summaryrefslogtreecommitdiffstats
path: root/Lib/urllib.py
diff options
context:
space:
mode:
authorChristian Heimes <christian@cheimes.de>2008-01-20 15:14:11 (GMT)
committerChristian Heimes <christian@cheimes.de>2008-01-20 15:14:11 (GMT)
commit9bd667ad030913ead3a789f45e73c26f9f28fb46 (patch)
treeea9c145cdcc74d4f1b0b084b083f9286a878c513 /Lib/urllib.py
parent78b11870a4c441e42cf60dca3a6d22f5896311ba (diff)
downloadcpython-9bd667ad030913ead3a789f45e73c26f9f28fb46.zip
cpython-9bd667ad030913ead3a789f45e73c26f9f28fb46.tar.gz
cpython-9bd667ad030913ead3a789f45e73c26f9f28fb46.tar.bz2
Merged revisions 60124-60142 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk ........ r60131 | georg.brandl | 2008-01-20 12:13:29 +0100 (Sun, 20 Jan 2008) | 3 lines #1351692: in pprint, always call format() for dict and list items to enable custom formatting of contents via subclassing PrettyPrinter. ........ r60133 | georg.brandl | 2008-01-20 12:43:03 +0100 (Sun, 20 Jan 2008) | 2 lines #1178141: add addinfourl.code to get http status code from urllib. ........ r60134 | georg.brandl | 2008-01-20 13:05:43 +0100 (Sun, 20 Jan 2008) | 4 lines #856047: respect the ``no_proxy`` env var when checking for proxies in urllib and using the other ``_proxy`` env vars. Original patch by Donovan Baarda. ........ r60135 | georg.brandl | 2008-01-20 13:18:17 +0100 (Sun, 20 Jan 2008) | 4 lines #1664522: in urllib, don't read non-existing directories in ftp mode, returning a 0-byte file -- raise an IOError instead. Original patch from Phil Knirsch. ........ r60136 | georg.brandl | 2008-01-20 13:57:47 +0100 (Sun, 20 Jan 2008) | 2 lines #799369: document possible sys.platform values. ........ r60137 | georg.brandl | 2008-01-20 14:08:37 +0100 (Sun, 20 Jan 2008) | 2 lines #652749: document the constants added to the builtins by site.py. ........ r60138 | georg.brandl | 2008-01-20 14:59:46 +0100 (Sun, 20 Jan 2008) | 2 lines #1648: add sys.gettrace() and sys.getprofile(). ........ r60139 | georg.brandl | 2008-01-20 15:17:42 +0100 (Sun, 20 Jan 2008) | 2 lines #1669: don't allow shutil.rmtree() to be called on a symlink. ........ r60140 | georg.brandl | 2008-01-20 15:20:02 +0100 (Sun, 20 Jan 2008) | 2 lines Fix test_pyclbr after urllib change. ........ r60141 | christian.heimes | 2008-01-20 15:28:28 +0100 (Sun, 20 Jan 2008) | 1 line Fixed a wrong assumption in configure.in and Include/pyport.h. The is finite function is not called isfinite() but finite(). Sorry, my fault. :) ........ r60142 | georg.brandl | 2008-01-20 15:31:27 +0100 (Sun, 20 Jan 2008) | 2 lines #1876: fix typos in test_operator. ........
Diffstat (limited to 'Lib/urllib.py')
-rw-r--r--Lib/urllib.py76
1 files changed, 63 insertions, 13 deletions
diff --git a/Lib/urllib.py b/Lib/urllib.py
index 1b1fc40..f9c8ec0 100644
--- a/Lib/urllib.py
+++ b/Lib/urllib.py
@@ -557,7 +557,7 @@ class FancyURLopener(URLopener):
def http_error_default(self, url, fp, errcode, errmsg, headers):
"""Default error handling -- don't raise an exception."""
- return addinfourl(fp, headers, "http:" + url)
+ return addinfourl(fp, headers, "http:" + url, errcode)
def http_error_302(self, url, fp, errcode, errmsg, headers, data=None):
"""Error 302 -- relocated (temporarily)."""
@@ -815,9 +815,19 @@ class ftpwrapper:
if not conn:
# Set transfer mode to ASCII!
self.ftp.voidcmd('TYPE A')
- # Try a directory listing
- if file: cmd = 'LIST ' + file
- else: cmd = 'LIST'
+ # Try a directory listing. Verify that directory exists.
+ if file:
+ pwd = self.ftp.pwd()
+ try:
+ try:
+ self.ftp.cwd(file)
+ except ftplib.error_perm as reason:
+ raise IOError('ftp error', reason) from reason
+ finally:
+ self.ftp.cwd(pwd)
+ cmd = 'LIST ' + file
+ else:
+ cmd = 'LIST'
conn = self.ftp.ntransfercmd(cmd)
self.busy = 1
# Pass back both a suitably decorated object and a retrieval length
@@ -898,14 +908,18 @@ class addinfo(addbase):
class addinfourl(addbase):
"""class to add info() and geturl() methods to an open file."""
- def __init__(self, fp, headers, url):
+ def __init__(self, fp, headers, url, code=None):
addbase.__init__(self, fp)
self.headers = headers
self.url = url
+ self.code = code
def info(self):
return self.headers
+ def getcode(self):
+ return self.code
+
def geturl(self):
return self.url
@@ -1228,10 +1242,33 @@ def getproxies_environment():
proxies = {}
for name, value in os.environ.items():
name = name.lower()
+ if name == 'no_proxy':
+ # handled in proxy_bypass_environment
+ continue
if value and name[-6:] == '_proxy':
proxies[name[:-6]] = value
return proxies
+def proxy_bypass_environment(host):
+ """Test if proxies should not be used for a particular host.
+
+ Checks the environment for a variable named no_proxy, which should
+ be a list of DNS suffixes separated by commas, or '*' for all hosts.
+ """
+ no_proxy = os.environ.get('no_proxy', '') or os.environ.get('NO_PROXY', '')
+ # '*' is special case for always bypass
+ if no_proxy == '*':
+ return 1
+ # strip port off host
+ hostonly, port = splitport(host)
+ # check if the host ends with any of the DNS suffixes
+ for name in no_proxy.split(','):
+ if name and (hostonly.endswith(name) or host.endswith(name)):
+ return 1
+ # otherwise, don't bypass
+ return 0
+
+
if sys.platform == 'darwin':
def getproxies_internetconfig():
"""Return a dictionary of scheme -> proxy server URL mappings.
@@ -1259,12 +1296,15 @@ if sys.platform == 'darwin':
pass
else:
proxies['http'] = 'http://%s' % value
- # FTP: XXXX To be done.
- # Gopher: XXXX To be done.
+ # FTP: XXX To be done.
+ # Gopher: XXX To be done.
return proxies
- def proxy_bypass(x):
- return 0
+ def proxy_bypass(host):
+ if getproxies_environment():
+ return proxy_bypass_environment(host)
+ else:
+ return 0
def getproxies():
return getproxies_environment() or getproxies_internetconfig()
@@ -1324,7 +1364,7 @@ elif os.name == 'nt':
"""
return getproxies_environment() or getproxies_registry()
- def proxy_bypass(host):
+ def proxy_bypass_registry(host):
try:
import _winreg
import re
@@ -1383,12 +1423,22 @@ elif os.name == 'nt':
return 1
return 0
+ def proxy_bypass(host):
+ """Return a dictionary of scheme -> proxy server URL mappings.
+
+ Returns settings gathered from the environment, if specified,
+ or the registry.
+
+ """
+ if getproxies_environment():
+ return proxy_bypass_environment(host)
+ else:
+ return proxy_bypass_registry(host)
+
else:
# By default use environment variables
getproxies = getproxies_environment
-
- def proxy_bypass(host):
- return 0
+ proxy_bypass = proxy_bypass_environment
# Test and time quote() and unquote()
def test1():