teemo/lib/myparser.py at master · bit4woo/teemo · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
import string
import re
import urllib


class parser:

    def __init__(self, results, word):
        self.results = results
        self.word = word
        self.temp = []

    def genericClean(self):
        self.results = re.sub('<em>', '', self.results)
        self.results = re.sub('<b>', '', self.results)
        self.results = re.sub('</b>', '', self.results)
        self.results = re.sub('</em>', '', self.results)
        #self.results = re.sub('%2f', ' ', self.results)
        #self.results = re.sub('%3a', ' ', self.results)
        self.results = re.sub('<strong>', '', self.results)
        self.results = re.sub('</strong>', '', self.results)
        self.results = re.sub('<wbr>','',self.results)
        self.results = re.sub('</wbr>','',self.results)

        i= 3
        while True:
            self.results = urllib.unquote(self.results)
            if "%25" in self.results and i>0:
                self.results = urllib.unquote(self.results)
                i -= 1
                continue
            else:
                self.results = urllib.unquote(self.results)
                i -= 1
                break


        for e in ('>', ':', '=', '<', '/', '\\', ';', '&', '%3A', '%3D', '%3C'):
            self.results = string.replace(self.results, e, ' ')

    def urlClean(self):
        self.results = re.sub('<em>', '', self.results)
        self.results = re.sub('</em>', '', self.results)
        self.results = re.sub('%2f', ' ', self.results)
        self.results = re.sub('%3a', ' ', self.results)

        for e in ('<', '>', ':', '=', ';', '&', '%3A', '%3D', '%3C'):
            self.results = string.replace(self.results, e, ' ')

    def emails(self):
        self.genericClean()
        reg_emails = re.compile(
            # Local part is required, charset is flexible
           # https://tools.ietf.org/html/rfc6531 (removed * and () as they provide FP mostly )
            '[a-zA-Z0-9.\-_+#~!$&,;=:]+' +
            '@' +
            '[a-zA-Z0-9.-]*' +
            self.word)
        self.temp = reg_emails.findall(self.results)
        emails = self.unique()
        return emails

    def fileurls(self, file):
        urls = []
        reg_urls = re.compile('<a href="(.*?)"')
        self.temp = reg_urls.findall(self.results)
        allurls = self.unique()
        for x in allurls:
            if x.count('webcache') or x.count('google.com') or x.count('search?hl'):
                pass
            else:
                urls.append(x)
        return urls

    def people_googleplus(self):
        self.results = re.sub('</b>', '', self.results)
        self.results = re.sub('<b>', '', self.results)
        reg_people = re.compile('>[a-zA-Z0-9._ ]* - Google\+')
        #reg_people = re.compile('">[a-zA-Z0-9._ -]* profiles | LinkedIn')
        self.temp = reg_people.findall(self.results)
        resul = []
        for x in self.temp:
            y = string.replace(x, ' | LinkedIn', '')
            y = string.replace(y, ' profiles ', '')
            y = string.replace(y, 'LinkedIn', '')
            y = string.replace(y, '"', '')
            y = string.replace(y, '>', '')
            if y != " ":
                resul.append(y)
        return resul


    def people_twitter(self):
        reg_people = re.compile('(@[a-zA-Z0-9._ -]*)')
        #reg_people = re.compile('">[a-zA-Z0-9._ -]* profiles | LinkedIn')
        self.temp = reg_people.findall(self.results)
        users = self.unique()
        resul = []
        for x in users:
            y = string.replace(x, ' | LinkedIn', '')
            y = string.replace(y, ' profiles ', '')
            y = string.replace(y, 'LinkedIn', '')
            y = string.replace(y, '"', '')
            y = string.replace(y, '>', '')
            if y != " ":
                resul.append(y)
        return resul

    def people_linkedin(self):
        reg_people = re.compile('">[a-zA-Z0-9._ -]* \| LinkedIn')
        #reg_people = re.compile('">[a-zA-Z0-9._ -]* profiles | LinkedIn')
        self.temp = reg_people.findall(self.results)
        resul = []
        for x in self.temp:
            y = string.replace(x, ' | LinkedIn', '')
            y = string.replace(y, ' profiles ', '')
            y = string.replace(y, 'LinkedIn', '')
            y = string.replace(y, '"', '')
            y = string.replace(y, '>', '')
            if y != " ":
                resul.append(y)
        return resul

    def profiles(self):
        reg_people = re.compile('">[a-zA-Z0-9._ -]* - <em>Google Profile</em>')
        self.temp = reg_people.findall(self.results)
        resul = []
        for x in self.temp:
            y = string.replace(x, ' <em>Google Profile</em>', '')
            y = string.replace(y, '-', '')
            y = string.replace(y, '">', '')
            if y != " ":
                resul.append(y)
        return resul

    def people_jigsaw(self):
        res = []
        #reg_people = re.compile("'tblrow' title='[a-zA-Z0-9.-]*'><span class='nowrap'/>")
        reg_people = re.compile(
            "href=javascript:showContact\('[0-9]*'\)>[a-zA-Z0-9., ]*</a></span>")
        self.temp = reg_people.findall(self.results)
        for x in self.temp:
            a = x.split('>')[1].replace("</a", "")
            res.append(a)
        return res

    def hostnames(self):
        self.genericClean()
        reg_hosts = re.compile('[a-zA-Z0-9]'+'[a-zA-Z0-9.-]*\.' + self.word)
        #reg_hosts = re.compile('[a-zA-Z0-9]+(-[a-z0-9]+)*\.)+[a-z]{2,}'+self.word)

        self.temp = reg_hosts.findall(self.results)
        hostnames = self.unique()
        return hostnames

    def smilarhostnames(self):
        self.genericClean()
        #reg_hosts = re.compile('[a-zA-Z0-9.-]*\.' + self.word)
        reg_hosts = re.compile('(?i)^([a-z0-9]+(-[a-z0-9]+)*\.)+[a-z]{2,}'+self.word.split('.')[-2])
        self.temp = reg_hosts.findall(self.results)
        smilarhostnames = self.unique()
        return smilarhostnames


    def set(self):
        reg_sets = re.compile('>[a-zA-Z0-9]*</a></font>')
        self.temp = reg_sets.findall(self.results)
        sets = []
        for x in self.temp:
            y = string.replace(x, '>', '')
            y = string.replace(y, '</a</font', '')
            sets.append(y)
        return sets

    def hostnames_all(self):
        reg_hosts = re.compile('<cite>(.*?)</cite>')
        temp = reg_hosts.findall(self.results)
        for x in temp:
            if x.count(':'):
                res = x.split(':')[1].split('/')[2]
            else:
                res = x.split("/")[0]
            self.temp.append(res)
        hostnames = self.unique()
        return hostnames

    def unique(self):
        self.new = []
        for x in self.temp:
            if ".." in x: #remove domain name like "IP...www.domain.com"
                pass
            elif x not in self.new:
                self.new.append(x)
        return self.new
if __name__ == "__main__":
    print("xx")