cpython/Lib/robotparser.py

218 lines
6.8 KiB
Python
Raw Normal View History

""" robotparser.py
Copyright (C) 2000 Bastian Kleineidam
1997-01-29 23:18:23 -04:00
You can choose between two licenses when using this package:
1) GNU GPLv2
2) PSF license for Python 2.2
1997-01-29 23:18:23 -04:00
The robots.txt Exclusion Protocol is implemented as specified in
http://info.webcrawler.com/mak/projects/robots/norobots-rfc.html
1997-01-29 23:18:23 -04:00
"""
import urlparse
import urllib
1997-01-29 23:18:23 -04:00
__all__ = ["RobotFileParser"]
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.default_entry = None
self.disallow_all = False
self.allow_all = False
self.set_url(url)
1998-04-06 11:29:28 -03:00
self.last_checked = 0
1997-01-29 23:18:23 -04:00
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.
"""
1998-04-06 11:29:28 -03:00
return self.last_checked
1997-01-29 23:18:23 -04:00
def modified(self):
"""Sets the time the robots.txt file was last fetched to the
current time.
"""
1998-04-06 11:29:28 -03:00
import time
self.last_checked = time.time()
1997-01-29 23:18:23 -04:00
def set_url(self, url):
"""Sets the URL referring to a robots.txt file."""
1998-04-06 11:29:28 -03:00
self.url = url
self.host, self.path = urlparse.urlparse(url)[1:3]
1997-01-29 23:18:23 -04:00
def read(self):
"""Reads the robots.txt URL and feeds it to the parser."""
opener = URLopener()
f = opener.open(self.url)
lines = [line.strip() for line in f]
f.close()
self.errcode = opener.errcode
if self.errcode in (401, 403):
self.disallow_all = True
elif self.errcode >= 400:
self.allow_all = True
elif self.errcode == 200 and lines:
self.parse(lines)
1997-01-29 23:18:23 -04:00
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)
1997-01-29 23:18:23 -04:00
def parse(self, lines):
"""parse the input lines from a robots.txt file.
2001-01-21 00:49:16 -04:00
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
linenumber = 0
entry = Entry()
2001-01-21 00:49:16 -04:00
1998-04-06 11:29:28 -03:00
for line in lines:
linenumber += 1
if not line:
if state == 1:
entry = Entry()
state = 0
elif state == 2:
self._add_entry(entry)
entry = Entry()
state = 0
1998-04-06 11:29:28 -03:00
# remove optional comment and strip line
2001-02-09 04:40:40 -04:00
i = line.find('#')
if i >= 0:
line = line[:i]
2001-02-09 04:40:40 -04:00
line = line.strip()
1998-04-06 11:29:28 -03:00
if not line:
continue
2001-02-09 04:40:40 -04:00
line = line.split(':', 1)
1998-04-06 11:29:28 -03:00
if len(line) == 2:
2001-02-09 04:40:40 -04:00
line[0] = line[0].strip().lower()
line[1] = urllib.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
if state == 2:
self._add_entry(entry)
1997-01-29 23:18:23 -04:00
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
# 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
1997-01-29 23:18:23 -04:00
def __str__(self):
return ''.join([str(entry) + "\n" for entry in self.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
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.extend(["User-agent: ", agent, "\n"])
for line in self.rulelines:
ret.extend([str(line), "\n"])
return ''.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
class URLopener(urllib.FancyURLopener):
def __init__(self, *args):
2003-02-27 16:14:51 -04:00
urllib.FancyURLopener.__init__(self, *args)
self.errcode = 200
2001-02-15 19:56:39 -04:00
2007-08-28 20:22:52 -03:00
def prompt_user_passwd(self, host, realm):
## If robots.txt file is accessible only with a password,
## we act as if the file wasn't there.
return None, None
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)