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
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
|
""" robotparser.py
Copyright (C) 2000 Bastian Kleineidam
You can choose between two licenses when using this package:
1) GNU GPLv2
2) PSF license for Python 2.2
The robots.txt Exclusion Protocol is implemented as specified in
http://info.webcrawler.com/mak/projects/robots/norobots-rfc.html
"""
import re,urlparse,urllib
__all__ = ["RobotFileParser"]
debug = 0
def _debug(msg):
if debug: print msg
class RobotFileParser:
def __init__(self, url=''):
self.entries = []
self.default_entry = None
self.disallow_all = 0
self.allow_all = 0
self.set_url(url)
self.last_checked = 0
def mtime(self):
return self.last_checked
def modified(self):
import time
self.last_checked = time.time()
def set_url(self, url):
self.url = url
self.host, self.path = urlparse.urlparse(url)[1:3]
def read(self):
opener = URLopener()
f = opener.open(self.url)
lines = []
line = f.readline()
while line:
lines.append(line.strip())
line = f.readline()
self.errcode = opener.errcode
if self.errcode == 401 or self.errcode == 403:
self.disallow_all = 1
_debug("disallow all")
elif self.errcode >= 400:
self.allow_all = 1
_debug("allow all")
elif self.errcode == 200 and lines:
_debug("parse lines")
self.parse(lines)
def _add_entry(self, entry):
if "*" in entry.useragents:
# the default entry is considered last
self.default_entry = entry
else:
self.entries.append(entry)
def parse(self, lines):
"""parse the input lines from a robot.txt file.
We allow that a user-agent: line is not preceded by
one or more blank lines."""
state = 0
linenumber = 0
entry = Entry()
for line in lines:
linenumber = linenumber + 1
if not line:
if state==1:
_debug("line %d: warning: you should insert"
" allow: or disallow: directives below any"
" user-agent: line" % linenumber)
entry = Entry()
state = 0
elif state==2:
self._add_entry(entry)
entry = Entry()
state = 0
# remove optional comment and strip line
i = line.find('#')
if i>=0:
line = line[:i]
line = line.strip()
if not line:
continue
line = line.split(':', 1)
if len(line) == 2:
line[0] = line[0].strip().lower()
line[1] = urllib.unquote(line[1].strip())
if line[0] == "user-agent":
if state==2:
_debug("line %d: warning: you should insert a blank"
" line before any user-agent"
" directive" % linenumber)
self._add_entry(entry)
entry = Entry()
entry.useragents.append(line[1])
state = 1
elif line[0] == "disallow":
if state==0:
_debug("line %d: error: you must insert a user-agent:"
" directive before this line" % linenumber)
else:
entry.rulelines.append(RuleLine(line[1], 0))
state = 2
elif line[0] == "allow":
if state==0:
_debug("line %d: error: you must insert a user-agent:"
" directive before this line" % linenumber)
else:
entry.rulelines.append(RuleLine(line[1], 1))
else:
_debug("line %d: warning: unknown key %s" % (linenumber,
line[0]))
else:
_debug("line %d: error: malformed line %s"%(linenumber, line))
if state==2:
self.entries.append(entry)
_debug("Parsed rules:\n%s" % str(self))
def can_fetch(self, useragent, url):
"""using the parsed robots.txt decide if useragent can fetch url"""
_debug("Checking robot.txt allowance for:\n user agent: %s\n url: %s" %
(useragent, url))
if self.disallow_all:
return False
if self.allow_all:
return True
# search for given user agent matches
# the first match counts
url = urllib.quote(urlparse.urlparse(urllib.unquote(url))[2]) or "/"
for entry in self.entries:
if entry.applies_to(useragent):
return entry.allowance(url)
# try the default entry last
if self.default_entry:
return self.default_entry.allowance(url)
# agent not found ==> access granted
return True
def __str__(self):
ret = ""
for entry in self.entries:
ret = ret + str(entry) + "\n"
return ret
class RuleLine:
"""A rule line is a single "Allow:" (allowance==1) or "Disallow:"
(allowance==0) followed by a path."""
def __init__(self, path, allowance):
if path == '' and not allowance:
# an empty value means allow all
allowance = 1
self.path = urllib.quote(path)
self.allowance = allowance
def applies_to(self, filename):
return self.path=="*" or filename.startswith(self.path)
def __str__(self):
return (self.allowance and "Allow" or "Disallow")+": "+self.path
class Entry:
"""An entry has one or more user-agents and zero or more rulelines"""
def __init__(self):
self.useragents = []
self.rulelines = []
def __str__(self):
ret = ""
for agent in self.useragents:
ret = ret + "User-agent: "+agent+"\n"
for line in self.rulelines:
ret = ret + str(line) + "\n"
return ret
def applies_to(self, useragent):
"""check if this entry applies to the specified agent"""
# split the name token and make it lower case
useragent = useragent.split("/")[0].lower()
for agent in self.useragents:
if agent=='*':
# we have the catch-all agent
return True
agent = agent.lower()
if useragent.find(agent) != -1:
return True
return False
def allowance(self, filename):
"""Preconditions:
- our agent applies to this entry
- filename is URL decoded"""
for line in self.rulelines:
_debug((filename, str(line), line.allowance))
if line.applies_to(filename):
return line.allowance
return 1
class URLopener(urllib.FancyURLopener):
def __init__(self, *args):
apply(urllib.FancyURLopener.__init__, (self,) + args)
self.errcode = 200
def http_error_default(self, url, fp, errcode, errmsg, headers):
self.errcode = errcode
return urllib.FancyURLopener.http_error_default(self, url, fp, errcode,
errmsg, headers)
def _check(a,b):
if not b:
ac = "access denied"
else:
ac = "access allowed"
if a!=b:
print "failed"
else:
print "ok (%s)" % ac
print
def _test():
global debug
rp = RobotFileParser()
debug = 1
# robots.txt that exists, gotten to by redirection
rp.set_url('http://www.musi-cal.com/robots.txt')
rp.read()
# test for re.escape
_check(rp.can_fetch('*', 'http://www.musi-cal.com/'), 1)
# this should match the first rule, which is a disallow
_check(rp.can_fetch('', 'http://www.musi-cal.com/'), 0)
# various cherry pickers
_check(rp.can_fetch('CherryPickerSE',
'http://www.musi-cal.com/cgi-bin/event-search'
'?city=San+Francisco'), 0)
_check(rp.can_fetch('CherryPickerSE/1.0',
'http://www.musi-cal.com/cgi-bin/event-search'
'?city=San+Francisco'), 0)
_check(rp.can_fetch('CherryPickerSE/1.5',
'http://www.musi-cal.com/cgi-bin/event-search'
'?city=San+Francisco'), 0)
# case sensitivity
_check(rp.can_fetch('ExtractorPro', 'http://www.musi-cal.com/blubba'), 0)
_check(rp.can_fetch('extractorpro', 'http://www.musi-cal.com/blubba'), 0)
# substring test
_check(rp.can_fetch('toolpak/1.1', 'http://www.musi-cal.com/blubba'), 0)
# tests for catch-all * agent
_check(rp.can_fetch('spam', 'http://www.musi-cal.com/search'), 0)
_check(rp.can_fetch('spam', 'http://www.musi-cal.com/Musician/me'), 1)
_check(rp.can_fetch('spam', 'http://www.musi-cal.com/'), 1)
_check(rp.can_fetch('spam', 'http://www.musi-cal.com/'), 1)
# robots.txt that does not exist
rp.set_url('http://www.lycos.com/robots.txt')
rp.read()
_check(rp.can_fetch('Mozilla', 'http://www.lycos.com/search'), 1)
if __name__ == '__main__':
_test()
|
