robotparser.py :  » Mobile » Python-for-PalmOS » Python-1.5.2+reduced-1.0 » Lib » Python Open Source

Home
Python Open Source
1.3.1.2 Python
2.Ajax
3.Aspect Oriented
4.Blog
5.Build
6.Business Application
7.Chart Report
8.Content Management Systems
9.Cryptographic
10.Database
11.Development
12.Editor
13.Email
14.ERP
15.Game 2D 3D
16.GIS
17.GUI
18.IDE
19.Installer
20.IRC
21.Issue Tracker
22.Language Interface
23.Log
24.Math
25.Media Sound Audio
26.Mobile
27.Network
28.Parser
29.PDF
30.Project Management
31.RSS
32.Search
33.Security
34.Template Engines
35.Test
36.UML
37.USB Serial
38.Web Frameworks
39.Web Server
40.Web Services
41.Web Unit
42.Wiki
43.Windows
44.XML
Python Open Source » Mobile » Python for PalmOS 
Python for PalmOS » Python 1.5.2 reduced 1.0 » Lib » robotparser.py
"""

Robots.txt file parser class.  Accepts a list of lines or robots.txt URL as
input, builds a set of rules from that list, then answers questions about
fetchability of other URLs.

"""

class RobotFileParser:

    def __init__(self):
        self.rules = {}
        self.debug = 0
        self.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
##      import urlmisc
##      self.url = urlmisc.canonical_url(url)

    def read(self):
        import urllib
        self.parse(urllib.urlopen(self.url).readlines())

    def parse(self, lines):
        import regsub, string, regex
        active = []
        for line in lines:
            if self.debug: print '>', line,
            # blank line terminates current record
            if not line[:-1]:
                active = []
                continue
            # remove optional comment and strip line
            line = string.strip(line[:string.find(line, '#')])
            if not line:
                continue
            line = regsub.split(line, ' *: *')
            if len(line) == 2:
                line[0] = string.lower(line[0])
                if line[0] == 'user-agent':
                    # this record applies to this user agent
                    if self.debug: print '>> user-agent:', line[1]
                    active.append(line[1])
                    if not self.rules.has_key(line[1]):
                        self.rules[line[1]] = []
                elif line[0] == 'disallow':
                    if line[1]:
                        if self.debug: print '>> disallow:', line[1]
                        for agent in active:
                            self.rules[agent].append(regex.compile(line[1]))
                    else:
                        pass
                        for agent in active:
                            if self.debug: print '>> allow', agent
                            self.rules[agent] = []
                else:
                    if self.debug: print '>> unknown:', line

        self.modified()

    # returns true if agent is allowed to fetch url
    def can_fetch(self, agent, url):
        import urlparse
        ag = agent
        if not self.rules.has_key(ag): ag = '*'
        if not self.rules.has_key(ag):
            if self.debug: print '>> allowing', url, 'fetch by', agent
            return 1
        path = urlparse.urlparse(url)[2]
        for rule in self.rules[ag]:
            if rule.match(path) != -1:
                if self.debug: print '>> disallowing', url, 'fetch by', agent
                return 0
        if self.debug: print '>> allowing', url, 'fetch by', agent
        return 1

def test():
    rp = RobotFileParser()
    rp.debug = 1
    rp.set_url('http://www.automatrix.com/robots.txt')
    rp.read()
    print rp.rules
    print rp.can_fetch('*', 'http://www.calendar.com/concerts/')
    print rp.can_fetch('Musi-Cal-Robot',
                       'http://dolphin:80/cgi-bin/music-search?performer=Rolling+Stones')

    print rp.can_fetch('Lycos', 'http://www/~skip/volkswagen/')
    print rp.can_fetch('Lycos', 'http://www/~skip/volkswagen/vanagon-list-001')
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.