|
1
|
|
|
"""The module describes the VirusTotalAPIUrls class |
|
2
|
|
|
|
|
3
|
|
|
Author: Evgeny Drobotun (c) 2019 |
|
4
|
|
|
License: MIT (https://github.com/drobotun/virustotalapi3/blob/master/LICENSE) |
|
5
|
|
|
|
|
6
|
|
|
More information: https://virustotalapi3.readthedocs.io/en/latest/url_class.html |
|
7
|
|
|
""" |
|
8
|
|
|
|
|
9
|
|
|
import base64 |
|
10
|
|
|
import hashlib |
|
11
|
|
|
import errno |
|
12
|
|
|
import requests |
|
13
|
|
|
|
|
14
|
|
|
from .vtapi3base import VirusTotalAPI |
|
15
|
|
|
from .vtapi3error import VirusTotalAPIError |
|
16
|
|
|
|
|
17
|
|
|
class VirusTotalAPIUrls(VirusTotalAPI): |
|
18
|
|
|
"""The analysis new URLs and retrieving information about any URLs from the VirusTotal database |
|
19
|
|
|
methods are defined in the class. |
|
20
|
|
|
|
|
21
|
|
|
Methods: |
|
22
|
|
|
get_url_id_base64(): Get base64 encoded URL identifier. |
|
23
|
|
|
get_url_id_sha256(): Get the URL identifier as a SHA256 hash. |
|
24
|
|
|
upload(): Upload URL for analysis. |
|
25
|
|
|
get_report(): Retrieve information about an URL. |
|
26
|
|
|
analyse(): Analyse an URL. |
|
27
|
|
|
get_comments(): Retrieve comments for an URL. |
|
28
|
|
|
put_comments(): Add a comment to a URL. |
|
29
|
|
|
get_votes(): Retrieve votes for an URL. |
|
30
|
|
|
put_votes(): Add a votes to a URL. |
|
31
|
|
|
get_network_location(): Get the domain or IP address for a URL. |
|
32
|
|
|
""" |
|
33
|
|
|
|
|
34
|
|
|
@staticmethod |
|
35
|
|
|
def get_url_id_base64(url): |
|
36
|
|
|
"""Get base64 encoded URL identifier. |
|
37
|
|
|
|
|
38
|
|
|
Args: |
|
39
|
|
|
url: The URL for which you want to get the identifier (str). |
|
40
|
|
|
|
|
41
|
|
|
Return: |
|
42
|
|
|
The identifier of the url, base64 encoded (str). |
|
43
|
|
|
""" |
|
44
|
|
|
return base64.urlsafe_b64encode(url.encode('utf-8')).decode('utf-8').rstrip('=') |
|
45
|
|
|
|
|
46
|
|
|
@staticmethod |
|
47
|
|
|
def get_url_id_sha256(url): |
|
48
|
|
|
"""Get the URL identifier as a SHA256 hash. |
|
49
|
|
|
|
|
50
|
|
|
Args: |
|
51
|
|
|
url: The URL for which you want to get the identifier (str). |
|
52
|
|
|
|
|
53
|
|
|
Return: |
|
54
|
|
|
The identifier of the url, SHA256 encoded (str). |
|
55
|
|
|
""" |
|
56
|
|
|
return hashlib.sha256(url.encode()).hexdigest() |
|
57
|
|
|
|
|
58
|
|
|
def upload(self, url): |
|
59
|
|
|
"""Upload URL for analysis. |
|
60
|
|
|
|
|
61
|
|
|
Args: |
|
62
|
|
|
url: URL to be analyzed (str). |
|
63
|
|
|
|
|
64
|
|
|
Return: |
|
65
|
|
|
The response from the server as a byte sequence. |
|
66
|
|
|
|
|
67
|
|
|
Exception |
|
68
|
|
|
VirusTotalAPIError(Connection error): In case of server connection errors. |
|
69
|
|
|
VirusTotalAPIError(Timeout error): If the response timeout from the server is exceeded. |
|
70
|
|
|
""" |
|
71
|
|
|
self._last_http_error = None |
|
72
|
|
|
self._last_result = None |
|
73
|
|
|
data = {'url': url} |
|
74
|
|
|
api_url = self.base_url + '/urls' |
|
75
|
|
|
try: |
|
76
|
|
|
response = requests.post(api_url, headers=self.headers, data=data, |
|
77
|
|
|
timeout=self.timeout, proxies=self.proxies) |
|
78
|
|
|
except requests.exceptions.Timeout: |
|
79
|
|
|
raise VirusTotalAPIError('Timeout error', errno.ETIMEDOUT) |
|
80
|
|
|
except requests.exceptions.ConnectionError: |
|
81
|
|
|
raise VirusTotalAPIError('Connection error', errno.ECONNABORTED) |
|
82
|
|
|
else: |
|
83
|
|
|
self._last_http_error = response.status_code |
|
84
|
|
|
self._last_result = response.content |
|
85
|
|
|
return response.content |
|
86
|
|
|
|
|
87
|
|
|
def get_report(self, url_id): |
|
88
|
|
|
"""Retrieve information about an URL. |
|
89
|
|
|
|
|
90
|
|
|
Args: |
|
91
|
|
|
url_id: URL identifier (str). This identifier can adopt two forms: the SHA-256 of the |
|
92
|
|
|
canonized URL (method 'get_url_id_sha256()'), the string resulting from encoding the |
|
93
|
|
|
URL in base64 without the "=" padding (method 'get_url_id_base64()'). |
|
94
|
|
|
|
|
95
|
|
|
Return: |
|
96
|
|
|
The response from the server as a byte sequence. |
|
97
|
|
|
|
|
98
|
|
|
Exception |
|
99
|
|
|
VirusTotalAPIError(Connection error): In case of server connection errors. |
|
100
|
|
|
VirusTotalAPIError(Timeout error): If the response timeout from the server is exceeded. |
|
101
|
|
|
""" |
|
102
|
|
|
self._last_http_error = None |
|
103
|
|
|
self._last_result = None |
|
104
|
|
|
api_url = self.base_url + '/urls/' + url_id |
|
105
|
|
|
try: |
|
106
|
|
|
response = requests.get(api_url, headers=self.headers, |
|
107
|
|
|
timeout=self.timeout, proxies=self.proxies) |
|
108
|
|
|
except requests.exceptions.Timeout: |
|
109
|
|
|
raise VirusTotalAPIError('Timeout error', errno.ETIMEDOUT) |
|
110
|
|
|
except requests.exceptions.ConnectionError: |
|
111
|
|
|
raise VirusTotalAPIError('Connection error', errno.ECONNABORTED) |
|
112
|
|
|
else: |
|
113
|
|
|
self._last_http_error = response.status_code |
|
114
|
|
|
self._last_result = response.content |
|
115
|
|
|
return response.content |
|
116
|
|
|
|
|
117
|
|
|
def analyse(self, url_id): |
|
118
|
|
|
"""Analyse an URL. |
|
119
|
|
|
|
|
120
|
|
|
Args: |
|
121
|
|
|
url_id: URL identifier (str). This identifier can adopt two forms: the SHA-256 of the |
|
122
|
|
|
canonized URL (method 'get_url_id_sha256()'), the string resulting from encoding the |
|
123
|
|
|
URL in base64 without the "=" padding (method 'get_url_id_base64()'). |
|
124
|
|
|
|
|
125
|
|
|
Return: |
|
126
|
|
|
The response from the server as a byte sequence. |
|
127
|
|
|
|
|
128
|
|
|
Exception |
|
129
|
|
|
VirusTotalAPIError(Connection error): In case of server connection errors. |
|
130
|
|
|
VirusTotalAPIError(Timeout error): If the response timeout from the server is exceeded. |
|
131
|
|
|
""" |
|
132
|
|
|
self._last_http_error = None |
|
133
|
|
|
self._last_result = None |
|
134
|
|
|
api_url = self.base_url + '/urls/' + url_id + '/analyse' |
|
135
|
|
|
try: |
|
136
|
|
|
response = requests.post(api_url, headers=self.headers, |
|
137
|
|
|
timeout=self.timeout, proxies=self.proxies) |
|
138
|
|
|
except requests.exceptions.Timeout: |
|
139
|
|
|
raise VirusTotalAPIError('Timeout error', errno.ETIMEDOUT) |
|
140
|
|
|
except requests.exceptions.ConnectionError: |
|
141
|
|
|
raise VirusTotalAPIError('Connection error', errno.ECONNABORTED) |
|
142
|
|
|
else: |
|
143
|
|
|
self._last_http_error = response.status_code |
|
144
|
|
|
self._last_result = response.content |
|
145
|
|
|
return response.content |
|
146
|
|
|
|
|
147
|
|
|
def get_comments(self, url_id, limit=10, cursor='""'): |
|
148
|
|
|
"""Retrieve comments for an URL. |
|
149
|
|
|
|
|
150
|
|
|
Args: |
|
151
|
|
|
url_id: URL identifier (str). This identifier can adopt two forms: the SHA-256 of the |
|
152
|
|
|
canonized URL (method 'get_url_id_sha256()'), the string resulting from encoding the |
|
153
|
|
|
URL in base64 without the "=" padding (method 'get_url_id_base64()'). |
|
154
|
|
|
limit: Maximum number of comments to retrieve (int). The default value is 10. |
|
155
|
|
|
cursor: Continuation cursor (str). The default value is ''. |
|
156
|
|
|
|
|
157
|
|
|
Return: |
|
158
|
|
|
The response from the server as a byte sequence. |
|
159
|
|
|
|
|
160
|
|
|
Exception |
|
161
|
|
|
VirusTotalAPIError(Connection error): In case of server connection errors. |
|
162
|
|
|
VirusTotalAPIError(Timeout error): If the response timeout from the server is exceeded. |
|
163
|
|
|
""" |
|
164
|
|
|
self._last_http_error = None |
|
165
|
|
|
self._last_result = None |
|
166
|
|
|
query_string = {'limit': str(limit), 'cursor': cursor} |
|
167
|
|
|
api_url = self.base_url + '/urls/' + url_id + '/comments' |
|
168
|
|
|
try: |
|
169
|
|
|
response = requests.get(api_url, headers=self.headers, params=query_string, |
|
170
|
|
|
timeout=self.timeout, proxies=self.proxies) |
|
171
|
|
|
except requests.exceptions.Timeout: |
|
172
|
|
|
raise VirusTotalAPIError('Timeout error', errno.ETIMEDOUT) |
|
173
|
|
|
except requests.exceptions.ConnectionError: |
|
174
|
|
|
raise VirusTotalAPIError('Connection error', errno.ECONNABORTED) |
|
175
|
|
|
else: |
|
176
|
|
|
self._last_http_error = response.status_code |
|
177
|
|
|
self._last_result = response.content |
|
178
|
|
|
return response.content |
|
179
|
|
|
|
|
180
|
|
|
def put_comments(self, url_id, text): |
|
181
|
|
|
"""Add a comment to a URL. |
|
182
|
|
|
|
|
183
|
|
|
Args: |
|
184
|
|
|
url_id: URL identifier (str). This identifier can adopt two forms: the SHA-256 of the |
|
185
|
|
|
canonized URL (method 'get_url_id_sha256()'), the string resulting from encoding the |
|
186
|
|
|
URL in base64 without the "=" padding (method 'get_url_id_base64()'). |
|
187
|
|
|
text: Text of the comment (str). |
|
188
|
|
|
|
|
189
|
|
|
Return: |
|
190
|
|
|
The response from the server as a byte sequence. |
|
191
|
|
|
|
|
192
|
|
|
Exception |
|
193
|
|
|
VirusTotalAPIError(Connection error): In case of server connection errors. |
|
194
|
|
|
VirusTotalAPIError(Timeout error): If the response timeout from the server is exceeded. |
|
195
|
|
|
""" |
|
196
|
|
|
self._last_http_error = None |
|
197
|
|
|
self._last_result = None |
|
198
|
|
|
comments = {"data": {'type': 'comment', 'attributes': {'text': text}}} |
|
199
|
|
|
api_url = self.base_url + '/urls/' + url_id + '/comments' |
|
200
|
|
|
try: |
|
201
|
|
|
response = requests.post(api_url, headers=self.headers, json=comments, |
|
202
|
|
|
timeout=self.timeout, proxies=self.proxies) |
|
203
|
|
|
except requests.exceptions.Timeout: |
|
204
|
|
|
raise VirusTotalAPIError('Timeout error', errno.ETIMEDOUT) |
|
205
|
|
|
except requests.exceptions.ConnectionError: |
|
206
|
|
|
raise VirusTotalAPIError('Connection error', errno.ECONNABORTED) |
|
207
|
|
|
else: |
|
208
|
|
|
self._last_http_error = response.status_code |
|
209
|
|
|
self._last_result = response.content |
|
210
|
|
|
return response.content |
|
211
|
|
|
|
|
212
|
|
|
def get_votes(self, url_id, limit=10, cursor='""'): |
|
213
|
|
|
"""Retrieve votes for a URL. |
|
214
|
|
|
|
|
215
|
|
|
Args: |
|
216
|
|
|
url_id: URL identifier (str). This identifier can adopt two forms: the SHA-256 of the |
|
217
|
|
|
canonized URL (method 'get_url_id_sha256()'), the string resulting from encoding the |
|
218
|
|
|
URL in base64 without the "=" padding (method 'get_url_id_base64()'). |
|
219
|
|
|
limit: Maximum number of comments to retrieve (int). The default value is 10. |
|
220
|
|
|
cursor: Continuation cursor (str). The default value is ''. |
|
221
|
|
|
|
|
222
|
|
|
Return: |
|
223
|
|
|
The response from the server as a byte sequence. |
|
224
|
|
|
|
|
225
|
|
|
Exception |
|
226
|
|
|
VirusTotalAPIError(Connection error): In case of server connection errors. |
|
227
|
|
|
VirusTotalAPIError(Timeout error): If the response timeout from the server is exceeded. |
|
228
|
|
|
""" |
|
229
|
|
|
self._last_http_error = None |
|
230
|
|
|
self._last_result = None |
|
231
|
|
|
query_string = {'limit': str(limit), 'cursor': cursor} |
|
232
|
|
|
api_url = self.base_url + '/urls/' + url_id + '/votes' |
|
233
|
|
|
try: |
|
234
|
|
|
response = requests.get(api_url, headers=self.headers, params=query_string, |
|
235
|
|
|
timeout=self.timeout, proxies=self.proxies) |
|
236
|
|
|
except requests.exceptions.Timeout: |
|
237
|
|
|
raise VirusTotalAPIError('Timeout error', errno.ETIMEDOUT) |
|
238
|
|
|
except requests.exceptions.ConnectionError: |
|
239
|
|
|
raise VirusTotalAPIError('Connection error', errno.ECONNABORTED) |
|
240
|
|
|
else: |
|
241
|
|
|
self._last_http_error = response.status_code |
|
242
|
|
|
self._last_result = response.content |
|
243
|
|
|
return response.content |
|
244
|
|
|
|
|
245
|
|
|
def put_votes(self, url_id, malicious=False): |
|
246
|
|
|
"""Add a vote for a URL. |
|
247
|
|
|
|
|
248
|
|
|
Args: |
|
249
|
|
|
url_id: URL identifier (str). This identifier can adopt two forms: the SHA-256 of the |
|
250
|
|
|
canonized URL (method 'get_url_id_sha256()'), the string resulting from encoding the |
|
251
|
|
|
URL in base64 without the "=" padding (method 'get_url_id_base64()'). |
|
252
|
|
|
malicious: Determines a malicious (True) or harmless (False) URL (bool). |
|
253
|
|
|
|
|
254
|
|
|
Return: |
|
255
|
|
|
The response from the server as a byte sequence. |
|
256
|
|
|
|
|
257
|
|
|
Exception |
|
258
|
|
|
VirusTotalAPIError(Connection error): In case of server connection errors. |
|
259
|
|
|
VirusTotalAPIError(Timeout error): If the response timeout from the server is exceeded. |
|
260
|
|
|
""" |
|
261
|
|
|
self._last_http_error = None |
|
262
|
|
|
self._last_result = None |
|
263
|
|
|
if malicious: |
|
264
|
|
|
verdict = 'malicious' |
|
265
|
|
|
else: |
|
266
|
|
|
verdict = 'harmless' |
|
267
|
|
|
votes = {'data': {'type': 'vote', 'attributes': {'verdict': verdict}}} |
|
268
|
|
|
api_url = self.base_url + '/urls/' + url_id + '/votes' |
|
269
|
|
|
try: |
|
270
|
|
|
response = requests.post(api_url, headers=self.headers, json=votes, |
|
271
|
|
|
timeout=self.timeout, proxies=self.proxies) |
|
272
|
|
|
except requests.exceptions.Timeout: |
|
273
|
|
|
raise VirusTotalAPIError('Timeout error', errno.ETIMEDOUT) |
|
274
|
|
|
except requests.exceptions.ConnectionError: |
|
275
|
|
|
raise VirusTotalAPIError('Connection error', errno.ECONNABORTED) |
|
276
|
|
|
else: |
|
277
|
|
|
self._last_http_error = response.status_code |
|
278
|
|
|
self._last_result = response.content |
|
279
|
|
|
return response.content |
|
280
|
|
|
|
|
281
|
|
|
def get_network_location(self, url_id): |
|
282
|
|
|
"""Get the domain or IP address for a URL. |
|
283
|
|
|
|
|
284
|
|
|
Args: |
|
285
|
|
|
url_id: URL identifier (str). This identifier can adopt two forms: the SHA-256 of the |
|
286
|
|
|
canonized URL (method 'get_url_id_sha256()'), the string resulting from encoding the |
|
287
|
|
|
URL in base64 without the "=" padding (method 'get_url_id_base64()'). |
|
288
|
|
|
|
|
289
|
|
|
Return: |
|
290
|
|
|
The response from the server as a byte sequence. |
|
291
|
|
|
|
|
292
|
|
|
Exception |
|
293
|
|
|
VirusTotalAPIError(Connection error): In case of server connection errors. |
|
294
|
|
|
VirusTotalAPIError(Timeout error): If the response timeout from the server is exceeded. |
|
295
|
|
|
""" |
|
296
|
|
|
self._last_http_error = None |
|
297
|
|
|
self._last_result = None |
|
298
|
|
|
api_url = self.base_url + '/urls/' + url_id + '/network_location' |
|
299
|
|
|
try: |
|
300
|
|
|
response = requests.get(api_url, headers=self.headers, |
|
301
|
|
|
timeout=self.timeout, proxies=self.proxies) |
|
302
|
|
|
except requests.exceptions.Timeout: |
|
303
|
|
|
raise VirusTotalAPIError('Timeout error', errno.ETIMEDOUT) |
|
304
|
|
|
except requests.exceptions.ConnectionError: |
|
305
|
|
|
raise VirusTotalAPIError('Connection error', errno.ECONNABORTED) |
|
306
|
|
|
else: |
|
307
|
|
|
self._last_http_error = response.status_code |
|
308
|
|
|
self._last_result = response.content |
|
309
|
|
|
return response.content |
|
310
|
|
|
|
|
311
|
|
|
def get_relationship(self, url_id, relationship='/last_serving_ip_address', |
|
312
|
|
|
limit=10, cursor='""'): |
|
313
|
|
|
"""Retrieve objects related to an URL |
|
314
|
|
|
|
|
315
|
|
|
Args: |
|
316
|
|
|
url_id: URL identifier (str). This identifier can adopt two forms: the SHA-256 of the |
|
317
|
|
|
canonized URL (method 'get_url_id_sha256()'), the string resulting from encoding the |
|
318
|
|
|
URL in base64 without the "=" padding (method 'get_url_id_base64()'). |
|
319
|
|
|
relationship: Relationship name (str). The default value is '/last_serving_ip_address'. |
|
320
|
|
|
limit: Maximum number of comments to retrieve (int). The default value is 10. |
|
321
|
|
|
cursor: Continuation cursor (str). The default value is ''. |
|
322
|
|
|
|
|
323
|
|
|
Return: |
|
324
|
|
|
The response from the server as a byte sequence. |
|
325
|
|
|
|
|
326
|
|
|
Exception |
|
327
|
|
|
VirusTotalAPIError(Connection error): In case of server connection errors. |
|
328
|
|
|
VirusTotalAPIError(Timeout error): If the response timeout from the server is exceeded. |
|
329
|
|
|
""" |
|
330
|
|
|
self._last_http_error = None |
|
331
|
|
|
self._last_result = None |
|
332
|
|
|
query_string = {'limit': str(limit), 'cursor': cursor} |
|
333
|
|
|
api_url = self.base_url + '/urls/' + url_id + relationship |
|
334
|
|
|
try: |
|
335
|
|
|
response = requests.get(api_url, headers=self.headers, params=query_string, |
|
336
|
|
|
timeout=self.timeout, proxies=self.proxies) |
|
337
|
|
|
except requests.exceptions.Timeout: |
|
338
|
|
|
raise VirusTotalAPIError('Timeout error', errno.ETIMEDOUT) |
|
339
|
|
|
except requests.exceptions.ConnectionError: |
|
340
|
|
|
raise VirusTotalAPIError('Connection error', errno.ECONNABORTED) |
|
341
|
|
|
else: |
|
342
|
|
|
self._last_http_error = response.status_code |
|
343
|
|
|
self._last_result = response.content |
|
344
|
|
|
return response.content |
|
345
|
|
|
|