robotparser.py 文件源码

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
        parsed_url = urlparse.urlparse(urllib.unquote(url))
        url = urlparse.urlunparse(('', '', parsed_url.path,
            parsed_url.params, parsed_url.query, parsed_url.fragment))
        url = urllib.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