[issue28756] robotfileparser always uses default Python user-agent

[John Nagle]

John Nagle added the comment:

Suggest adding a user_agent optional parameter, as shown here:

    def __init__(self, url='', user_agent=None):
        urllib.robotparser.RobotFileParser.__init__(self, url)  # init parent
        self.user_agent = user_agent                    # save user agent
         
    def read(self):
        """
        Reads the robots.txt URL and feeds it to the parser.
        Overrides parent read function.
        """
        try:
            req = urllib.request.Request(               # request with user agent specified
                self.url, 
                data=None)
            if self.user_agent is not None :            # if overriding user agent
                req.add_header("User-Agent", self.user_agent)
            f = urllib.request.urlopen(req)             # open connection
        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())

----------

_______________________________________
Python tracker <report at bugs.python.org>
<http://bugs.python.org/issue28756>
_______________________________________