mirror of https://github.com/python/cpython
Fix old urllib/urllib2/urlparse usage.
This commit is contained in:
Georg Brandl
parent
0f7ede4569
commit
029986af24
|
|
@ -100,7 +100,7 @@ The following classes are provided:
|
|||
|
||||
.. seealso::
|
||||
|
||||
Module :mod:`urllib2`
|
||||
Module :mod:`urllib.request`
|
||||
URL opening with automatic cookie handling.
|
||||
|
||||
Module :mod:`http.cookies`
|
||||
|
|
@ -149,11 +149,11 @@ contained :class:`Cookie` objects.
|
|||
the :class:`CookieJar`'s :class:`CookiePolicy` instance are true and false
|
||||
respectively), the :mailheader:`Cookie2` header is also added when appropriate.
|
||||
|
||||
The *request* object (usually a :class:`urllib2.Request` instance) must support
|
||||
the methods :meth:`get_full_url`, :meth:`get_host`, :meth:`get_type`,
|
||||
:meth:`unverifiable`, :meth:`get_origin_req_host`, :meth:`has_header`,
|
||||
:meth:`get_header`, :meth:`header_items`, and :meth:`add_unredirected_header`,as
|
||||
documented by :mod:`urllib2`.
|
||||
The *request* object (usually a :class:`urllib.request..Request` instance)
|
||||
must support the methods :meth:`get_full_url`, :meth:`get_host`,
|
||||
:meth:`get_type`, :meth:`unverifiable`, :meth:`get_origin_req_host`,
|
||||
:meth:`has_header`, :meth:`get_header`, :meth:`header_items`, and
|
||||
:meth:`add_unredirected_header`, as documented by :mod:`urllib.request`.
|
||||
|
||||
|
||||
.. method:: CookieJar.extract_cookies(response, request)
|
||||
|
|
@ -166,14 +166,15 @@ contained :class:`Cookie` objects.
|
|||
as appropriate (subject to the :meth:`CookiePolicy.set_ok` method's approval).
|
||||
|
||||
The *response* object (usually the result of a call to
|
||||
:meth:`urllib2.urlopen`, or similar) should support an :meth:`info` method,
|
||||
which returns a :class:`email.message.Message` instance.
|
||||
:meth:`urllib.request.urlopen`, or similar) should support an :meth:`info`
|
||||
method, which returns a :class:`email.message.Message` instance.
|
||||
|
||||
The *request* object (usually a :class:`urllib2.Request` instance) must support
|
||||
the methods :meth:`get_full_url`, :meth:`get_host`, :meth:`unverifiable`, and
|
||||
:meth:`get_origin_req_host`, as documented by :mod:`urllib2`. The request is
|
||||
used to set default values for cookie-attributes as well as for checking that
|
||||
the cookie is allowed to be set.
|
||||
The *request* object (usually a :class:`urllib.request.Request` instance)
|
||||
must support the methods :meth:`get_full_url`, :meth:`get_host`,
|
||||
:meth:`unverifiable`, and :meth:`get_origin_req_host`, as documented by
|
||||
:mod:`urllib.request`. The request is used to set default values for
|
||||
cookie-attributes as well as for checking that the cookie is allowed to be
|
||||
set.
|
||||
|
||||
|
||||
.. method:: CookieJar.set_policy(policy)
|
||||
|
|
@ -715,18 +716,18 @@ Examples
|
|||
|
||||
The first example shows the most common usage of :mod:`http.cookiejar`::
|
||||
|
||||
import http.cookiejar, urllib2
|
||||
import http.cookiejar, urllib.request
|
||||
cj = http.cookiejar.CookieJar()
|
||||
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
|
||||
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
|
||||
r = opener.open("http://example.com/")
|
||||
|
||||
This example illustrates how to open a URL using your Netscape, Mozilla, or Lynx
|
||||
cookies (assumes Unix/Netscape convention for location of the cookies file)::
|
||||
|
||||
import os, http.cookiejar, urllib2
|
||||
import os, http.cookiejar, urllib.request
|
||||
cj = http.cookiejar.MozillaCookieJar()
|
||||
cj.load(os.path.join(os.environ["HOME"], ".netscape/cookies.txt"))
|
||||
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
|
||||
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
|
||||
r = opener.open("http://example.com/")
|
||||
|
||||
The next example illustrates the use of :class:`DefaultCookiePolicy`. Turn on
|
||||
|
|
@ -734,12 +735,12 @@ RFC 2965 cookies, be more strict about domains when setting and returning
|
|||
Netscape cookies, and block some domains from setting cookies or having them
|
||||
returned::
|
||||
|
||||
import urllib2
|
||||
import urllib.request
|
||||
from http.cookiejar import CookieJar, DefaultCookiePolicy
|
||||
policy = DefaultCookiePolicy(
|
||||
rfc2965=True, strict_ns_domain=Policy.DomainStrict,
|
||||
blocked_domains=["ads.net", ".ads.net"])
|
||||
cj = CookieJar(policy)
|
||||
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
|
||||
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
|
||||
r = opener.open("http://example.com/")
|
||||
|
||||
|
|
|
|||
|
|
@ -1077,7 +1077,7 @@ Adding HTTP headers:
|
|||
|
||||
Use the *headers* argument to the :class:`Request` constructor, or::
|
||||
|
||||
import urllib
|
||||
import urllib.request
|
||||
req = urllib.request.Request('http://www.example.com/')
|
||||
req.add_header('Referer', 'http://www.python.org/')
|
||||
r = urllib.request.urlopen(req)
|
||||
|
|
@ -1085,7 +1085,7 @@ Use the *headers* argument to the :class:`Request` constructor, or::
|
|||
:class:`OpenerDirector` automatically adds a :mailheader:`User-Agent` header to
|
||||
every :class:`Request`. To change this::
|
||||
|
||||
import urllib
|
||||
import urllib.request
|
||||
opener = urllib.request.build_opener()
|
||||
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
|
||||
opener.open('http://www.example.com/')
|
||||
|
|
|
|||
|
|
@ -1305,7 +1305,7 @@ class CookieJar:
|
|||
return attrs
|
||||
|
||||
def add_cookie_header(self, request):
|
||||
"""Add correct Cookie: header to request (urllib2.Request object).
|
||||
"""Add correct Cookie: header to request (urllib.request.Request object).
|
||||
|
||||
The Cookie2 header is also added unless policy.hide_cookie2 is true.
|
||||
|
||||
|
|
|
|||
|
|
@ -1002,11 +1002,11 @@ class HTTPHandler(logging.Handler):
|
|||
Send the record to the Web server as an URL-encoded dictionary
|
||||
"""
|
||||
try:
|
||||
import http.client, urllib
|
||||
import http.client, urllib.parse
|
||||
host = self.host
|
||||
h = http.client.HTTP(host)
|
||||
url = self.url
|
||||
data = urllib.urlencode(self.mapLogRecord(record))
|
||||
data = urllib.parse.urlencode(self.mapLogRecord(record))
|
||||
if self.method == "GET":
|
||||
if (url.find('?') >= 0):
|
||||
sep = '&'
|
||||
|
|
|
|||
|
|
@ -47,24 +47,25 @@ _call_chain conventions
|
|||
|
||||
Example usage:
|
||||
|
||||
import urllib2
|
||||
import urllib.request
|
||||
|
||||
# set up authentication info
|
||||
authinfo = urllib2.HTTPBasicAuthHandler()
|
||||
authinfo = urllib.request.HTTPBasicAuthHandler()
|
||||
authinfo.add_password(realm='PDQ Application',
|
||||
uri='https://mahler:8092/site-updates.py',
|
||||
user='klem',
|
||||
passwd='geheim$parole')
|
||||
|
||||
proxy_support = urllib2.ProxyHandler({"http" : "http://ahad-haam:3128"})
|
||||
proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})
|
||||
|
||||
# build a new opener that adds authentication and caching FTP handlers
|
||||
opener = urllib2.build_opener(proxy_support, authinfo, urllib2.CacheFTPHandler)
|
||||
opener = urllib.request.build_opener(proxy_support, authinfo,
|
||||
urllib.request.CacheFTPHandler)
|
||||
|
||||
# install it
|
||||
urllib2.install_opener(opener)
|
||||
urllib.request.install_opener(opener)
|
||||
|
||||
f = urllib2.urlopen('http://www.python.org/')
|
||||
f = urllib.request.urlopen('http://www.python.org/')
|
||||
"""
|
||||
|
||||
# XXX issues:
|
||||
|
|
@ -502,7 +503,7 @@ class HTTPRedirectHandler(BaseHandler):
|
|||
|
||||
# Strictly (according to RFC 2616), 301 or 302 in response to
|
||||
# a POST MUST NOT cause a redirection without confirmation
|
||||
# from the user (of urllib2, in this case). In practice,
|
||||
# from the user (of urllib.request, in this case). In practice,
|
||||
# essentially all clients do redirect in this case, so we do
|
||||
# the same.
|
||||
# be conciliant with URIs containing a space
|
||||
|
|
@ -655,7 +656,7 @@ class ProxyHandler(BaseHandler):
|
|||
if proxy_type is None:
|
||||
proxy_type = orig_type
|
||||
if user and password:
|
||||
user_pass = '%s:%s' % (unquote(user),
|
||||
user_pass = '%s:%s' % (urllib.parse.unquote(user),
|
||||
urllib.parse.unquote(password))
|
||||
creds = base64.b64encode(user_pass.encode()).decode("ascii")
|
||||
req.add_header('Proxy-authorization', 'Basic ' + creds)
|
||||
|
|
@ -808,7 +809,7 @@ class ProxyBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler):
|
|||
|
||||
def http_error_407(self, req, fp, code, msg, headers):
|
||||
# http_error_auth_reqed requires that there is no userinfo component in
|
||||
# authority. Assume there isn't one, since urllib2 does not (and
|
||||
# authority. Assume there isn't one, since urllib.request does not (and
|
||||
# should not, RFC 3986 s. 3.2.1) support requests for URLs containing
|
||||
# userinfo.
|
||||
authority = req.get_host()
|
||||
|
|
@ -1194,7 +1195,7 @@ class FileHandler(BaseHandler):
|
|||
return urllib.response.addinfourl(open(localfile, 'rb'),
|
||||
headers, 'file:'+file)
|
||||
except OSError as msg:
|
||||
# urllib2 users shouldn't expect OSErrors coming from urlopen()
|
||||
# users shouldn't expect OSErrors coming from urlopen()
|
||||
raise urllib.error.URLError(msg)
|
||||
raise urllib.error.URLError('file not on local host')
|
||||
|
||||
|
|
|
|||
|
|
@ -9,7 +9,8 @@ bootstrap issues (/usr/bin/python is Python 2.3 on OSX 10.4)
|
|||
|
||||
Usage: see USAGE variable in the script.
|
||||
"""
|
||||
import platform, os, sys, getopt, textwrap, shutil, urllib2, stat, time, pwd
|
||||
import platform, os, sys, getopt, textwrap, shutil, stat, time, pwd
|
||||
import urllib.request
|
||||
import grp
|
||||
|
||||
INCLUDE_TIMESTAMP = 1
|
||||
|
|
@ -442,7 +443,7 @@ def downloadURL(url, fname):
|
|||
if KNOWNSIZES.get(url) == size:
|
||||
print("Using existing file for", url)
|
||||
return
|
||||
fpIn = urllib2.urlopen(url)
|
||||
fpIn = urllib.request.urlopen(url)
|
||||
fpOut = open(fname, 'wb')
|
||||
block = fpIn.read(10240)
|
||||
try:
|
||||
|
|
|
|||
|
|
@ -1889,7 +1889,6 @@ random Random variable generators
|
|||
re Regular Expressions.
|
||||
reprlib Redo repr() but with limits on most sizes.
|
||||
rlcompleter Word completion for GNU readline 2.0.
|
||||
robotparser Parse robots.txt files, useful for web spiders.
|
||||
sched A generally useful event scheduler class.
|
||||
shelve Manage shelves of pickled objects.
|
||||
shlex Lexical analyzer class for simple shell-like syntaxes.
|
||||
|
|
@ -1920,8 +1919,9 @@ turtle LogoMation-like turtle graphics
|
|||
types Define names for all type symbols in the std interpreter.
|
||||
tzparse Parse a timezone specification.
|
||||
unicodedata Interface to unicode properties.
|
||||
urllib Open an arbitrary URL.
|
||||
urlparse Parse URLs according to latest draft of standard.
|
||||
urllib.parse Parse URLs according to latest draft of standard.
|
||||
urllib.request Open an arbitrary URL.
|
||||
urllib.robotparser Parse robots.txt files, useful for web spiders.
|
||||
user Hook to allow user-specified customization code to run.
|
||||
uu UUencode/UUdecode.
|
||||
unittest Utilities for implementing unit testing.
|
||||
|
|
|
|||
Loading…
Reference in New Issue