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
|
""" 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://www.robotstxt.org/norobots-rfc.txt
"""
import collections
import urllib.parse
import urllib.request
__all__ = ["RobotFileParser"]
RequestRate = collections.namedtuple("RequestRate", "requests seconds")
class RobotFileParser:
""" This class provides a set of methods to read, parse and answer
questions about a single robots.txt file.
"""
def __init__(self, url=''):
self.entries = []
self.sitemaps = []
self.default_entry = None
self.disallow_all = False
self.allow_all = False
self.set_url(url)
self.last_checked = 0
def mtime(self):
"""Returns the time the robots.txt file was last fetched.
This is useful for long-running web spiders that need to
check for new robots.txt files periodically.
"""
return self.last_checked
def modified(self):
"""Sets the time the robots.txt file was last fetched to the
current time.
"""
import time
self.last_checked = time.time()
def set_url(self, url):
"""Sets the URL referring to a robots.txt file."""
self.url = url
self.host, self.path = urllib.parse.urlparse(url)[1:3]
def read(self):
"""Reads the robots.txt URL and feeds it to the parser."""
try:
f = urllib.request.urlopen(self.url)
except urllib.error.HTTPError as err:
if err.code in (401, 403):
self.disallow_all = True
elif err.code >= 400 and err.code < 500:
self.allow_all = True
else:
raw = f.read()
self.parse(raw.decode("utf-8").splitlines())
def _add_entry(self, entry):
if "*" in entry.useragents:
# the default entry is considered last
if self.default_entry is None:
# the first default entry wins
self.default_entry = entry
else:
self.entries.append(entry)
def parse(self, lines):
"""Parse the input lines from a robots.txt file.
We allow that a user-agent: line is not preceded by
one or more blank lines.
"""
# states:
# 0: start state
# 1: saw user-agent line
# 2: saw an allow or disallow line
state = 0
entry = Entry()
self.modified()
for line in lines:
if not line:
if state == 1:
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.parse.unquote(line[1].strip())
if line[0] == "user-agent":
if state == 2:
self._add_entry(entry)
entry = Entry()
entry.useragents.append(line[1])
state = 1
elif line[0] == "disallow":
if state != 0:
entry.rulelines.append(RuleLine(line[1], False))
state = 2
elif line[0] == "allow":
if state != 0:
entry.rulelines.append(RuleLine(line[1], True))
state = 2
elif line[0] == "crawl-delay":
if state != 0:
# before trying to convert to int we need to make
# sure that robots.txt has valid syntax otherwise
# it will crash
if line[1].strip().isdigit():
entry.delay = int(line[1])
state = 2
elif line[0] == "request-rate":
if state != 0:
numbers = line[1].split('/')
# check if all values are sane
if (len(numbers) == 2 and numbers[0].strip().isdigit()
and numbers[1].strip().isdigit()):
entry.req_rate = RequestRate(int(numbers[0]), int(numbers[1]))
state = 2
elif line[0] == "sitemap":
# According to http://www.sitemaps.org/protocol.html
# "This directive is independent of the user-agent line,
# so it doesn't matter where you place it in your file."
# Therefore we do not change the state of the parser.
self.sitemaps.append(line[1])
if state == 2:
self._add_entry(entry)
def can_fetch(self, useragent, url):
"""using the parsed robots.txt decide if useragent can fetch url"""
if self.disallow_all:
return False
if self.allow_all:
return True
# Until the robots.txt file has been read or found not
# to exist, we must assume that no url is allowable.
# This prevents false positives when a user erroneously
# calls can_fetch() before calling read().
if not self.last_checked:
return False
# search for given user agent matches
# the first match counts
parsed_url = urllib.parse.urlparse(urllib.parse.unquote(url))
url = urllib.parse.urlunparse(('','',parsed_url.path,
parsed_url.params,parsed_url.query, parsed_url.fragment))
url = urllib.parse.quote(url)
if not url:
url = "/"
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 crawl_delay(self, useragent):
if not self.mtime():
return None
for entry in self.entries:
if entry.applies_to(useragent):
return entry.delay
return self.default_entry.delay
def request_rate(self, useragent):
if not self.mtime():
return None
for entry in self.entries:
if entry.applies_to(useragent):
return entry.req_rate
return self.default_entry.req_rate
def site_maps(self):
if not self.sitemaps:
return None
return self.sitemaps
def __str__(self):
entries = self.entries
if self.default_entry is not None:
entries = entries + [self.default_entry]
return '\n\n'.join(map(str, entries))
class RuleLine:
"""A rule line is a single "Allow:" (allowance==True) or "Disallow:"
(allowance==False) followed by a path."""
def __init__(self, path, allowance):
if path == '' and not allowance:
# an empty value means allow all
allowance = True
path = urllib.parse.urlunparse(urllib.parse.urlparse(path))
self.path = urllib.parse.quote(path)
self.allowance = allowance
def applies_to(self, filename):
return self.path == "*" or filename.startswith(self.path)
def __str__(self):
return ("Allow" if self.allowance else "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 = []
self.delay = None
self.req_rate = None
def __str__(self):
ret = []
for agent in self.useragents:
ret.append(f"User-agent: {agent}")
if self.delay is not None:
ret.append(f"Crawl-delay: {self.delay}")
if self.req_rate is not None:
rate = self.req_rate
ret.append(f"Request-rate: {rate.requests}/{rate.seconds}")
ret.extend(map(str, self.rulelines))
return '\n'.join(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 agent in useragent:
return True
return False
def allowance(self, filename):
"""Preconditions:
- our agent applies to this entry
- filename is URL decoded"""
for line in self.rulelines:
if line.applies_to(filename):
return line.allowance
return True
|
