forked from c00w/bitHopper
/
client.py
862 lines (698 loc) · 29.3 KB
/
client.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
# -*- test-case-name: twisted.web.test.test_webclient -*-
# Copyright (c) 2001-2010 Twisted Matrix Laboratories.
# See LICENSE for details.
"""
HTTP client.
"""
import os, types
from urlparse import urlunparse
from twisted.python import log
from twisted.web import http
from twisted.internet import defer, protocol, reactor
from twisted.python import failure
from twisted.python.util import InsensitiveDict
from twisted.web import error
from twisted.web.http_headers import Headers
from twisted.python.compat import set
class PartialDownloadError(error.Error):
"""
Page was only partially downloaded, we got disconnected in middle.
@ivar response: All of the response body which was downloaded.
"""
class HTTPPageGetter(http.HTTPClient):
"""
Gets a resource via HTTP, then quits.
Typically used with L{HTTPClientFactory}. Note that this class does not, by
itself, do anything with the response. If you want to download a resource
into a file, use L{HTTPPageDownloader} instead.
"""
quietLoss = 0
followRedirect = True
failed = 0
_specialHeaders = set(('host', 'user-agent', 'cookie', 'content-length'))
def connectionMade(self):
method = getattr(self.factory, 'method', 'GET')
self.sendCommand(method, self.factory.path)
self.sendHeader('Host', self.factory.headers.get("host", self.factory.host))
self.sendHeader('User-Agent', self.factory.agent)
data = getattr(self.factory, 'postdata', None)
if data is not None:
self.sendHeader("Content-Length", str(len(data)))
cookieData = []
for (key, value) in self.factory.headers.items():
if key.lower() not in self._specialHeaders:
# we calculated it on our own
self.sendHeader(key, value)
if key.lower() == 'cookie':
cookieData.append(value)
for cookie, cookval in self.factory.cookies.items():
cookieData.append('%s=%s' % (cookie, cookval))
if cookieData:
self.sendHeader('Cookie', '; '.join(cookieData))
self.endHeaders()
self.headers = {}
if data is not None:
self.transport.write(data)
def handleHeader(self, key, value):
"""
Called every time a header is received. Stores the header information
as key-value pairs in the C{headers} attribute.
@type key: C{str}
@param key: An HTTP header field name.
@type value: C{str}
@param value: An HTTP header field value.
"""
key = key.lower()
l = self.headers.setdefault(key, [])
l.append(value)
def handleStatus(self, version, status, message):
self.version, self.status, self.message = version, status, message
self.factory.gotStatus(version, status, message)
def handleEndHeaders(self):
self.factory.gotHeaders(self.headers)
m = getattr(self, 'handleStatus_'+self.status, self.handleStatusDefault)
m()
def handleStatus_200(self):
pass
handleStatus_201 = lambda self: self.handleStatus_200()
handleStatus_202 = lambda self: self.handleStatus_200()
def handleStatusDefault(self):
self.failed = 1
def handleStatus_301(self):
l = self.headers.get('location')
if not l:
self.handleStatusDefault()
return
url = l[0]
if self.followRedirect:
# TODO: None of those variables get used.. is this function even required?
scheme, host, port, path = \
_parse(url, defaultPort=self.transport.getPeer().port)
self.factory._redirectCount += 1
if self.factory._redirectCount >= self.factory.redirectLimit:
err = error.InfiniteRedirection(
self.status,
'Infinite redirection detected',
location=url)
self.factory.noPage(failure.Failure(err))
self.quietLoss = True
self.transport.loseConnection()
return
self.factory.setURL(url)
if self.factory.scheme == 'https':
from twisted.internet import ssl
contextFactory = ssl.ClientContextFactory()
reactor.connectSSL(self.factory.host, self.factory.port,
self.factory, contextFactory)
else:
reactor.connectTCP(self.factory.host, self.factory.port,
self.factory)
else:
self.handleStatusDefault()
self.factory.noPage(
failure.Failure(
error.PageRedirect(
self.status, self.message, location = url)))
self.quietLoss = True
self.transport.loseConnection()
def handleStatus_302(self):
if self.afterFoundGet:
self.handleStatus_303()
self.handleStatus_301()
def handleStatus_303(self):
self.factory.method = 'GET'
self.handleStatus_301()
def connectionLost(self, reason):
if not self.quietLoss:
http.HTTPClient.connectionLost(self, reason)
self.factory.noPage(reason)
def handleResponse(self, response):
if self.quietLoss:
return
if self.failed:
self.factory.noPage(
failure.Failure(
error.Error(
self.status, self.message, response)))
if self.factory.method == 'HEAD':
# Callback with empty string, since there is never a response
# body for HEAD requests.
self.factory.page('')
elif self.length != None and self.length != 0:
self.factory.noPage(failure.Failure(
PartialDownloadError(self.status, self.message, response)))
else:
self.factory.page(response)
# server might be stupid and not close connection. admittedly
# the fact we do only one request per connection is also
# stupid...
self.transport.loseConnection()
def timeout(self):
self.quietLoss = True
self.transport.loseConnection()
self.factory.noPage(defer.TimeoutError("Getting %s took longer than %s seconds." % (self.factory.url, self.factory.timeout)))
class HTTPPageDownloader(HTTPPageGetter):
transmittingPage = 0
def handleStatus_200(self, partialContent=0):
HTTPPageGetter.handleStatus_200(self)
self.transmittingPage = 1
self.factory.pageStart(partialContent)
def handleStatus_206(self):
self.handleStatus_200(partialContent=1)
def handleResponsePart(self, data):
if self.transmittingPage:
self.factory.pagePart(data)
def handleResponseEnd(self):
if self.length:
self.transmittingPage = 0
self.factory.noPage(
failure.Failure(
PartialDownloadError(self.status)))
if self.transmittingPage:
self.factory.pageEnd()
self.transmittingPage = 0
if self.failed:
self.factory.noPage(
failure.Failure(
error.Error(
self.status, self.message, None)))
self.transport.loseConnection()
class HTTPClientFactory(protocol.ClientFactory):
"""Download a given URL.
@type deferred: Deferred
@ivar deferred: A Deferred that will fire when the content has
been retrieved. Once this is fired, the ivars `status', `version',
and `message' will be set.
@type status: str
@ivar status: The status of the response.
@type version: str
@ivar version: The version of the response.
@type message: str
@ivar message: The text message returned with the status.
@type response_headers: dict
@ivar response_headers: The headers that were specified in the
response from the server.
@type method: str
@ivar method: The HTTP method to use in the request. This should be one of
OPTIONS, GET, HEAD, POST, PUT, DELETE, TRACE, or CONNECT (case
matters). Other values may be specified if the server being contacted
supports them.
@type redirectLimit: int
@ivar redirectLimit: The maximum number of HTTP redirects that can occur
before it is assumed that the redirection is endless.
@type afterFoundGet: C{bool}
@ivar afterFoundGet: Deviate from the HTTP 1.1 RFC by handling redirects
the same way as most web browsers; if the request method is POST and a
302 status is encountered, the redirect is followed with a GET method
@type _redirectCount: int
@ivar _redirectCount: The current number of HTTP redirects encountered.
"""
protocol = HTTPPageGetter
url = None
scheme = None
host = ''
port = None
path = None
def __init__(self, url, method='GET', postdata=None, headers=None,
agent="Twisted PageGetter", timeout=0, cookies=None,
followRedirect=True, redirectLimit=20,
afterFoundGet=False):
self.followRedirect = followRedirect
self.redirectLimit = redirectLimit
self._redirectCount = 0
self.timeout = timeout
self.agent = agent
self.afterFoundGet = afterFoundGet
if cookies is None:
cookies = {}
self.cookies = cookies
if headers is not None:
self.headers = InsensitiveDict(headers)
else:
self.headers = InsensitiveDict()
if postdata is not None:
self.headers.setdefault('Content-Length', len(postdata))
# just in case a broken http/1.1 decides to keep connection alive
self.headers.setdefault("connection", "close")
self.postdata = postdata
self.method = method
self.setURL(url)
self.waiting = 1
self.deferred = defer.Deferred()
self.response_headers = None
def __repr__(self):
return "<%s: %s>" % (self.__class__.__name__, self.url)
def setURL(self, url):
self.url = url
scheme, host, port, path = _parse(url)
if scheme and host:
self.scheme = scheme
self.host = host
self.port = port
self.path = path
def buildProtocol(self, addr):
p = protocol.ClientFactory.buildProtocol(self, addr)
p.followRedirect = self.followRedirect
p.afterFoundGet = self.afterFoundGet
if self.timeout:
timeoutCall = reactor.callLater(self.timeout, p.timeout)
self.deferred.addBoth(self._cancelTimeout, timeoutCall)
return p
def _cancelTimeout(self, result, timeoutCall):
if timeoutCall.active():
timeoutCall.cancel()
return result
def gotHeaders(self, headers):
self.response_headers = headers
if headers.has_key('set-cookie'):
for cookie in headers['set-cookie']:
cookparts = cookie.split(';')
cook = cookparts[0]
cook.lstrip()
k, v = cook.split('=', 1)
self.cookies[k.lstrip()] = v.lstrip()
def gotStatus(self, version, status, message):
self.version, self.status, self.message = version, status, message
def page(self, page):
if self.waiting:
self.waiting = 0
self.deferred.callback(page)
def noPage(self, reason):
if self.waiting:
self.waiting = 0
self.deferred.errback(reason)
def clientConnectionFailed(self, _, reason):
if self.waiting:
self.waiting = 0
self.deferred.errback(reason)
class HTTPDownloader(HTTPClientFactory):
"""Download to a file."""
protocol = HTTPPageDownloader
value = None
def __init__(self, url, fileOrName,
method='GET', postdata=None, headers=None,
agent="Twisted client", supportPartial=0,
timeout=0, cookies=None, followRedirect=1,
redirectLimit=20):
self.requestedPartial = 0
if isinstance(fileOrName, types.StringTypes):
self.fileName = fileOrName
self.file = None
if supportPartial and os.path.exists(self.fileName):
fileLength = os.path.getsize(self.fileName)
if fileLength:
self.requestedPartial = fileLength
if headers == None:
headers = {}
headers["range"] = "bytes=%d-" % fileLength
else:
self.file = fileOrName
HTTPClientFactory.__init__(
self, url, method=method, postdata=postdata, headers=headers,
agent=agent, timeout=timeout, cookies=cookies,
followRedirect=followRedirect, redirectLimit=redirectLimit)
def gotHeaders(self, headers):
HTTPClientFactory.gotHeaders(self, headers)
if self.requestedPartial:
contentRange = headers.get("content-range", None)
if not contentRange:
# server doesn't support partial requests, oh well
self.requestedPartial = 0
return
# TODO: end and realLength are not being used anywhere.. maybe use dump variable: _ or use parseContentRange()[0:2]
start, end, realLength = http.parseContentRange(contentRange[0])
if start != self.requestedPartial:
# server is acting wierdly
self.requestedPartial = 0
def openFile(self, partialContent):
if partialContent:
file = open(self.fileName, 'rb+')
file.seek(0, 2)
else:
file = open(self.fileName, 'wb')
return file
def pageStart(self, partialContent):
"""Called on page download start.
@param partialContent: tells us if the download is partial download we requested.
"""
if partialContent and not self.requestedPartial:
raise ValueError, "we shouldn't get partial content response if we didn't want it!"
if self.waiting:
try:
if not self.file:
self.file = self.openFile(partialContent)
except IOError:
#raise
self.deferred.errback(failure.Failure())
def pagePart(self, data):
if not self.file:
return
try:
self.file.write(data)
except IOError:
#raise
self.file = None
self.deferred.errback(failure.Failure())
def noPage(self, reason):
"""
Close the storage file and errback the waiting L{Deferred} with the
given reason.
"""
if self.waiting:
self.waiting = 0
if self.file:
try:
self.file.close()
except:
log.err(None, "Error closing HTTPDownloader file")
self.deferred.errback(reason)
def pageEnd(self):
self.waiting = 0
if not self.file:
return
try:
self.file.close()
except IOError:
self.deferred.errback(failure.Failure())
return
self.deferred.callback(self.value)
def _parse(url, defaultPort=None):
"""
Split the given URL into the scheme, host, port, and path.
@type url: C{str}
@param url: An URL to parse.
@type defaultPort: C{int} or C{None}
@param defaultPort: An alternate value to use as the port if the URL does
not include one.
@return: A four-tuple of the scheme, host, port, and path of the URL. All
of these are C{str} instances except for port, which is an C{int}.
"""
url = url.strip()
parsed = http.urlparse(url)
scheme = parsed[0]
path = urlunparse(('', '') + parsed[2:])
if defaultPort is None:
if scheme == 'https':
defaultPort = 443
else:
defaultPort = 80
host, port = parsed[1], defaultPort
if ':' in host:
host, port = host.split(':')
try:
port = int(port)
except ValueError:
port = defaultPort
if path == '':
path = '/'
return scheme, host, port, path
def _makeGetterFactory(url, factoryFactory, contextFactory=None,
*args, **kwargs):
"""
Create and connect an HTTP page getting factory.
Any additional positional or keyword arguments are used when calling
C{factoryFactory}.
@param factoryFactory: Factory factory that is called with C{url}, C{args}
and C{kwargs} to produce the getter
@param contextFactory: Context factory to use when creating a secure
connection, defaulting to C{None}
@return: The factory created by C{factoryFactory}
"""
# TODO: Another unused variable: path. See TODO for similar case above
scheme, host, port, path = _parse(url)
factory = factoryFactory(url, *args, **kwargs)
if scheme == 'https':
from twisted.internet import ssl
if contextFactory is None:
contextFactory = ssl.ClientContextFactory()
reactor.connectSSL(host, port, factory, contextFactory)
else:
reactor.connectTCP(host, port, factory)
return factory
def getPage(url, contextFactory=None, *args, **kwargs):
"""
Download a web page as a string.
Download a page. Return a deferred, which will callback with a
page (as a string) or errback with a description of the error.
See L{HTTPClientFactory} to see what extra arguments can be passed.
"""
return _makeGetterFactory(
url,
HTTPClientFactory,
contextFactory=contextFactory,
*args, **kwargs).deferred
def downloadPage(url, file, contextFactory=None, *args, **kwargs):
"""
Download a web page to a file.
@param file: path to file on filesystem, or file-like object.
See HTTPDownloader to see what extra args can be passed.
"""
factoryFactory = lambda url, *a, **kw: HTTPDownloader(url, file, *a, **kw)
return _makeGetterFactory(
url,
factoryFactory,
contextFactory=contextFactory,
*args, **kwargs).deferred
# The code which follows is based on the new HTTP client implementation. It
# should be significantly better than anything above, though it is not yet
# feature equivalent.
from twisted.internet.protocol import ClientCreator
from twisted.web.error import SchemeNotSupported
# TODO: ResponseDone and Response from _newclient never seem to be used?
# Since I can't be sure if they aren't deps I need somebody else to look at this
from _newclient import ResponseDone, ResponseFailed, Request, \
Response, HTTP11ClientProtocol
from twisted.internet.error import ConnectionDone
try:
from twisted.internet.ssl import ClientContextFactory
except ImportError:
class WebClientContextFactory(object):
"""
A web context factory which doesn't work because the necessary SSL
support is missing.
"""
def getContext(self, hostname, port):
raise NotImplementedError("SSL support unavailable")
else:
class WebClientContextFactory(ClientContextFactory):
"""
A web context factory which ignores the hostname and port and does no
certificate verification.
"""
def getContext(self, hostname, port):
return ClientContextFactory.getContext(self)
class _WebToNormalContextFactory(object):
"""
Adapt a web context factory to a normal context factory.
@ivar _webContext: A web context factory which accepts a hostname and port
number to its C{getContext} method.
@ivar _hostname: The hostname which will be passed to
C{_webContext.getContext}.
@ivar _port: The port number which will be passed to
C{_webContext.getContext}.
"""
def __init__(self, webContext, hostname, port):
self._webContext = webContext
self._hostname = hostname
self._port = port
def getContext(self):
"""
Called the wrapped web context factory's C{getContext} method with a
hostname and port number and return the resulting context object.
"""
return self._webContext.getContext(self._hostname, self._port)
class Agent(object):
"""
L{Agent} is a very basic HTTP client. It supports I{HTTP} and I{HTTPS}
scheme URIs (but performs no certificate checking by default). It also
supports persistent connections.
@ivar _reactor: The L{IReactorTCP} and L{IReactorSSL} implementation which
will be used to set up connections over which to issue requests.
@ivar _contextFactory: A web context factory which will be used to create
SSL context objects for any SSL connections the agent needs to make.
@ivar persistent: Set to C{True} when you use HTTP persistent connecton.
@type persistent: Boolean
@ivar maxConnections: Max number of HTTP connections per a server. The
default value is 1. This is effective only when the
C{self.persistent} is C{True}.
RFC 2616 says "A single-user client SHOULD NOT maintain more than 2
connections with any server or proxy."
@type maxConnections: C{int}
@ivar _semaphores: A dictioinary mapping a tuple (scheme, host, port)
to an instance of L{DeferredSemaphore}. It is used to limit the
number of connections to a server when C{self.persistent==True}.
@ivar _protocolCache: A dictioinary mapping a tuple (scheme, host, port)
to a list of instances of L{HTTP11ClientProtocol}. It is used to
cache the connections to the servers when C{self.persistent==True}.
@since: 9.0
"""
_protocol = HTTP11ClientProtocol
maxConnections = 1
def __init__(self, reactor, contextFactory=WebClientContextFactory(),
persistent=False):
self._reactor = reactor
self._contextFactory = contextFactory
self.persistent = persistent
self._semaphores = {}
self._protocolCache = {}
def _wrapContextFactory(self, host, port):
"""
Create and return a normal context factory wrapped around
C{self._contextFactory} in such a way that C{self._contextFactory} will
have the host and port information passed to it.
@param host: A C{str} giving the hostname which will be connected to in
order to issue a request.
@param port: An C{int} giving the port number the connection will be on.
@return: A context factory suitable to be passed to C{reactor.connectSSL}.
"""
return _WebToNormalContextFactory(self._contextFactory, host, port)
def _connect(self, scheme, host, port):
"""
Connect to the given host and port, using a transport selected based on
scheme.
@param scheme: A string like C{'http'} or C{'https'} (the only two
supported values) to use to determine how to establish the
connection.
@param host: A C{str} giving the hostname which will be connected to in
order to issue a request.
@param port: An C{int} giving the port number the connection will be on.
@return: A L{Deferred} which fires with a connected instance of
C{self._protocol}.
"""
cc = ClientCreator(self._reactor, self._protocol)
if scheme == 'http':
d = cc.connectTCP(host, port)
elif scheme == 'https':
d = cc.connectSSL(host, port, self._wrapContextFactory(host, port))
else:
d = defer.fail(SchemeNotSupported(
"Unsupported scheme: %r" % (scheme,)))
return d
def request(self, method, uri, headers=None, bodyProducer=None):
"""
Issue a new request.
@param method: The request method to send.
@type method: C{str}
@param uri: The request URI send.
@type uri: C{str}
@param headers: The request headers to send. If no I{Host} header is
included, one will be added based on the request URI.
@type headers: L{Headers}
@param bodyProducer: An object which will produce the request body or,
if the request body is to be empty, L{None}.
@type bodyProducer: L{IBodyProducer} provider
@return: A L{Deferred} which fires with the result of the request (a
L{Response} instance), or fails if there is a problem setting up a
connection over which to issue the request. It may also fail with
L{SchemeNotSupported} if the scheme of the given URI is not
supported.
@rtype: L{Deferred}
"""
scheme, host, port, path = _parse(uri)
if headers is None:
headers = Headers()
if not headers.hasHeader('host'):
# This is a lot of copying. It might be nice if there were a bit
# less.
headers = Headers(dict(headers.getAllRawHeaders()))
headers.addRawHeader(
'host', self._computeHostValue(scheme, host, port))
if self.persistent:
sem = self._semaphores.get((scheme, host, port))
if sem is None:
sem = defer.DeferredSemaphore(self.maxConnections)
self._semaphores[scheme, host, port] = sem
return sem.run(self._request, method, scheme, host, port, path,
headers, bodyProducer)
else:
return self._request(
method, scheme, host, port, path, headers, bodyProducer)
def _request(self, method, scheme, host, port, path, headers, bodyProducer):
"""
Issue a new request.
This will be called by request(), users should not call it.
@param method: The request method to send.
@type method: C{str}
@param scheme: A string like C{'http'} or C{'https'} (the only two
supported values) to use to determine how to establish the
connection.
@param host: A C{str} giving the hostname which will be connected to in
order to issue a request.
@param port: An C{int} giving the port number the connection will be on.
@param path: A C{str} giving the path portion of the request URL.
@param headers: The request headers to send. If no I{Host} header is
included, one will be added based on the request URI.
@type headers: L{Headers}
@param bodyProducer: An object which will produce the request body or,
if the request body is to be empty, L{None}.
@type bodyProducer: L{IBodyProducer} provider
@return: A L{Deferred} which fires with the result of the request (a
L{Response} instance), or fails if there is a problem setting up a
connection over which to issue the request. It may also fail with
L{SchemeNotSupported} if the scheme of the given URI is not
supported.
@rtype: L{Deferred}
"""
protos = self._protocolCache.setdefault((scheme, host, port), [])
maybeDisconnected = False
while protos:
# connection exists
p = protos.pop(0)
if p.state == 'QUIESCENT':
d = defer.succeed(p)
maybeDisconnected = True
break
else:
# new connection
d = self._connect(scheme, host, port)
req = Request(method, path, headers, bodyProducer,
persistent=self.persistent)
def saveProtocol(response, proto):
if self.persistent:
protos.append(proto)
return response
def cbConnected(proto):
def ebRequest(f):
# Previous connection is unavailable.
if f.check(ResponseFailed):
for reason in f.value.reasons:
if (isinstance(reason, failure.Failure) and
isinstance(reason.value, ConnectionDone)):
# Maybe timeout has been exeeded before I send
# the request. So I retry again.
def retry(proto):
d = proto.request(req)
d.addCallback(saveProtocol, proto)
return d
d = self._connect(scheme, host, port)
d.addCallback(retry)
return d
return f
d = proto.request(req)
d.addCallback(saveProtocol, proto)
if maybeDisconnected:
d.addErrback(ebRequest)
return d
d.addCallback(cbConnected)
return d
def _computeHostValue(self, scheme, host, port):
"""
Compute the string to use for the value of the I{Host} header, based on
the given scheme, host name, and port number.
"""
if (scheme, port) in (('http', 80), ('https', 443)):
return host
return '%s:%d' % (host, port)
def closeCachedConnections(self):
"""
Close all the cached persistent connections.
"""
for protos in self._protocolCache.itervalues():
for p in protos:
p.transport.loseConnection()
self._protocolCache = {}
__all__ = [
'PartialDownloadError',
'HTTPPageGetter', 'HTTPPageDownloader', 'HTTPClientFactory', 'HTTPDownloader',
'getPage', 'downloadPage',
'ResponseDone', 'Response', 'Agent']