = self.recorded_fields_dict[i]
fp_sql += field + " & " + str(j) + ' = ' + field + bool_op
if out_put_type == 2 and search_type in ('2', '4'):
val_k = []
for k, v in tmp_stat.items():
for j in self.def_dict.values():
if j.has_key(k):
val_k = j[k][0]
break
if val_k:
stat_part += str(val_k) + sign_mol_stat + str(v) + ' AND '
if stat_part:
head_flag = '(' + stat_part.rstrip('AND ') + ') AND ('
if fp_sql.rstrip(bool_op):
return (stat, head_flag + fp_sql.rstrip(bool_op) + end_flag)
else:
return ({}, '1')
def save_project():
form_data = json.loads(request.data) # todo 需要验证表单数据
name_r = re.compile(r'^[0-9a-zA-Z_-]+$')
if not name_r.search(form_data['name']):
return jsonify({
'success': False,
'msg': '计划名称必须满足正则规则: ^[0-9a-zA-Z_-]+$ '
})
exists_project = list(Mongo.get()['projects'].find(
{
'name': form_data['name']
}, {
'_id': 1,
'add_time': 1
}).limit(1))
if 'edit' not in form_data and exists_project:
return jsonify({'success': False, 'msg': '计划名称已经存在!'})
# 新增计划或更新计划
data = {
'name':
form_data['name'],
'init_url':
form_data['init_url'],
'desc':
form_data['desc'] if 'desc' in form_data else '',
'code':
form_data['code'],
'static':
'暂停中',
'update_time':
int(time.time()),
'add_time':
exists_project[0]['add_time'] if exists_project else int(time.time()),
}
Mongo.get()['projects'].update({'name': form_data['name']}, data, True)
# 当是新计划时的初始化
if 'edit' not in form_data:
Mongo.get()['queue_' + form_data['name']].insert({
'url':
form_data['init_url'],
'url_md5':
md5(form_data['init_url']),
'flag_time':
0,
'add_time':
int(time.time()),
'slave_ip':
'0.0.0.0'
})
# 在没创建集合前设置索引mongodb会自动创建该集合并赋索引
Mongo.get()['parsed_' + form_data['name']].ensure_index('url_md5',
unique=True)
Mongo.get()['queue_' + form_data['name']].ensure_index('url_md5',
unique=True)
# 有新计划加入, 重启全部slave
restart_slave_list = GlobalHelper.get('restart_slave_list') or []
for slave_record in Mongo.get()['slave_record'].find():
restart_slave_list.append(slave_record['ip'])
GlobalHelper.set('restart_slave_list', list(set(restart_slave_list)))
return jsonify({'success': True, 'msg': '保存成功!'})
def gen_search_sql_tuple(self, smiles, search_type="1", out_put_type=1):
"""
gen_search_sql_tuple(smiles[, search_type[, out_put_type]]) -- Returns a tuple
args:
smiles: str, smiles that represents a molecule.
search_type: str. values:
'1': full march,
'2': target structure contains substructure,
'3': target structure dosen't contains substructure
'4': target structure contains superstructure,
'5': target structure dosen't contains superstructure
out_put_type: int. values:
1 or not 2: without the mol_stat part.
2: contains the mol_stat part
generates the search sql string according to the smiles string.
returns a tuple contains two elements:
0: stat, some statistic of the mol such as number of C, number of rings and etc.
1: the sql part, sql not fully generated, only a part like this " FROM ... WHERE ... "
"""
fp_sql = ""
stat = {}
head_flag = "("
end_flag = ")"
stat_part = ""
md5_ob_can_smi_key = self.env["MD5_OPENBABEL_CAN_SMI_KEY"]
fp_bits_key = self.env["FP_BITS_KEY"]
sign_mol_stat = " >= "
try:
num_H_key = self.env["NUM_H_KEY"]
except:
num_H_key = "NUM_H"
bool_op = " AND "
mol_fp = {}
mol = mymol("smi", smiles)
mol.get_fps(mol_fp)
if search_type == "1":
if md5_ob_can_smi_key in self.recorded_fields_dict.keys():
return (
{},
self.recorded_fields_dict[md5_ob_can_smi_key]
+ " = '"
+ md5(mymol("smi", smiles).gen_openbabel_can_smiles())
+ "'",
)
else:
return ({}, "")
elif search_type in ("2", "4"):
mol_stat = {}
tmp_stat = {}
mol.get_mol_stat(mol_stat)
if mol_stat.has_key(num_H_key):
mol_stat.pop(num_H_key)
tmp_stat[str(fp_bits_key)] = mol_fp[fp_bits_key]
tmp_stat.update(mol_stat)
if search_type == "2":
sign_mol_stat = " >= "
stat["sub"] = tmp_stat
elif search_type == "4":
sign_mol_stat = " <= "
stat["sup"] = tmp_stat
bool_op = " AND "
elif search_type in ("3", "5"):
bool_op = " AND "
head_flag = " NOT ("
fps_keys = mol_fp.items()
fps_keys.sort()
for i, j in fps_keys:
if self.recorded_fields_dict.has_key(i) and i != fp_bits_key and j != 0:
if search_type in ("2", "3"):
fp_sql += self.recorded_fields_dict[i] + " & " + str(j) + " = " + str(j) + bool_op
elif search_type in ("4", "5"):
field = self.recorded_fields_dict[i]
fp_sql += field + " & " + str(j) + " = " + field + bool_op
if out_put_type == 2 and search_type in ("2", "4"):
val_k = []
for k, v in tmp_stat.items():
for j in self.def_dict.values():
if j.has_key(k):
val_k = j[k][0]
break
if val_k:
stat_part += str(val_k) + sign_mol_stat + str(v) + " AND "
if stat_part:
head_flag = "(" + stat_part.rstrip("AND ") + ") AND ("
if fp_sql.rstrip(bool_op):
return (stat, head_flag + fp_sql.rstrip(bool_op) + end_flag)
else:
return ({}, "1")