httplib.py

来自「mallet是自然语言处理、机器学习领域的一个开源项目。」· Python 代码 · 共 1,235 行 · 第 1/3 页

        SharedSocketClient.__init__(self, sock)
        self._ssl = ssl
        self._buf = ''
        self._bufsize = bufsize or self.__class__.BUFSIZE

    def _read(self):
        buf = ''
        # put in a loop so that we retry on transient errors
        while 1:
            try:
                buf = self._ssl.read(self._bufsize)
            except socket.sslerror, err:
                if (err[0] == socket.SSL_ERROR_WANT_READ
                    or err[0] == socket.SSL_ERROR_WANT_WRITE):
                    continue
                if (err[0] == socket.SSL_ERROR_ZERO_RETURN
                    or err[0] == socket.SSL_ERROR_EOF):
                    break
                raise
            except socket.error, err:
                if err[0] == errno.EINTR:
                    continue
                if err[0] == errno.EBADF:
                    # XXX socket was closed?
                    break
                raise
            else:
                break
        return buf

    def read(self, size=None):
        L = [self._buf]
        avail = len(self._buf)
        while size is None or avail < size:
            s = self._read()
            if s == '':
                break
            L.append(s)
            avail += len(s)
        all = "".join(L)
        if size is None:
            self._buf = ''
            return all
        else:
            self._buf = all[size:]
            return all[:size]

    def readline(self):
        L = [self._buf]
        self._buf = ''
        while 1:
            i = L[-1].find("\n")
            if i >= 0:
                break
            s = self._read()
            if s == '':
                break
            L.append(s)
        if i == -1:
            # loop exited because there is no more data
            return "".join(L)
        else:
            all = "".join(L)
            # XXX could do enough bookkeeping not to do a 2nd search
            i = all.find("\n") + 1
            line = all[:i]
            self._buf = all[i:]
            return line

class FakeSocket(SharedSocketClient):

    class _closedsocket:
        def __getattr__(self, name):
            raise error(9, 'Bad file descriptor')

    def __init__(self, sock, ssl):
        sock = SharedSocket(sock)
        SharedSocketClient.__init__(self, sock)
        self._ssl = ssl

    def close(self):
        SharedSocketClient.close(self)
        self._sock = self.__class__._closedsocket()

    def makefile(self, mode, bufsize=None):
        if mode != 'r' and mode != 'rb':
            raise UnimplementedFileMode()
        return SSLFile(self._shared, self._ssl, bufsize)

    def send(self, stuff, flags = 0):
        return self._ssl.write(stuff)

    sendall = send

    def recv(self, len = 1024, flags = 0):
        return self._ssl.read(len)

    def __getattr__(self, attr):
        return getattr(self._sock, attr)


class HTTPSConnection(HTTPConnection):
    "This class allows communication via SSL."

    default_port = HTTPS_PORT

    def __init__(self, host, port=None, key_file=None, cert_file=None,
                 strict=None):
        HTTPConnection.__init__(self, host, port, strict)
        self.key_file = key_file
        self.cert_file = cert_file

    def connect(self):
        "Connect to a host on a given (SSL) port."

        sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        sock.connect((self.host, self.port))
        realsock = sock
        if hasattr(sock, "_sock"):
            realsock = sock._sock
        ssl = socket.ssl(realsock, self.key_file, self.cert_file)
        self.sock = FakeSocket(sock, ssl)


class HTTP:
    "Compatibility class with httplib.py from 1.5."

    _http_vsn = 10
    _http_vsn_str = 'HTTP/1.0'

    debuglevel = 0

    _connection_class = HTTPConnection

    def __init__(self, host='', port=None, strict=None):
        "Provide a default host, since the superclass requires one."

        # some joker passed 0 explicitly, meaning default port
        if port == 0:
            port = None

        # Note that we may pass an empty string as the host; this will throw
        # an error when we attempt to connect. Presumably, the client code
        # will call connect before then, with a proper host.
        self._setup(self._connection_class(host, port, strict))

    def _setup(self, conn):
        self._conn = conn

        # set up delegation to flesh out interface
        self.send = conn.send
        self.putrequest = conn.putrequest
        self.endheaders = conn.endheaders
        self.set_debuglevel = conn.set_debuglevel

        conn._http_vsn = self._http_vsn
        conn._http_vsn_str = self._http_vsn_str

        self.file = None

    def connect(self, host=None, port=None):
        "Accept arguments to set the host/port, since the superclass doesn't."

        if host is not None:
            self._conn._set_hostport(host, port)
        self._conn.connect()

    def getfile(self):
        "Provide a getfile, since the superclass' does not use this concept."
        return self.file

    def putheader(self, header, *values):
        "The superclass allows only one value argument."
        self._conn.putheader(header, '\r\n\t'.join(values))

    def getreply(self):
        """Compat definition since superclass does not define it.

        Returns a tuple consisting of:
        - server status code (e.g. '200' if all goes well)
        - server "reason" corresponding to status code
        - any RFC822 headers in the response from the server
        """
        try:
            response = self._conn.getresponse()
        except BadStatusLine, e:
            ### hmm. if getresponse() ever closes the socket on a bad request,
            ### then we are going to have problems with self.sock

            ### should we keep this behavior? do people use it?
            # keep the socket open (as a file), and return it
            self.file = self._conn.sock.makefile('rb', 0)

            # close our socket -- we want to restart after any protocol error
            self.close()

            self.headers = None
            return -1, e.line, None

        self.headers = response.msg
        self.file = response.fp
        return response.status, response.reason, response.msg

    def close(self):
        self._conn.close()

        # note that self.file == response.fp, which gets closed by the
        # superclass. just clear the object ref here.
        ### hmm. messy. if status==-1, then self.file is owned by us.
        ### well... we aren't explicitly closing, but losing this ref will
        ### do it
        self.file = None

if hasattr(socket, 'ssl'):
    class HTTPS(HTTP):
        """Compatibility with 1.5 httplib interface

        Python 1.5.2 did not have an HTTPS class, but it defined an
        interface for sending http requests that is also useful for
        https.
        """

        _connection_class = HTTPSConnection

        def __init__(self, host='', port=None, key_file=None, cert_file=None,
                     strict=None):
            # provide a default host, pass the X509 cert info

            # urf. compensate for bad input.
            if port == 0:
                port = None
            self._setup(self._connection_class(host, port, key_file,
                                               cert_file, strict))

            # we never actually use these for anything, but we keep them
            # here for compatibility with post-1.5.2 CVS.
            self.key_file = key_file
            self.cert_file = cert_file


class HTTPException(Exception):
    # Subclasses that define an __init__ must call Exception.__init__
    # or define self.args.  Otherwise, str() will fail.
    pass

class NotConnected(HTTPException):
    pass

class InvalidURL(HTTPException):
    pass

class UnknownProtocol(HTTPException):
    def __init__(self, version):
        self.args = version,
        self.version = version

class UnknownTransferEncoding(HTTPException):
    pass

class UnimplementedFileMode(HTTPException):
    pass

class IncompleteRead(HTTPException):
    def __init__(self, partial):
        self.args = partial,
        self.partial = partial

class ImproperConnectionState(HTTPException):
    pass

class CannotSendRequest(ImproperConnectionState):
    pass

class CannotSendHeader(ImproperConnectionState):
    pass

class ResponseNotReady(ImproperConnectionState):
    pass

class BadStatusLine(HTTPException):
    def __init__(self, line):
        self.args = line,
        self.line = line

# for backwards compatibility
error = HTTPException

class LineAndFileWrapper:
    """A limited file-like object for HTTP/0.9 responses."""

    # The status-line parsing code calls readline(), which normally
    # get the HTTP status line.  For a 0.9 response, however, this is
    # actually the first line of the body!  Clients need to get a
    # readable file object that contains that line.

    def __init__(self, line, file):
        self._line = line
        self._file = file
        self._line_consumed = 0
        self._line_offset = 0
        self._line_left = len(line)

    def __getattr__(self, attr):
        return getattr(self._file, attr)

    def _done(self):
        # called when the last byte is read from the line.  After the
        # call, all read methods are delegated to the underlying file
        # obhect.
        self._line_consumed = 1
        self.read = self._file.read
        self.readline = self._file.readline
        self.readlines = self._file.readlines

    def read(self, amt=None):
        assert not self._line_consumed and self._line_left
        if amt is None or amt > self._line_left:
            s = self._line[self._line_offset:]
            self._done()
            if amt is None:
                return s + self._file.read()
            else:
                return s + self._file.read(amt - len(s))
        else:
            assert amt <= self._line_left
            i = self._line_offset
            j = i + amt
            s = self._line[i:j]
            self._line_offset = j
            self._line_left -= amt
            if self._line_left == 0:
                self._done()
            return s

    def readline(self):
        s = self._line[self._line_offset:]
        self._done()
        return s

    def readlines(self, size=None):
        L = [self._line[self._line_offset:]]
        self._done()
        if size is None:
            return L + self._file.readlines()
        else:
            return L + self._file.readlines(size)

def test():
    """Test this module.

    A hodge podge of tests collected here, because they have too many
    external dependencies for the regular test suite.
    """

    import sys
    import getopt
    opts, args = getopt.getopt(sys.argv[1:], 'd')
    dl = 0
    for o, a in opts:
        if o == '-d': dl = dl + 1
    host = 'www.python.org'
    selector = '/'
    if args[0:]: host = args[0]
    if args[1:]: selector = args[1]
    h = HTTP()
    h.set_debuglevel(dl)
    h.connect(host)
    h.putrequest('GET', selector)
    h.endheaders()
    status, reason, headers = h.getreply()
    print 'status =', status
    print 'reason =', reason
    print "read", len(h.getfile().read())
    print
    if headers:
        for header in headers.headers: print header.strip()
    print

    # minimal test that code to extract host from url works
    class HTTP11(HTTP):
        _http_vsn = 11
        _http_vsn_str = 'HTTP/1.1'

    h = HTTP11('www.python.org')
    h.putrequest('GET', 'http://www.python.org/~jeremy/')
    h.endheaders()
    h.getreply()
    h.close()

    if hasattr(socket, 'ssl'):

        for host, selector in (('sourceforge.net', '/projects/python'),
                               ):
            print "https://%s%s" % (host, selector)
            hs = HTTPS()
            hs.set_debuglevel(dl)
            hs.connect(host)
            hs.putrequest('GET', selector)
            hs.endheaders()
            status, reason, headers = hs.getreply()
            print 'status =', status
            print 'reason =', reason
            print "read", len(hs.getfile().read())
            print
            if headers:
                for header in headers.headers: print header.strip()
            print

if __name__ == '__main__':
    test()