add exclude_badExits.py

README.md

@@ -71,3 +71,79 @@ You can expect it to take an hour or two the first time this is run:
 >700 domains.
 
 For usage, do ```python3 exclude_badExits.py --help`
+
+## Usage
+```
+usage: exclude_badExits.py [-h] [--https_cafile HTTPS_CAFILE]
+                           [--proxy_host PROXY_HOST] [--proxy_port PROXY_PORT]
+                           [--proxy_ctl PROXY_CTL] [--torrc TORRC]
+                           [--timeout TIMEOUT] [--good_nodes GOOD_NODES]
+                           [--bad_nodes BAD_NODES] [--contact CONTACT]
+                           [--bad_contacts BAD_CONTACTS]
+                           [--strict_nodes {0,1}] [--wait_boot WAIT_BOOT]
+                           [--points_timeout POINTS_TIMEOUT]
+                           [--log_level LOG_LEVEL]
+                           [--bad_sections BAD_SECTIONS]
+                           [--white_services WHITE_SERVICES]
+                           [--torrc_output TORRC_OUTPUT]
+                           [--proof_output PROOF_OUTPUT]
+```
+
+### Optional arguments:
+
+```
+  -h, --help            show this help message and exit
+  --https_cafile HTTPS_CAFILE
+                        Certificate Authority file (in PEM)
+```
+```
+  --proxy_host PROXY_HOST, --proxy-host PROXY_HOST
+                        proxy host
+  --proxy_port PROXY_PORT, --proxy-port PROXY_PORT
+                        proxy control port
+  --proxy_ctl PROXY_CTL, --proxy-ctl PROXY_CTL
+                        control socket - or port
+```
+```
+  --torrc TORRC         torrc to check for suggestions
+  --timeout TIMEOUT     proxy download connect timeout
+```
+```
+  --good_nodes GOOD_NODES
+                        Yaml file of good info that should not be excluded
+  --bad_nodes BAD_NODES
+                        Yaml file of bad nodes that should also be excluded
+```
+```
+  --contact CONTACT     comma sep list of conditions - Empty,NoEmail
+  --bad_contacts BAD_CONTACTS
+                        Yaml file of bad contacts that bad FPs are using
+```
+```
+  --strict_nodes {0,1}  Set StrictNodes: 1 is less anonymous but more secure,
+                        although some sites may be unreachable
+  --wait_boot WAIT_BOOT
+                        Seconds to wait for Tor to booststrap
+  --points_timeout POINTS_TIMEOUT
+                        Timeout for getting introduction points - must be long
+                        >120sec. 0 means disabled looking for IPs
+```
+```
+  --log_level LOG_LEVEL
+                        10=debug 20=info 30=warn 40=error
+  --bad_sections BAD_SECTIONS
+                        sections of the badnodes.yaml to use, comma separated,
+                        '' BROKEN
+```
+```
+  --white_services WHITE_SERVICES
+                        comma sep. list of onions to whitelist their
+                        introduction points - BROKEN
+```
+```
+  --torrc_output TORRC_OUTPUT
+                        Write the torrc configuration to a file
+  --proof_output PROOF_OUTPUT
+                        Write the proof data of the included nodes to a YAML
+                        file
+```

exclude_badExits.py

@@ -48,7 +48,7 @@ exclusion: the ```--contact``` commandline arg is a comma sep list of conditions
 More may be added later.
 
 Because you don't want to exclude the introduction points to any onion
-you want to connect to, ```--white_services``` should whitelist the
+you want to connect to, ```--white_onions``` should whitelist the
 introduction points to a  comma sep list of onions, but is
 currently broken in stem 1.8.0: see:
 * https://github.com/torproject/stem/issues/96
@@ -88,7 +88,7 @@ import time
 import argparse
 import string
 from io import StringIO
-import ipaddr
+import ipaddress
 # list(ipaddress._find_address_range(ipaddress.IPv4Network('172.16.0.0/12'))
 
 from urllib3.util.ssl_match_hostname import CertificateError
@@ -98,15 +98,23 @@ from stem.control import Controller
 from stem.connection import IncorrectPassword
 from stem.util.tor_tools import is_valid_fingerprint
 try:
-    import yaml
+    from ruamel.yaml import YAML
+    yaml = YAML()
+    safe_load = yaml.load
 except:
     yaml = None
+if yaml is None:
+    try:
+        import yaml
+        safe_load = yaml.safe_load
+    except:
+        yaml = None
+
 try:
     from unbound import ub_ctx,RR_TYPE_TXT,RR_CLASS_IN
 except:
     ub_ctx = RR_TYPE_TXT = RR_CLASS_IN = None
 
-
 global LOG
 import logging
 import warnings
@@ -158,7 +166,7 @@ def lYamlBadNodes(sFile,
     if not yaml: return l
     if os.path.exists(sFile):
         with open(sFile, 'rt') as oFd:
-            oBAD_NODES = yaml.safe_load(oFd)
+            oBAD_NODES = safe_load(oFd)
 
     # BROKEN
 #    root = 'ExcludeNodes'
@@ -170,7 +178,7 @@ def lYamlBadNodes(sFile,
 
     root = 'ExcludeDomains'
     if root not in oBAD_NODES[oBAD_ROOT] or not oBAD_NODES[oBAD_ROOT][root]:
-        lMAYBE_NODNS = yaml.safe_load(StringIO(yKNOWN_NODNS))
+        lMAYBE_NODNS = safe_load(StringIO(yKNOWN_NODNS))
     else:
         lMAYBE_NODNS = oBAD_NODES[oBAD_ROOT][root]
     return l
@@ -184,7 +192,7 @@ def lYamlGoodNodes(sFile='/etc/tor/torrc-goodnodes.yaml'):
     if not yaml: return l
     if os.path.exists(sFile):
         with open(sFile, 'rt') as oFd:
-            o = yaml.safe_load(oFd)
+            o = safe_load(oFd)
             oGOOD_NODES = o
         if 'GuardNodes' in o[oGOOD_ROOT].keys():
             l = o[oGOOD_ROOT]['GuardNodes']
@@ -373,7 +381,7 @@ def aParseContact(contact, fp):
     s += '\n'.join([f"  {line}\"".replace(':',': \"', 1)
                     for line in l])
     oFd = StringIO(s)
-    a = yaml.safe_load(oFd)
+    a = safe_load(oFd)
     return a
 
 def oMainArgparser(_=None):
@@ -414,10 +422,10 @@ def oMainArgparser(_=None):
                         help='proxy download connect timeout')
 
     parser.add_argument('--good_nodes', type=str,
-                        default=os.path.join(ETC_DIR, 'torrc-goodnodes.yaml'),
+                        default=os.path.join(ETC_DIR, 'goodnodes.yaml'),
                         help="Yaml file of good info that should not be excluded")
     parser.add_argument('--bad_nodes', type=str,
-                        default=os.path.join(ETC_DIR, 'torrc-badnodes.yaml'),
+                        default=os.path.join(ETC_DIR, 'badnodes.yaml'),
                         help="Yaml file of bad nodes that should also be excluded")
     parser.add_argument('--contact', type=str, default='Empty,NoEmail',
                         help="comma sep list of conditions - Empty,NoEmail")
@@ -437,13 +445,13 @@ def oMainArgparser(_=None):
     parser.add_argument('--bad_sections', type=str,
                         default='MyBadExit',
                         help="sections of the badnodes.yaml to use, comma separated, '' BROKEN")
-    parser.add_argument('--white_services', type=str,
+    parser.add_argument('--white_onions', type=str,
                         default='',
                         help="comma sep. list of onions to whitelist their introduction points - BROKEN")
     parser.add_argument('--torrc_output', type=str,
                         default=os.path.join(ETC_DIR, 'torrc.new'),
                         help="Write the torrc configuration to a file")
-    parser.add_argument('--proof_output', type=str, default=os.path.join(ETC_DIR, 'proof.yaml'),
+    parser.add_argument('--proof_output', type=str, default=os.path.join(ETC_DIR, 'goodcontacts.yaml'),
                         help="Write the proof data of the included nodes to a YAML file")
     return parser
 
@@ -493,8 +501,7 @@ def iMain(lArgs):
     if sFile and os.path.exists(sFile):
         try:
             with open(sFile, 'rt') as oFd:
-                aTRUST_DB = yaml.safe_load(oFd)
+                aTRUST_DB = safe_load(oFd)
-            assert type(aTRUST_DB) == dict
             LOG.info(f"{len(aTRUST_DB.keys())} trusted contacts from {sFile}")
             # reverse lookup of fps to contacts
             # but...
@@ -541,10 +548,17 @@ def iMain(lArgs):
     t = set()
     if 'IntroductionPoints' in oGOOD_NODES[oGOOD_ROOT]['Relays'].keys():
         t = set(oGOOD_NODES[oGOOD_ROOT]['Relays']['IntroductionPoints'])
-    # not working = maybe when stem is updated
+    w = set()
-    w = set(oGOOD_NODES[oGOOD_ROOT]['Services'])
+    if 'Services' in oGOOD_NODES[oGOOD_ROOT].keys():
-    if oArgs.white_services:
+        # 'Onions' can I use the IntroductionPoints for Services too?
-        w.update(oArgs.white_services.split(','))
+        # w = set(oGOOD_NODES[oGOOD_ROOT]['Services'])
+        pass
+    if 'Onions' in oGOOD_NODES[oGOOD_ROOT].keys():
+        # Provides the descriptor for a hidden service. The **address** is the
+        # '.onion' address of the hidden service 
+        w = set(oGOOD_NODES[oGOOD_ROOT]['Onions'])
+    if oArgs.white_onions:
+        w.update(oArgs.white_onions.split(','))
     if oArgs.points_timeout > 0:
         LOG.info(f"{len(w)} services will be checked from IntroductionPoints")
         t.update(lIntroductionPoints(controller, w, itimeout=oArgs.points_timeout))

support_onions.py

@@ -14,10 +14,12 @@ if False:
     import cepa as stem
     from cepa.control import Controller
     from cepa.connection import MissingPassword
+    from cepa.util.tor_tools import is_valid_fingerprint
 else:
     import stem
     from stem.control import Controller
     from stem.connection import MissingPassword
+    from stem.util.tor_tools import is_valid_fingerprint
 
 global LOG
 import logging
@@ -144,7 +146,11 @@ def bin_to_hex(raw_id, length=None):
     return res.upper()
 
 def lIntroductionPoints(controller=None, lOnions=[], itimeout=120, log_level=10):
-    """now working !!! stem 1.8.x timeout must be huge >120"""
+    """now working !!! stem 1.8.x timeout must be huge >120
+    'Provides the descriptor for a hidden service. The **address** is the
+    '.onion' address of the hidden service '
+    What about Services?
+    """
     try:
         from cryptography.utils import int_from_bytes
     except ImportError:

trustor_poc.py

@@ -355,7 +355,7 @@ def _my_match_hostname(cert, asserted_hostname):
     try:
         my_match_hostname(cert, asserted_hostname)
     except CertificateError as e:
-        log.warning(
+        LOG.warning(
             "Certificate did not match hostname: %s. Certificate: %s",
             asserted_hostname,
             cert,