def __init__(self):
#: A case-insensitive dictionary of headers to be sent on each
#: :class:`Request <Request>` sent from this
#: :class:`Session <Session>`.
self.headers = default_headers()
#: Default Authentication tuple or object to attach to
#: :class:`Request <Request>`.
self.auth = None
#: Dictionary mapping protocol to the URL of the proxy (e.g.
#: {'http': 'foo.bar:3128'}) to be used on each
#: :class:`Request <Request>`.
self.proxies = {}
#: Event-handling hooks.
self.hooks = default_hooks()
#: Dictionary of querystring data to attach to each
#: :class:`Request <Request>`. The dictionary values may be lists for
#: representing multivalued query parameters.
self.params = {}
#: Stream response content default.
self.stream = False
#: SSL Verification default.
self.verify = True
#: SSL certificate default.
self.cert = None
#: Maximum number of redirects allowed. If the request exceeds this
#: limit, a :class:`TooManyRedirects` exception is raised.
self.max_redirects = DEFAULT_REDIRECT_LIMIT
#: Should we trust the environment?
self.trust_env = True
#: A CookieJar containing all currently outstanding cookies set on this
#: session. By default it is a
#: :class:`RequestsCookieJar <requests.cookies.RequestsCookieJar>`, but
#: may be any other ``cookielib.CookieJar`` compatible object.
self.cookies = cookiejar_from_dict({})
# Default connection adapters.
self.adapters = OrderedDict()
self.mount('https://', HTTPAdapter())
self.mount('http://', HTTPAdapter())
def __init__(self, *args, **kwargs):
retries = kwargs.pop("retries", 0)
cache = kwargs.pop("cache", None)
super(PipSession, self).__init__(*args, **kwargs)
# Attach our User Agent to the request
self.headers["User-Agent"] = user_agent()
# Attach our Authentication handler to the session
self.auth = MultiDomainBasicAuth()
if cache:
http_adapter = CacheControlAdapter(
cache=SafeFileCache(cache),
max_retries=retries,
)
else:
http_adapter = HTTPAdapter(max_retries=retries)
self.mount("http://", http_adapter)
self.mount("https://", http_adapter)
# Enable file:// urls
self.mount("file://", LocalFSAdapter())
def __init__(self, *args, **kwargs):
retries = kwargs.pop("retries", 0)
cache = kwargs.pop("cache", None)
insecure_hosts = kwargs.pop("insecure_hosts", [])
super(PipSession, self).__init__(*args, **kwargs)
# Attach our User Agent to the request
self.headers["User-Agent"] = user_agent()
# Attach our Authentication handler to the session
self.auth = MultiDomainBasicAuth()
# Create our urllib3.Retry instance which will allow us to customize
# how we handle retries.
retries = urllib3.Retry(
# Set the total number of retries that a particular request can
# have.
total=retries,
# A 503 error from PyPI typically means that the Fastly -> Origin
# connection got interrupted in some way. A 503 error in general
# is typically considered a transient error so we'll go ahead and
# retry it.
status_forcelist=[503],
# Add a small amount of back off between failed requests in
# order to prevent hammering the service.
backoff_factor=0.25,
)
# We want to _only_ cache responses on securely fetched origins. We do
# this because we can't validate the response of an insecurely fetched
# origin, and we don't want someone to be able to poison the cache and
# require manual eviction from the cache to fix it.
if cache:
secure_adapter = CacheControlAdapter(
cache=SafeFileCache(cache, use_dir_lock=True),
max_retries=retries,
)
else:
secure_adapter = HTTPAdapter(max_retries=retries)
# Our Insecure HTTPAdapter disables HTTPS validation. It does not
# support caching (see above) so we'll use it for all http:// URLs as
# well as any https:// host that we've marked as ignoring TLS errors
# for.
insecure_adapter = InsecureHTTPAdapter(max_retries=retries)
self.mount("https://", secure_adapter)
self.mount("http://", insecure_adapter)
# Enable file:// urls
self.mount("file://", LocalFSAdapter())
# We want to use a non-validating adapter for any requests which are
# deemed insecure.
for host in insecure_hosts:
self.mount("https://{0}/".format(host), insecure_adapter)
def send(self, request, **kwargs):
conn = S3Connection(is_secure=True)
bucket_name = os.getenv('S3_PIP_BUCKET_NAME')
update_indexes = os.getenv('S3_PIP_COMPARE_CACHE')
bucket = conn.get_bucket(bucket_name)
keyname = urlparse.urlparse(request.url).path
html = False
if keyname.endswith("/"):
keyname += "index.html"
html = True
key = bucket.get_key(keyname)
if html:
content_type = "text/html"
else:
content_type = mimetypes.guess_type(request.url)[0] or "text/plain"
if key is None:
pypi_resp = HTTPAdapter().send(request, **kwargs)
if pypi_resp.status_code != 200:
return pypi_resp
content = pypi_resp.content
resp = S3Response(content, request.url, len(content), content_type)
self.s3_sync(request.url, content, bucket,
pypi_resp.headers.get('x-pypi-last-serial'))
return resp
logger.notify("Found item in S3 {0}".format(keyname))
resp = S3Response(key.get_contents_as_string(), request.url, key.size,
content_type)
if update_indexes:
pypi_resp = HTTPAdapter().send(request, **kwargs)
if pypi_resp.headers['x-pypi-last-serial'] > key.get_metadata(
'x-pypi-last-serial'):
content = pypi_resp.content
resp = S3Response(content, request.url, len(content),
content_type)
self.s3_sync(request.url, content, bucket,
pypi_resp.headers['x-pypi-last-serial'])
return resp
def __init__(self, *args, **kwargs):
"""
:param trusted_hosts: Domains not to emit warnings for when not using
HTTPS.
"""
retries = kwargs.pop("retries", 0)
cache = kwargs.pop("cache", None)
trusted_hosts = kwargs.pop("trusted_hosts", []) # type: List[str]
index_urls = kwargs.pop("index_urls", None)
super(PipSession, self).__init__(*args, **kwargs)
# Namespace the attribute with "pip_" just in case to prevent
# possible conflicts with the base class.
self.pip_trusted_origins = [] # type: List[Tuple[str, Optional[int]]]
# Attach our User Agent to the request
self.headers["User-Agent"] = user_agent()
# Attach our Authentication handler to the session
self.auth = MultiDomainBasicAuth(index_urls=index_urls)
# Create our urllib3.Retry instance which will allow us to customize
# how we handle retries.
retries = urllib3.Retry(
# Set the total number of retries that a particular request can
# have.
total=retries,
# A 503 error from PyPI typically means that the Fastly -> Origin
# connection got interrupted in some way. A 503 error in general
# is typically considered a transient error so we'll go ahead and
# retry it.
# A 500 may indicate transient error in Amazon S3
# A 520 or 527 - may indicate transient error in CloudFlare
status_forcelist=[500, 503, 520, 527],
# Add a small amount of back off between failed requests in
# order to prevent hammering the service.
backoff_factor=0.25,
)
# Check to ensure that the directory containing our cache directory
# is owned by the user current executing pip. If it does not exist
# we will check the parent directory until we find one that does exist.
if cache and not check_path_owner(cache):
logger.warning(
"The directory '%s' or its parent directory is not owned by "
"the current user and the cache has been disabled. Please "
"check the permissions and owner of that directory. If "
"executing pip with sudo, you may want sudo's -H flag.",
cache,
)
cache = None
# We want to _only_ cache responses on securely fetched origins. We do
# this because we can't validate the response of an insecurely fetched
# origin, and we don't want someone to be able to poison the cache and
# require manual eviction from the cache to fix it.
if cache:
secure_adapter = CacheControlAdapter(
cache=SafeFileCache(cache, use_dir_lock=True),
max_retries=retries,
)
else:
secure_adapter = HTTPAdapter(max_retries=retries)
# Our Insecure HTTPAdapter disables HTTPS validation. It does not
# support caching (see above) so we'll use it for all http:// URLs as
# well as any https:// host that we've marked as ignoring TLS errors
# for.
insecure_adapter = InsecureHTTPAdapter(max_retries=retries)
# Save this for later use in add_insecure_host().
self._insecure_adapter = insecure_adapter
self.mount("https://", secure_adapter)
self.mount("http://", insecure_adapter)
# Enable file:// urls
self.mount("file://", LocalFSAdapter())
for host in trusted_hosts:
self.add_trusted_host(host, suppress_logging=True)
def __init__(
self,
*args: Any,
retries: int = 0,
cache: Optional[str] = None,
trusted_hosts: Sequence[str] = (),
index_urls: Optional[List[str]] = None,
**kwargs: Any,
) -> None:
"""
:param trusted_hosts: Domains not to emit warnings for when not using
HTTPS.
"""
super().__init__(*args, **kwargs)
# Namespace the attribute with "pip_" just in case to prevent
# possible conflicts with the base class.
self.pip_trusted_origins: List[Tuple[str, Optional[int]]] = []
# Attach our User Agent to the request
self.headers["User-Agent"] = user_agent()
# Attach our Authentication handler to the session
self.auth = MultiDomainBasicAuth(index_urls=index_urls)
# Create our urllib3.Retry instance which will allow us to customize
# how we handle retries.
retries = urllib3.Retry(
# Set the total number of retries that a particular request can
# have.
total=retries,
# A 503 error from PyPI typically means that the Fastly -> Origin
# connection got interrupted in some way. A 503 error in general
# is typically considered a transient error so we'll go ahead and
# retry it.
# A 500 may indicate transient error in Amazon S3
# A 520 or 527 - may indicate transient error in CloudFlare
status_forcelist=[500, 503, 520, 527],
# Add a small amount of back off between failed requests in
# order to prevent hammering the service.
backoff_factor=0.25,
) # type: ignore
# Our Insecure HTTPAdapter disables HTTPS validation. It does not
# support caching so we'll use it for all http:// URLs.
# If caching is disabled, we will also use it for
# https:// hosts that we've marked as ignoring
# TLS errors for (trusted-hosts).
insecure_adapter = InsecureHTTPAdapter(max_retries=retries)
# We want to _only_ cache responses on securely fetched origins or when
# the host is specified as trusted. We do this because
# we can't validate the response of an insecurely/untrusted fetched
# origin, and we don't want someone to be able to poison the cache and
# require manual eviction from the cache to fix it.
if cache:
secure_adapter = CacheControlAdapter(
cache=SafeFileCache(cache),
max_retries=retries,
)
self._trusted_host_adapter = InsecureCacheControlAdapter(
cache=SafeFileCache(cache),
max_retries=retries,
)
else:
secure_adapter = HTTPAdapter(max_retries=retries)
self._trusted_host_adapter = insecure_adapter
self.mount("https://", secure_adapter)
self.mount("http://", insecure_adapter)
# Enable file:// urls
self.mount("file://", LocalFSAdapter())
for host in trusted_hosts:
self.add_trusted_host(host, suppress_logging=True)
# -*- coding=utf-8 -*-
import csv # 加载csv包便于读取csv文件
import json
from time import sleep
from pip._vendor import requests
from pip._vendor.requests.adapters import HTTPAdapter
from pip._vendor.requests.packages.urllib3 import Retry
session = requests.Session()
retry = Retry(connect=10000, backoff_factor=0.5)
adapter = HTTPAdapter(max_retries=retry)
session.mount('http://', adapter)
session.mount('https://', adapter)
import pymysql
conn = pymysql.connect(host='127.0.0.1', port=3306, user='******', passwd='haha', db='ireading')
cur = conn.cursor()
cur.execute("select Max(id) from word_slim e where e.word REGEXP '^[A-Za-z]+$' and e.word not in (select m.word from word_mini m) and uk_pron is not null and us_pron is not null")
for item in cur:
index = item[0] if item[0] else 0
cur.execute("select word from word_slim e where e.word REGEXP '^[A-Za-z]+$' and e.word not in (select m.word from word_mini m) and id>" + str(index))
l = []
c=0
count = index
for item in cur:
l.append(item[0])
print('finish')
for word in l:
# Add a small amount of back off between failed requests in
# order to prevent hammering the service.
backoff_factor=0.25,
)
# We want to _only_ cache responses on securely fetched origins. We do
# this because we can't validate the response of an insecurely fetched
# origin, and we don't want someone to be able to poison the cache and
# require manual evication from the cache to fix it.
if cache:
secure_adapter = CacheControlAdapter(
cache=SafeFileCache(cache),
max_retries=retries,
)
else:
secure_adapter = HTTPAdapter(max_retries=retries)
# Our Insecure HTTPAdapter disables HTTPS validation. It does not
# support caching (see above) so we'll use it for all http:// URLs as
# well as any https:// host that we've marked as ignoring TLS errors
# for.
insecure_adapter = InsecureHTTPAdapter(max_retries=retries)
self.mount("https://", secure_adapter)
self.mount("http://", insecure_adapter)
# Enable file:// urls
self.mount("file://", LocalFSAdapter())
# We want to use a non-validating adapter for any requests which are
# deemed insecure.
