def __new__(cls, io_loop=None, max_clients=10,
max_simultaneous_connections=None):
# There is one client per IOLoop since they share curl instances
io_loop = io_loop or ioloop.IOLoop.instance()
if io_loop in cls._ASYNC_CLIENTS:
return cls._ASYNC_CLIENTS[io_loop]
else:
instance = super(AsyncHTTPClient, cls).__new__(cls)
instance.io_loop = io_loop
instance._multi = pycurl.CurlMulti()
instance._curls = [_curl_create(max_simultaneous_connections)
for i in xrange(max_clients)]
instance._free_list = instance._curls[:]
instance._requests = collections.deque()
instance._fds = {}
instance._events = {}
instance._added_perform_callback = False
instance._timeout = None
instance._closed = False
cls._ASYNC_CLIENTS[io_loop] = instance
return instance
python类CurlMulti()的实例源码
def __new__(cls, io_loop=None, max_clients=10,
max_simultaneous_connections=None):
# There is one client per IOLoop since they share curl instances
io_loop = io_loop or ioloop.IOLoop.instance()
if io_loop in cls._ASYNC_CLIENTS:
return cls._ASYNC_CLIENTS[io_loop]
else:
instance = super(AsyncHTTPClient2, cls).__new__(cls)
instance.io_loop = io_loop
instance._multi = pycurl.CurlMulti()
instance._multi.setopt(pycurl.M_TIMERFUNCTION,
instance._set_timeout)
instance._multi.setopt(pycurl.M_SOCKETFUNCTION,
instance._handle_socket)
instance._curls = [_curl_create(max_simultaneous_connections)
for i in xrange(max_clients)]
instance._free_list = instance._curls[:]
instance._requests = collections.deque()
instance._fds = {}
instance._timeout = None
cls._ASYNC_CLIENTS[io_loop] = instance
return instance
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [self._curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [self._curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [self._curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def __init__(self, multi_handler=None, max_simultanous_connections=None, defer_callbacks=False):
self.requests = {}
if multi_handler:
self._curl_multi_handler = multi_handler
else:
self._curl_multi_handler = pycurl.CurlMulti()
if max_simultanous_connections is not None:
self._curl_multi_handler.setopt(pycurl.M_MAX_TOTAL_CONNECTIONS, max_simultanous_connections)
self._defer_callbacks = defer_callbacks
self._async_callbacks = []
self._async_results = []
def create_pool(self, num_conn):
# Pre-allocate a list of curl objects
self.m = pycurl.CurlMulti()
self.m.handles = []
for i in range(num_conn):
c = pycurl.Curl()
self.m.handles.append(c)
self.freelist.put(c)
def __init__(self, url, filename, get={}, post={}, referer=None, cj=None, bucket=None,
options={}, progressNotify=None, disposition=False):
self.url = url
self.filename = filename #complete file destination, not only name
self.get = get
self.post = post
self.referer = referer
self.cj = cj #cookiejar if cookies are needed
self.bucket = bucket
self.options = options
self.disposition = disposition
# all arguments
self.abort = False
self.size = 0
self.nameDisposition = None #will be parsed from content disposition
self.chunks = []
self.log = getLogger("log")
try:
self.info = ChunkInfo.load(filename)
self.info.resume = True #resume is only possible with valid info file
self.size = self.info.size
self.infoSaved = True
except IOError:
self.info = ChunkInfo(filename)
self.chunkSupport = None
self.m = pycurl.CurlMulti()
#needed for speed calculation
self.lastArrived = []
self.speeds = []
self.lastSpeeds = [0, 0]
self.progressNotify = progressNotify
def __init__(self, p_timeoutMs=1000, p_curlMOpts=None):
self.m_handle = pycurl.CurlMulti()
self.m_clients = []
self.m_timeoutMs = p_timeoutMs
self.m_opts = p_curlMOpts
if p_curlMOpts is None:
self.m_opts = {}
self._init_opt()
curl_httpclient.py 文件源码
项目：My-Web-Server-Framework-With-Python2.7
作者: syjsu
项目源码
文件源码
阅读 16
收藏 0
点赞 0
评论 0
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [self._curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def initialize(self, io_loop=None, max_clients=10,
max_simultaneous_connections=None):
self.io_loop = io_loop
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [_curl_create(max_simultaneous_connections)
for i in xrange(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
try:
self._socket_action = self._multi.socket_action
except AttributeError:
# socket_action is found in pycurl since 7.18.2 (it's been
# in libcurl longer than that but wasn't accessible to
# python).
logging.warning("socket_action method missing from pycurl; "
"falling back to socket_all. Upgrading "
"libcurl and pycurl will improve performance")
self._socket_action = \
lambda fd, action: self._multi.socket_all()
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
def create_pool(self, num_conn):
# Pre-allocate a list of curl objects
self.m = pycurl.CurlMulti()
self.m.handles = []
for i in range(num_conn):
c = pycurl.Curl()
self.m.handles.append(c)
self.freelist.put(c)
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [_curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
try:
self._socket_action = self._multi.socket_action
except AttributeError:
# socket_action is found in pycurl since 7.18.2 (it's been
# in libcurl longer than that but wasn't accessible to
# python).
gen_log.warning("socket_action method missing from pycurl; "
"falling back to socket_all. Upgrading "
"libcurl and pycurl will improve performance")
self._socket_action = \
lambda fd, action: self._multi.socket_all()
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [self._curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [self._curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def initialize(self, io_loop=None, max_clients=10,
max_simultaneous_connections=None):
self.io_loop = io_loop
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [_curl_create(max_simultaneous_connections)
for i in xrange(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
try:
self._socket_action = self._multi.socket_action
except AttributeError:
# socket_action is found in pycurl since 7.18.2 (it's been
# in libcurl longer than that but wasn't accessible to
# python).
logging.warning("socket_action method missing from pycurl; "
"falling back to socket_all. Upgrading "
"libcurl and pycurl will improve performance")
self._socket_action = \
lambda fd, action: self._multi.socket_all()
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [_curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
try:
self._socket_action = self._multi.socket_action
except AttributeError:
# socket_action is found in pycurl since 7.18.2 (it's been
# in libcurl longer than that but wasn't accessible to
# python).
gen_log.warning("socket_action method missing from pycurl; "
"falling back to socket_all. Upgrading "
"libcurl and pycurl will improve performance")
self._socket_action = \
lambda fd, action: self._multi.socket_all()
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def __init__(self, *args, **kwargs):
DownloadRequest.__init__(self, *args, **kwargs)
self.path = None
self.disposition = False
self.chunks = []
self.chunk_support = None
self.__manager = pycurl.CurlMulti()
# needed for speed calculation
self.last_arrived = []
self.speeds = []
self.last_speeds = [0, 0]
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [self._curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [self._curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def __init__(self, start_id, conns=2, skip_timeout=120):
Thread.__init__(self)
self.m = pycurl.CurlMulti()
self.handles = [self._create_handle() for i in range(conns)]
self.free_handles = list(self.handles)
self.last_request = None
self.skip_ahead = False
self.skip_timeout = skip_timeout
self.dl_deltas = deque(maxlen=10)
self.req_time = deque(maxlen=20)
self.queue_time = deque(maxlen=20)
self.peek_time = deque(maxlen=20)
self.req_delay_time = deque(maxlen=20)
self.stat_thread = Thread(target=self.calc_stat)
self.dps = deque(maxlen=60)
self.delta_lock = Lock()
self.delta_count = 0
# queue for requests so we can ensure a delay between each request
# use a list instead of an actual queue to be able to choose min ID
self.req_queue = []
self.req_queue_lock = Lock()
# requests by order
self.requests = []
self.requests_lock = Lock()
self.res_queue = Queue(maxsize=RES_QUEUE_MAXSIZE)
self.evt_stop = Event()
self.add_request(start_id)
def initialize(self, io_loop, max_clients=10, defaults=None):
super(CurlAsyncHTTPClient, self).initialize(io_loop, defaults=defaults)
self._multi = pycurl.CurlMulti()
self._multi.setopt(pycurl.M_TIMERFUNCTION, self._set_timeout)
self._multi.setopt(pycurl.M_SOCKETFUNCTION, self._handle_socket)
self._curls = [self._curl_create() for i in range(max_clients)]
self._free_list = self._curls[:]
self._requests = collections.deque()
self._fds = {}
self._timeout = None
# libcurl has bugs that sometimes cause it to not report all
# relevant file descriptors and timeouts to TIMERFUNCTION/
# SOCKETFUNCTION. Mitigate the effects of such bugs by
# forcing a periodic scan of all active requests.
self._force_timeout_callback = ioloop.PeriodicCallback(
self._handle_force_timeout, 1000, io_loop=io_loop)
self._force_timeout_callback.start()
# Work around a bug in libcurl 7.29.0: Some fields in the curl
# multi object are initialized lazily, and its destructor will
# segfault if it is destroyed without having been used. Add
# and remove a dummy handle to make sure everything is
# initialized.
dummy_curl_handle = pycurl.Curl()
self._multi.add_handle(dummy_curl_handle)
self._multi.remove_handle(dummy_curl_handle)
def __init__(self, transport, max_conn=20):
# Backpointer to transport object
self.__xport = transport
# Curl handles
self.__mhandle = pycurl.CurlMulti()
self.__chandles = []
self.__active_handles = 0
self.__max_handles = max_conn
# Request queue
self.__req_q = deque()
# List of failures
self.__failures = []
# List of URLs successfully transferred
self.__success = []
# List of Orphaned URLs.
self.__orphans = set()
# Set default file buffer size at 128k, callers override
# this setting after looking at VFS block size.
self.__file_bufsz = 131072
# Header bits and pieces
self.__user_agent = None
self.__common_header = {}
self.__last_stall_check = 0
# Set options on multi-handle
self.__mhandle.setopt(pycurl.M_PIPELINING, 0)
# initialize easy handles
for i in range(self.__max_handles):
eh = pycurl.Curl()
eh.url = None
eh.repourl = None
eh.fobj = None
eh.r_fobj = None
eh.filepath = None
eh.success = False
eh.fileprog = None
eh.filetime = -1
eh.starttime = -1
eh.uuid = None
self.__chandles.append(eh)
# copy handles into handle freelist
self.__freehandles = self.__chandles[:]
