def check():
"""
checks a list of url's against Spamhaus's SBL - urllist.txt
the list must be full path and include http://
http://www.spamhaus.org/sbl/listings/{domain_provider} i.e. godaddy.com
:return: url's that are listed
"""
checker = SpamHausChecker()
with open('urllist.txt', 'r') as urllist:
for url in urllist:
url = url.strip()
if checker.is_spam(url) is True:
print url, 'is in the SBL'
else:
continue
def check():
"""
checks a list of url's against Spamhaus's SBL - urllist.txt
the list must be full path and include http://
http://www.spamhaus.org/sbl/listings/{domain_provider} i.e. godaddy.com
:return: url's that are listed
"""
checker = SpamHausChecker()
with open('urllist.txt', 'r') as urllist:
for url in urllist:
url = url.strip()
if checker.is_spam(url) is True:
print url, 'is in the SBL'
else:
continue
def check_spamhaus(url):
global urlschecked, want_spamhaus
domain = get_domain(url)
if not want_spamhaus:
return False
if url.startswith('http') or url.startswith('https'):
# short cirquit (caching is good!)
if urlschecked.has_key("sh-" + domain):
return urlschecked["sh-" + domain]
checker = SpamHausChecker()
try:
ret = checker.is_spam(url)
except Exception:
print("Whoops, trying again")
return False
urlschecked["sh-" + domain] = ret
return ret
else:
return False
# In[ ]:
# In[9]:
from sklearn.preprocessing import LabelEncoder
data = ['first', 'second', 'third', 'fourth']
enc = LabelEncoder()
label_encoder = enc.fit(data)
integer_classes = label_encoder.transform(label_encoder.classes_)
integer_classes
# In[12]:
from spam.spamhaus import SpamHausChecker
checker = SpamHausChecker()
checker.is_spam("http://www.google.com/search?q=food")
# In[16]:
from sklearn.ensemble import RandomForestClassifier
import numpy as np
print('test')
# In[12]:
import pandas as pd
import numpy as np
import seaborn as sns
df = pd.DataFrame({'a': [1, 1, 0, 1], 'b': [1, 1, 1, 0]})
sum((df['a'] == 1) & (df['b'] == 1))
# In[9]:
from sklearn.preprocessing import LabelEncoder
data = ['first', 'second', 'third', 'fourth']
enc = LabelEncoder()
label_encoder = enc.fit(data)
integer_classes = label_encoder.transform(label_encoder.classes_)
integer_classes
# In[12]:
from spam.spamhaus import SpamHausChecker
checker = SpamHausChecker()
checker.is_spam("http://www.google.com/search?q=food")
# In[16]:
from sklearn.ensemble import RandomForestClassifier
import numpy as np
print('test')
# In[12]:
import pandas as pd
import numpy as np
import seaborn as sns
