If you need to process HTTP responses in a streaming manner, there are several options.
You can do this via downloadPage:
from xml.sax import make_parser
from twisted.web.client import downloadPage
class StreamingXMLParser:
def __init__(self):
self._parser = make_parser()
def write(self, bytes):
self._parser.feed(bytes)
def close(self):
self._parser.feed('', True)
parser = StreamingXMLParser()
d = downloadPage(url, parser)
, downloadPage - , . write close , XML, .
HTTPPageGetter. HTTPPageGetter - , getPage.
class StreamingXMLParsingHTTPClient(HTTPPageGetter):
def connectionMade(self):
HTTPPageGetter.connectionMade(self)
self._parser = make_parser()
def handleResponsePart(self, bytes):
self._parser.feed(bytes)
def handleResponseEnd(self):
self._parser.feed('', True)
self.handleResponse(None)
factory = HTTPClientFactory(url)
factory.protocol = StreamingXMLParsingHTTPClient
reactor.connectTCP(host, port, factory)
d = factory.deferred
, API- HTTP. - , , , , , , .:) API . , - :
class StreamingXMLParser(Protocol):
def __init__(self):
self.done = Deferred()
def connectionMade(self):
self._parser = make_parser()
def dataReceived(self, bytes):
self._parser.feed(bytes)
def connectionLost(self, reason):
self._parser.feed('', True)
self.done.callback(None)
from twisted.web.client import Agent
from twisted.internet import reactor
agent = Agent(reactor)
d = agent.request('GET', url, headers, None)
def cbRequest(response):
protocol = StreamingXMLParser()
response.deliverBody(protocol)
return protocol.done
d.addCallback(cbRequest)