使用 twistedmatrix 时如何压缩和处理响应部分ProxyClient
?
我需要检查文本或 javascript 和 ajax 查询/答案。我应该使用handleResponseEnd
吗?
我认为它在 handleResponsePart 内部,但看起来我误解了一点或什么,这是我的骨架代码:
from twisted.python import log
from twisted.web import http, proxy
class ProxyClient(proxy.ProxyClient):
"""Mange returned header, content here.
Use `self.father` methods to modify request directly.
"""
def handleHeader(self, key, value):
# change response header here
log.msg("Header: %s: %s" % (key, value))
proxy.ProxyClient.handleHeader(self, key, value)
def handleResponsePart(self, buffer):
# this part below do not work,
# looks like @ this moment i do not have 'Content-Encoding' or 'Content-Type'
# what am i misunderstading?
cEncoding = self.father.getAllHeaders().get('Content-Encoding', '')
cType = self.father.getAllHeaders().get('Content-Type', '')
print >> sys.stderr, 'Content-Encoding', cEncoding
print >> sys.stderr, 'Content-Type', cType
if ('text' in cType.lower() or 'javascript' in cType.lower()) and 'gzip' in cEncoding.lower():
buf = StringIO(buffer)
s = gzip.GzipFile(mode="rb", fileobj=buf)
content = s.read(len(buffer))
# here process content as it should be gunziped
proxy.ProxyClient.handleResponsePart(self, buffer)
class ProxyClientFactory(proxy.ProxyClientFactory):
protocol = ProxyClient
class ProxyRequest(proxy.ProxyRequest):
protocols = dict(http=ProxyClientFactory)
class Proxy(proxy.Proxy):
requestFactory = ProxyRequest
class ProxyFactory(http.HTTPFactory):
protocol = Proxy
从我的日志中我有:
2013-06-11 14:07:33+0200 [ProxyClient,client] Header: Date: Tue, 11 Jun 2013 12:07:25 GMT
2013-06-11 14:07:33+0200 [ProxyClient,client] Header: Server: Apache
...
2013-06-11 14:07:33+0200 [ProxyClient,client] Header: Content-Type: text/html;charset=ISO-8859-1
...
2013-06-11 14:07:33+0200 [ProxyClient,client] Header: Content-Encoding: gzip
...
2013-06-11 14:07:33+0200 [ProxyClient,client] Header: Connection: close
因此我应该满足这两个条件!请问我错过了什么?
即使我对第二种方式不感兴趣,也就是删除对请求的接受,像这样,是否可以这样做:(顺便说一句,它看起来不起作用或者测试的网络服务器不关心事实上我们不想接收 gzip 格式的内容)
class ProxyRequest(proxy.ProxyRequest):
protocols = dict(http=ProxyClientFactory)
def process(self):
# removing the accept so that we do not tell "i'm ok with gzip encoded content" and should receive only not gzip-ed
self.requestHeaders.removeHeader('accept')
self.requestHeaders.removeHeader('accept-encoding')