def get_page(source):
protocol = urlparse(source)[0] + "://"
source = protocol + quote(source.replace(protocol, ""))
if settings.USING_PROXY:
http = SOCKSProxyManager(
settings.proxy_type + "://" + settings.proxy_host + ":" + settings.proxy_port,
cert_reqs="CERT_REQUIRED", # Force certificate check
ca_certs=certifi.where(), # Path to the Certifi bundle
)
else:
http = urllib3.PoolManager(
cert_reqs="CERT_REQUIRED", # Force certificate check
ca_certs=certifi.where(), # Path to the Certifi bundle
)
try:
page = http.urlopen(
"GET",
source,
preload_content=False,
# timeout=urllib3.Timeout(connect=5.0, read=10.0),
headers={'User-Agent': 'Mozilla'}
)
except urllib3.exceptions.MaxRetryError as error:
print("Connection error:", error)
sys.exit(1)
else:
return page
def request(self):
req = self._request
if req.proxy:
if req.proxy_userpwd:
headers = make_headers(proxy_basic_auth=req.proxy_userpwd)
else:
headers = None
proxy_url = '%s://%s' % (req.proxy_type, req.proxy)
if req.proxy_type == 'socks5':
pool = SOCKSProxyManager(proxy_url) # , proxy_headers=headers)
else:
pool = ProxyManager(proxy_url, proxy_headers=headers)
else:
pool = self.pool
try:
retry = Retry(redirect=False, connect=False, read=False)
# The read timeout is not total response time timeout
# It is the timeout on read of next data chunk from the server
# Total response timeout is handled by Grab
timeout = Timeout(connect=req.connect_timeout, read=req.timeout)
#req_headers = dict((make_unicode(x), make_unicode(y))
# for (x, y) in req.headers.items())
if six.PY3:
req_url = make_unicode(req.url)
req_method = make_unicode(req.method)
else:
req_url = make_str(req.url)
req_method = req.method
req.op_started = time.time()
res = pool.urlopen(req_method,
req_url,
body=req.data,
timeout=timeout,
retries=retry,
headers=req.headers,
preload_content=False)
except exceptions.ReadTimeoutError as ex:
raise error.GrabTimeoutError('ReadTimeoutError', ex)
except exceptions.ConnectTimeoutError as ex:
raise error.GrabConnectionError('ConnectTimeoutError', ex)
except exceptions.ProtocolError as ex:
# TODO:
# the code
# raise error.GrabConnectionError(ex.args[1][0], ex.args[1][1])
# fails
# with error TypeError: 'OSError' object is not subscriptable
raise error.GrabConnectionError('ProtocolError', ex)
# WTF?
self.request_head = b''
self.request_body = b''
self.request_log = b''
self._response = res
def request(self):
req = self._request
if req.proxy:
if req.proxy_userpwd:
headers = make_headers(proxy_basic_auth=req.proxy_userpwd)
else:
headers = None
proxy_url = '%s://%s' % (req.proxy_type, req.proxy)
if req.proxy_type == 'socks5':
pool = SOCKSProxyManager(
proxy_url,
cert_reqs='CERT_REQUIRED',
ca_certs=certifi.where()) # , proxy_headers=headers)
else:
pool = ProxyManager(proxy_url,
proxy_headers=headers,
cert_reqs='CERT_REQUIRED',
ca_certs=certifi.where())
else:
pool = self.pool
with self.wrap_transport_error():
# Retries can be disabled by passing False:
# http://urllib3.readthedocs.io/en/latest/reference/urllib3.util.html#module-urllib3.util.retry
# Do not use False because of warning:
# Converted retries value: False -> Retry(total=False,
# connect=None, read=None, redirect=0, status=None)
retry = Retry(
total=False,
connect=False,
read=False,
redirect=0,
status=None,
)
# The read timeout is not total response time timeout
# It is the timeout on read of next data chunk from the server
# Total response timeout is handled by Grab
timeout = Timeout(connect=req.connect_timeout, read=req.timeout)
#req_headers = dict((make_unicode(x), make_unicode(y))
# for (x, y) in req.headers.items())
if six.PY3:
req_url = make_unicode(req.url)
req_method = make_unicode(req.method)
else:
req_url = make_str(req.url)
req_method = req.method
req.op_started = time.time()
try:
res = pool.urlopen(req_method,
req_url,
body=req.data,
timeout=timeout,
retries=retry,
headers=req.headers,
preload_content=False)
except UnicodeError as ex:
raise error.GrabConnectionError('GrabInvalidUrl', ex)
#except exceptions.ReadTimeoutError as ex:
# raise error.GrabTimeoutError('ReadTimeoutError', ex)
#except exceptions.ConnectTimeoutError as ex:
# raise error.GrabConnectionError('ConnectTimeoutError', ex)
#except exceptions.ProtocolError as ex:
# # TODO:
# # the code
# # raise error.GrabConnectionError(ex.args[1][0], ex.args[1][1])
# # fails
# # with error TypeError: 'OSError' object is not subscriptable
# raise error.GrabConnectionError('ProtocolError', ex)
#except exceptions.SSLError as ex:
# raise error.GrabConnectionError('SSLError', ex)
# WTF?
self.request_head = b''
self.request_body = b''
self.request_log = b''
self._response = res
def request(self):
req = self._request
if req.proxy:
if req.proxy_userpwd:
headers = make_headers(proxy_basic_auth=req.proxy_userpwd)
else:
headers = None
proxy_url = '%s://%s' % (req.proxy_type, req.proxy)
if req.proxy_type == 'socks5':
pool = SOCKSProxyManager(
proxy_url,
cert_reqs='CERT_REQUIRED',
ca_certs=certifi.where()
) # , proxy_headers=headers)
else:
pool = ProxyManager(
proxy_url, proxy_headers=headers,
cert_reqs='CERT_REQUIRED',
ca_certs=certifi.where()
)
else:
pool = self.pool
try:
# Retries can be disabled by passing False:
# http://urllib3.readthedocs.io/en/latest/reference/urllib3.util.html#module-urllib3.util.retry
# Do not use False because of warning:
# Converted retries value: False -> Retry(total=False,
# connect=None, read=None, redirect=0, status=None)
retry = Retry(
total=False,
connect=False,
read=False,
redirect=0,
status=None,
)
# The read timeout is not total response time timeout
# It is the timeout on read of next data chunk from the server
# Total response timeout is handled by Grab
timeout = Timeout(connect=req.connect_timeout,
read=req.timeout)
#req_headers = dict((make_unicode(x), make_unicode(y))
# for (x, y) in req.headers.items())
if six.PY3:
req_url = make_unicode(req.url)
req_method = make_unicode(req.method)
else:
req_url = make_str(req.url)
req_method = req.method
req.op_started = time.time()
try:
res = pool.urlopen(req_method,
req_url,
body=req.data, timeout=timeout,
retries=retry,
headers=req.headers,
preload_content=False)
except UnicodeError as ex:
raise error.GrabConnectionError('GrabInvalidUrl', ex)
except exceptions.ReadTimeoutError as ex:
raise error.GrabTimeoutError('ReadTimeoutError', ex)
except exceptions.ConnectTimeoutError as ex:
raise error.GrabConnectionError('ConnectTimeoutError', ex)
except exceptions.ProtocolError as ex:
# TODO:
# the code
# raise error.GrabConnectionError(ex.args[1][0], ex.args[1][1])
# fails
# with error TypeError: 'OSError' object is not subscriptable
raise error.GrabConnectionError('ProtocolError', ex)
except exceptions.SSLError as ex:
raise error.GrabConnectionError('SSLError', ex)
# WTF?
self.request_head = b''
self.request_body = b''
self.request_log = b''
self._response = res