1994-03-22 12:05:32 +00:00
|
|
|
# Open an arbitrary URL
|
|
|
|
#
|
1997-02-10 17:51:56 +00:00
|
|
|
# See the following document for more info on URLs:
|
|
|
|
# "Names and Addresses, URIs, URLs, URNs, URCs", at
|
|
|
|
# http://www.w3.org/pub/WWW/Addressing/Overview.html
|
|
|
|
#
|
|
|
|
# See also the HTTP spec (from which the error codes are derived):
|
|
|
|
# "HTTP - Hypertext Transfer Protocol", at
|
|
|
|
# http://www.w3.org/pub/WWW/Protocols/
|
|
|
|
#
|
|
|
|
# Related standards and specs:
|
|
|
|
# - RFC1808: the "relative URL" spec. (authoritative status)
|
|
|
|
# - RFC1738 - the "URL standard". (authoritative status)
|
|
|
|
# - RFC1630 - the "URI spec". (informational status)
|
1994-03-22 12:05:32 +00:00
|
|
|
#
|
|
|
|
# The object returned by URLopener().open(file) will differ per
|
|
|
|
# protocol. All you know is that is has methods read(), readline(),
|
|
|
|
# readlines(), fileno(), close() and info(). The read*(), fileno()
|
|
|
|
# and close() methods work like those of open files.
|
1997-02-10 17:51:56 +00:00
|
|
|
# The info() method returns a mimetools.Message object which can be
|
1994-03-22 12:05:32 +00:00
|
|
|
# used to query various info about the object, if available.
|
1995-08-04 04:29:05 +00:00
|
|
|
# (mimetools.Message objects are queried with the getheader() method.)
|
1994-03-22 12:05:32 +00:00
|
|
|
|
1994-07-04 22:14:49 +00:00
|
|
|
import string
|
1994-03-22 12:05:32 +00:00
|
|
|
import socket
|
1995-12-15 13:22:13 +00:00
|
|
|
import os
|
1996-11-20 22:02:24 +00:00
|
|
|
import sys
|
1994-03-22 12:05:32 +00:00
|
|
|
|
|
|
|
|
1997-10-27 18:56:19 +00:00
|
|
|
__version__ = '1.9'
|
1997-06-06 21:11:11 +00:00
|
|
|
|
|
|
|
MAXFTPCACHE = 10 # Trim the ftp cache beyond this size
|
1995-06-22 19:00:13 +00:00
|
|
|
|
1995-12-15 13:22:13 +00:00
|
|
|
# Helper for non-unix systems
|
|
|
|
if os.name == 'mac':
|
1996-03-21 16:31:41 +00:00
|
|
|
from macurl2path import url2pathname, pathname2url
|
1996-06-26 19:47:37 +00:00
|
|
|
elif os.name == 'nt':
|
|
|
|
from nturl2path import url2pathname, pathname2url
|
1995-12-15 13:22:13 +00:00
|
|
|
else:
|
1995-12-21 15:43:53 +00:00
|
|
|
def url2pathname(pathname):
|
|
|
|
return pathname
|
|
|
|
def pathname2url(pathname):
|
1995-12-15 13:22:13 +00:00
|
|
|
return pathname
|
1995-06-22 19:00:13 +00:00
|
|
|
|
1994-03-22 12:05:32 +00:00
|
|
|
# This really consists of two pieces:
|
|
|
|
# (1) a class which handles opening of all sorts of URLs
|
|
|
|
# (plus assorted utilities etc.)
|
|
|
|
# (2) a set of functions for parsing URLs
|
|
|
|
# XXX Should these be separated out into different modules?
|
|
|
|
|
|
|
|
|
|
|
|
# Shortcut for basic usage
|
|
|
|
_urlopener = None
|
1996-12-10 16:00:28 +00:00
|
|
|
def urlopen(url, data=None):
|
1994-03-22 12:05:32 +00:00
|
|
|
global _urlopener
|
|
|
|
if not _urlopener:
|
1995-08-04 04:29:05 +00:00
|
|
|
_urlopener = FancyURLopener()
|
1996-12-10 16:00:28 +00:00
|
|
|
if data is None:
|
|
|
|
return _urlopener.open(url)
|
|
|
|
else:
|
|
|
|
return _urlopener.open(url, data)
|
1996-06-11 00:16:27 +00:00
|
|
|
def urlretrieve(url, filename=None):
|
1994-03-22 12:05:32 +00:00
|
|
|
global _urlopener
|
|
|
|
if not _urlopener:
|
1995-08-04 04:29:05 +00:00
|
|
|
_urlopener = FancyURLopener()
|
1996-06-11 00:16:27 +00:00
|
|
|
if filename:
|
|
|
|
return _urlopener.retrieve(url, filename)
|
|
|
|
else:
|
|
|
|
return _urlopener.retrieve(url)
|
1994-03-22 12:05:32 +00:00
|
|
|
def urlcleanup():
|
|
|
|
if _urlopener:
|
|
|
|
_urlopener.cleanup()
|
|
|
|
|
|
|
|
|
|
|
|
# Class to open URLs.
|
|
|
|
# This is a class rather than just a subroutine because we may need
|
|
|
|
# more than one set of global protocol-specific options.
|
1995-08-04 04:29:05 +00:00
|
|
|
# Note -- this is a base class for those who don't want the
|
|
|
|
# automatic handling of errors type 302 (relocated) and 401
|
|
|
|
# (authorization needed).
|
1994-03-22 12:05:32 +00:00
|
|
|
ftpcache = {}
|
|
|
|
class URLopener:
|
|
|
|
|
1997-10-27 18:56:19 +00:00
|
|
|
__tempfiles = None
|
1996-11-27 19:39:58 +00:00
|
|
|
|
1994-03-22 12:05:32 +00:00
|
|
|
# Constructor
|
1996-03-20 15:33:11 +00:00
|
|
|
def __init__(self, proxies=None):
|
|
|
|
if proxies is None:
|
|
|
|
proxies = getproxies()
|
1997-11-18 15:50:39 +00:00
|
|
|
assert hasattr(proxies, 'has_key'), "proxies must be a mapping"
|
1996-03-20 15:33:11 +00:00
|
|
|
self.proxies = proxies
|
1995-06-22 19:00:13 +00:00
|
|
|
server_version = "Python-urllib/%s" % __version__
|
|
|
|
self.addheaders = [('User-agent', server_version)]
|
1997-09-08 02:16:33 +00:00
|
|
|
self.__tempfiles = []
|
1997-10-27 18:56:19 +00:00
|
|
|
self.__unlink = os.unlink # See cleanup()
|
1994-08-23 13:32:20 +00:00
|
|
|
self.tempcache = None
|
|
|
|
# Undocumented feature: if you assign {} to tempcache,
|
|
|
|
# it is used to cache files retrieved with
|
|
|
|
# self.retrieve(). This is not enabled by default
|
|
|
|
# since it does not work for changing documents (and I
|
|
|
|
# haven't got the logic to check expiration headers
|
|
|
|
# yet).
|
1994-03-22 12:05:32 +00:00
|
|
|
self.ftpcache = ftpcache
|
|
|
|
# Undocumented feature: you can use a different
|
|
|
|
# ftp cache by assigning to the .ftpcache member;
|
|
|
|
# in case you want logically independent URL openers
|
|
|
|
|
|
|
|
def __del__(self):
|
|
|
|
self.close()
|
|
|
|
|
|
|
|
def close(self):
|
|
|
|
self.cleanup()
|
|
|
|
|
|
|
|
def cleanup(self):
|
1997-10-27 18:56:19 +00:00
|
|
|
# This code sometimes runs when the rest of this module
|
|
|
|
# has already been deleted, so it can't use any globals
|
|
|
|
# or import anything.
|
1997-09-03 22:36:15 +00:00
|
|
|
if self.__tempfiles:
|
|
|
|
for file in self.__tempfiles:
|
1994-08-23 13:32:20 +00:00
|
|
|
try:
|
1997-10-27 18:56:19 +00:00
|
|
|
self.__unlink(file)
|
|
|
|
except:
|
1994-08-23 13:32:20 +00:00
|
|
|
pass
|
1997-10-27 18:56:19 +00:00
|
|
|
del self.__tempfiles[:]
|
|
|
|
if self.tempcache:
|
|
|
|
self.tempcache.clear()
|
1994-03-22 12:05:32 +00:00
|
|
|
|
|
|
|
# Add a header to be used by the HTTP interface only
|
|
|
|
# e.g. u.addheader('Accept', 'sound/basic')
|
|
|
|
def addheader(self, *args):
|
|
|
|
self.addheaders.append(args)
|
|
|
|
|
|
|
|
# External interface
|
|
|
|
# Use URLopener().open(file) instead of open(file, 'r')
|
1996-12-10 16:00:28 +00:00
|
|
|
def open(self, fullurl, data=None):
|
1995-08-29 19:19:12 +00:00
|
|
|
fullurl = unwrap(fullurl)
|
|
|
|
type, url = splittype(fullurl)
|
1994-03-22 12:05:32 +00:00
|
|
|
if not type: type = 'file'
|
1996-09-10 17:02:56 +00:00
|
|
|
self.openedurl = '%s:%s' % (type, url)
|
1996-03-20 15:33:11 +00:00
|
|
|
if self.proxies.has_key(type):
|
|
|
|
proxy = self.proxies[type]
|
|
|
|
type, proxy = splittype(proxy)
|
|
|
|
host, selector = splithost(proxy)
|
|
|
|
url = (host, fullurl) # Signal special case to open_*()
|
1994-03-22 12:05:32 +00:00
|
|
|
name = 'open_' + type
|
|
|
|
if '-' in name:
|
1997-09-29 23:23:46 +00:00
|
|
|
# replace - with _
|
|
|
|
name = string.join(string.split(name, '-'), '_')
|
1994-03-22 12:05:32 +00:00
|
|
|
if not hasattr(self, name):
|
1996-12-10 16:00:28 +00:00
|
|
|
if data is None:
|
|
|
|
return self.open_unknown(fullurl)
|
|
|
|
else:
|
|
|
|
return self.open_unknown(fullurl, data)
|
1994-03-22 12:05:32 +00:00
|
|
|
try:
|
1996-12-10 16:00:28 +00:00
|
|
|
if data is None:
|
|
|
|
return getattr(self, name)(url)
|
|
|
|
else:
|
|
|
|
return getattr(self, name)(url, data)
|
1994-03-22 12:05:32 +00:00
|
|
|
except socket.error, msg:
|
1997-09-29 23:23:46 +00:00
|
|
|
raise IOError, ('socket error', msg), sys.exc_info()[2]
|
1994-03-22 12:05:32 +00:00
|
|
|
|
1995-08-29 19:19:12 +00:00
|
|
|
# Overridable interface to open unknown URL type
|
1996-12-10 16:00:28 +00:00
|
|
|
def open_unknown(self, fullurl, data=None):
|
1995-08-29 19:19:12 +00:00
|
|
|
type, url = splittype(fullurl)
|
|
|
|
raise IOError, ('url error', 'unknown url type', type)
|
|
|
|
|
1994-03-22 12:05:32 +00:00
|
|
|
# External interface
|
|
|
|
# retrieve(url) returns (filename, None) for a local object
|
|
|
|
# or (tempfilename, headers) for a remote object
|
1996-06-11 00:16:27 +00:00
|
|
|
def retrieve(self, url, filename=None):
|
1994-08-23 13:32:20 +00:00
|
|
|
if self.tempcache and self.tempcache.has_key(url):
|
1994-03-22 12:05:32 +00:00
|
|
|
return self.tempcache[url]
|
|
|
|
url1 = unwrap(url)
|
1996-10-22 13:28:37 +00:00
|
|
|
self.openedurl = url1
|
1994-08-23 13:32:20 +00:00
|
|
|
if self.tempcache and self.tempcache.has_key(url1):
|
1994-03-22 12:05:32 +00:00
|
|
|
self.tempcache[url] = self.tempcache[url1]
|
|
|
|
return self.tempcache[url1]
|
|
|
|
type, url1 = splittype(url1)
|
1996-06-11 00:16:27 +00:00
|
|
|
if not filename and (not type or type == 'file'):
|
1994-03-22 12:05:32 +00:00
|
|
|
try:
|
|
|
|
fp = self.open_local_file(url1)
|
|
|
|
del fp
|
1995-12-21 15:43:53 +00:00
|
|
|
return url2pathname(splithost(url1)[1]), None
|
1994-03-22 12:05:32 +00:00
|
|
|
except IOError, msg:
|
|
|
|
pass
|
|
|
|
fp = self.open(url)
|
|
|
|
headers = fp.info()
|
1996-06-11 00:16:27 +00:00
|
|
|
if not filename:
|
|
|
|
import tempfile
|
|
|
|
filename = tempfile.mktemp()
|
1997-09-03 22:36:15 +00:00
|
|
|
self.__tempfiles.append(filename)
|
1996-06-11 00:16:27 +00:00
|
|
|
result = filename, headers
|
1994-08-23 13:32:20 +00:00
|
|
|
if self.tempcache is not None:
|
1994-09-21 11:36:19 +00:00
|
|
|
self.tempcache[url] = result
|
1997-04-11 19:01:48 +00:00
|
|
|
tfp = open(filename, 'wb')
|
1994-03-22 12:05:32 +00:00
|
|
|
bs = 1024*8
|
|
|
|
block = fp.read(bs)
|
|
|
|
while block:
|
|
|
|
tfp.write(block)
|
|
|
|
block = fp.read(bs)
|
1997-08-26 19:06:40 +00:00
|
|
|
fp.close()
|
|
|
|
tfp.close()
|
1994-03-22 12:05:32 +00:00
|
|
|
del fp
|
|
|
|
del tfp
|
|
|
|
return result
|
|
|
|
|
|
|
|
# Each method named open_<type> knows how to open that type of URL
|
|
|
|
|
|
|
|
# Use HTTP protocol
|
1996-12-10 16:00:28 +00:00
|
|
|
def open_http(self, url, data=None):
|
1994-03-22 12:05:32 +00:00
|
|
|
import httplib
|
1996-03-20 15:33:11 +00:00
|
|
|
if type(url) is type(""):
|
|
|
|
host, selector = splithost(url)
|
1996-08-26 18:09:59 +00:00
|
|
|
user_passwd, host = splituser(host)
|
1997-06-03 14:34:19 +00:00
|
|
|
realhost = host
|
1996-03-20 15:33:11 +00:00
|
|
|
else:
|
|
|
|
host, selector = url
|
1996-08-26 18:09:59 +00:00
|
|
|
urltype, rest = splittype(selector)
|
1997-04-02 05:46:35 +00:00
|
|
|
user_passwd = None
|
1997-06-03 14:34:19 +00:00
|
|
|
if string.lower(urltype) != 'http':
|
|
|
|
realhost = None
|
|
|
|
else:
|
1996-08-26 18:09:59 +00:00
|
|
|
realhost, rest = splithost(rest)
|
|
|
|
user_passwd, realhost = splituser(realhost)
|
|
|
|
if user_passwd:
|
|
|
|
selector = "%s://%s%s" % (urltype,
|
|
|
|
realhost, rest)
|
1997-04-02 05:46:35 +00:00
|
|
|
#print "proxy via http:", host, selector
|
1994-04-18 09:39:56 +00:00
|
|
|
if not host: raise IOError, ('http error', 'no host given')
|
1995-08-04 04:29:05 +00:00
|
|
|
if user_passwd:
|
|
|
|
import base64
|
|
|
|
auth = string.strip(base64.encodestring(user_passwd))
|
|
|
|
else:
|
|
|
|
auth = None
|
1994-03-22 12:05:32 +00:00
|
|
|
h = httplib.HTTP(host)
|
1996-12-10 16:00:28 +00:00
|
|
|
if data is not None:
|
|
|
|
h.putrequest('POST', selector)
|
|
|
|
h.putheader('Content-type',
|
|
|
|
'application/x-www-form-urlencoded')
|
|
|
|
h.putheader('Content-length', '%d' % len(data))
|
|
|
|
else:
|
|
|
|
h.putrequest('GET', selector)
|
1996-11-11 19:01:17 +00:00
|
|
|
if auth: h.putheader('Authorization', 'Basic %s' % auth)
|
1997-06-03 14:34:19 +00:00
|
|
|
if realhost: h.putheader('Host', realhost)
|
1994-03-22 12:05:32 +00:00
|
|
|
for args in self.addheaders: apply(h.putheader, args)
|
1995-06-22 19:00:13 +00:00
|
|
|
h.endheaders()
|
1996-12-10 16:00:28 +00:00
|
|
|
if data is not None:
|
|
|
|
h.send(data + '\r\n')
|
1994-03-22 12:05:32 +00:00
|
|
|
errcode, errmsg, headers = h.getreply()
|
1995-06-22 19:00:13 +00:00
|
|
|
fp = h.getfile()
|
|
|
|
if errcode == 200:
|
1996-09-10 17:02:56 +00:00
|
|
|
return addinfourl(fp, headers, self.openedurl)
|
1995-06-22 19:00:13 +00:00
|
|
|
else:
|
1995-08-04 04:29:05 +00:00
|
|
|
return self.http_error(url,
|
|
|
|
fp, errcode, errmsg, headers)
|
|
|
|
|
|
|
|
# Handle http errors.
|
|
|
|
# Derived class can override this, or provide specific handlers
|
|
|
|
# named http_error_DDD where DDD is the 3-digit error code
|
|
|
|
def http_error(self, url, fp, errcode, errmsg, headers):
|
|
|
|
# First check if there's a specific handler for this error
|
|
|
|
name = 'http_error_%d' % errcode
|
|
|
|
if hasattr(self, name):
|
|
|
|
method = getattr(self, name)
|
|
|
|
result = method(url, fp, errcode, errmsg, headers)
|
|
|
|
if result: return result
|
|
|
|
return self.http_error_default(
|
|
|
|
url, fp, errcode, errmsg, headers)
|
|
|
|
|
|
|
|
# Default http error handler: close the connection and raises IOError
|
|
|
|
def http_error_default(self, url, fp, errcode, errmsg, headers):
|
|
|
|
void = fp.read()
|
|
|
|
fp.close()
|
|
|
|
raise IOError, ('http error', errcode, errmsg, headers)
|
1994-03-22 12:05:32 +00:00
|
|
|
|
|
|
|
# Use Gopher protocol
|
|
|
|
def open_gopher(self, url):
|
|
|
|
import gopherlib
|
|
|
|
host, selector = splithost(url)
|
1994-04-18 09:39:56 +00:00
|
|
|
if not host: raise IOError, ('gopher error', 'no host given')
|
1994-03-22 12:05:32 +00:00
|
|
|
type, selector = splitgophertype(selector)
|
|
|
|
selector, query = splitquery(selector)
|
1994-07-04 22:14:49 +00:00
|
|
|
selector = unquote(selector)
|
|
|
|
if query:
|
|
|
|
query = unquote(query)
|
|
|
|
fp = gopherlib.send_query(selector, query, host)
|
|
|
|
else:
|
|
|
|
fp = gopherlib.send_selector(selector, host)
|
1996-09-10 17:02:56 +00:00
|
|
|
return addinfourl(fp, noheaders(), self.openedurl)
|
1994-03-22 12:05:32 +00:00
|
|
|
|
|
|
|
# Use local file or FTP depending on form of URL
|
|
|
|
def open_file(self, url):
|
1997-08-20 23:34:01 +00:00
|
|
|
if url[:2] == '//' and url[2:3] != '/':
|
|
|
|
return self.open_ftp(url)
|
|
|
|
else:
|
|
|
|
return self.open_local_file(url)
|
1994-03-22 12:05:32 +00:00
|
|
|
|
|
|
|
# Use local file
|
|
|
|
def open_local_file(self, url):
|
|
|
|
host, file = splithost(url)
|
1996-10-10 16:01:16 +00:00
|
|
|
if not host:
|
1997-06-06 17:44:07 +00:00
|
|
|
return addinfourl(
|
|
|
|
open(url2pathname(file), 'rb'),
|
|
|
|
noheaders(), 'file:'+file)
|
1994-03-22 12:05:32 +00:00
|
|
|
host, port = splitport(host)
|
|
|
|
if not port and socket.gethostbyname(host) in (
|
|
|
|
localhost(), thishost()):
|
1994-07-04 22:14:49 +00:00
|
|
|
file = unquote(file)
|
1997-06-06 17:44:07 +00:00
|
|
|
return addinfourl(
|
|
|
|
open(url2pathname(file), 'rb'),
|
|
|
|
noheaders(), 'file:'+file)
|
1994-03-22 12:05:32 +00:00
|
|
|
raise IOError, ('local file error', 'not on local host')
|
|
|
|
|
|
|
|
# Use FTP protocol
|
|
|
|
def open_ftp(self, url):
|
1994-07-04 22:14:49 +00:00
|
|
|
host, path = splithost(url)
|
1994-03-22 12:05:32 +00:00
|
|
|
if not host: raise IOError, ('ftp error', 'no host given')
|
|
|
|
host, port = splitport(host)
|
1994-07-04 22:14:49 +00:00
|
|
|
user, host = splituser(host)
|
|
|
|
if user: user, passwd = splitpasswd(user)
|
|
|
|
else: passwd = None
|
1994-03-22 12:05:32 +00:00
|
|
|
host = socket.gethostbyname(host)
|
|
|
|
if not port:
|
|
|
|
import ftplib
|
|
|
|
port = ftplib.FTP_PORT
|
1997-12-02 20:26:21 +00:00
|
|
|
else:
|
|
|
|
port = int(port)
|
1994-07-04 22:14:49 +00:00
|
|
|
path, attrs = splitattr(path)
|
|
|
|
dirs = string.splitfields(path, '/')
|
|
|
|
dirs, file = dirs[:-1], dirs[-1]
|
|
|
|
if dirs and not dirs[0]: dirs = dirs[1:]
|
|
|
|
key = (user, host, port, string.joinfields(dirs, '/'))
|
1997-06-06 21:11:11 +00:00
|
|
|
if len(self.ftpcache) > MAXFTPCACHE:
|
|
|
|
# Prune the cache, rather arbitrarily
|
|
|
|
for k in self.ftpcache.keys():
|
|
|
|
if k != key:
|
|
|
|
v = self.ftpcache[k]
|
|
|
|
del self.ftpcache[k]
|
|
|
|
v.close()
|
1994-03-22 12:05:32 +00:00
|
|
|
try:
|
|
|
|
if not self.ftpcache.has_key(key):
|
1994-07-04 22:14:49 +00:00
|
|
|
self.ftpcache[key] = \
|
|
|
|
ftpwrapper(user, passwd,
|
|
|
|
host, port, dirs)
|
|
|
|
if not file: type = 'D'
|
|
|
|
else: type = 'I'
|
|
|
|
for attr in attrs:
|
|
|
|
attr, value = splitvalue(attr)
|
|
|
|
if string.lower(attr) == 'type' and \
|
|
|
|
value in ('a', 'A', 'i', 'I', 'd', 'D'):
|
|
|
|
type = string.upper(value)
|
1997-06-06 17:44:07 +00:00
|
|
|
return addinfourl(
|
|
|
|
self.ftpcache[key].retrfile(file, type),
|
|
|
|
noheaders(), self.openedurl)
|
1994-03-22 12:05:32 +00:00
|
|
|
except ftperrors(), msg:
|
1997-09-29 23:23:46 +00:00
|
|
|
raise IOError, ('ftp error', msg), sys.exc_info()[2]
|
1994-03-22 12:05:32 +00:00
|
|
|
|
|
|
|
|
1995-08-04 04:29:05 +00:00
|
|
|
# Derived class with handlers for errors we can handle (perhaps)
|
|
|
|
class FancyURLopener(URLopener):
|
|
|
|
|
|
|
|
def __init__(self, *args):
|
|
|
|
apply(URLopener.__init__, (self,) + args)
|
|
|
|
self.auth_cache = {}
|
|
|
|
|
|
|
|
# Default error handling -- don't raise an exception
|
|
|
|
def http_error_default(self, url, fp, errcode, errmsg, headers):
|
1996-09-10 17:02:56 +00:00
|
|
|
return addinfourl(fp, headers, self.openedurl)
|
1995-08-04 04:29:05 +00:00
|
|
|
|
1996-09-10 17:02:56 +00:00
|
|
|
# Error 302 -- relocated (temporarily)
|
1995-08-04 04:29:05 +00:00
|
|
|
def http_error_302(self, url, fp, errcode, errmsg, headers):
|
|
|
|
# XXX The server can force infinite recursion here!
|
|
|
|
if headers.has_key('location'):
|
|
|
|
newurl = headers['location']
|
|
|
|
elif headers.has_key('uri'):
|
|
|
|
newurl = headers['uri']
|
|
|
|
else:
|
|
|
|
return
|
|
|
|
void = fp.read()
|
|
|
|
fp.close()
|
|
|
|
return self.open(newurl)
|
|
|
|
|
1996-09-10 17:02:56 +00:00
|
|
|
# Error 301 -- also relocated (permanently)
|
|
|
|
http_error_301 = http_error_302
|
|
|
|
|
1995-08-04 04:29:05 +00:00
|
|
|
# Error 401 -- authentication required
|
|
|
|
# See this URL for a description of the basic authentication scheme:
|
|
|
|
# http://www.ics.uci.edu/pub/ietf/http/draft-ietf-http-v10-spec-00.txt
|
|
|
|
def http_error_401(self, url, fp, errcode, errmsg, headers):
|
|
|
|
if headers.has_key('www-authenticate'):
|
|
|
|
stuff = headers['www-authenticate']
|
1997-09-29 23:23:46 +00:00
|
|
|
import re
|
|
|
|
match = re.match(
|
|
|
|
'[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff)
|
|
|
|
if match:
|
1998-02-05 16:21:28 +00:00
|
|
|
scheme, realm = match.groups()
|
1995-08-04 04:29:05 +00:00
|
|
|
if string.lower(scheme) == 'basic':
|
|
|
|
return self.retry_http_basic_auth(
|
|
|
|
url, realm)
|
|
|
|
|
|
|
|
def retry_http_basic_auth(self, url, realm):
|
|
|
|
host, selector = splithost(url)
|
|
|
|
i = string.find(host, '@') + 1
|
|
|
|
host = host[i:]
|
|
|
|
user, passwd = self.get_user_passwd(host, realm, i)
|
|
|
|
if not (user or passwd): return None
|
|
|
|
host = user + ':' + passwd + '@' + host
|
|
|
|
newurl = '//' + host + selector
|
|
|
|
return self.open_http(newurl)
|
|
|
|
|
|
|
|
def get_user_passwd(self, host, realm, clear_cache = 0):
|
|
|
|
key = realm + '@' + string.lower(host)
|
|
|
|
if self.auth_cache.has_key(key):
|
|
|
|
if clear_cache:
|
|
|
|
del self.auth_cache[key]
|
|
|
|
else:
|
|
|
|
return self.auth_cache[key]
|
|
|
|
user, passwd = self.prompt_user_passwd(host, realm)
|
|
|
|
if user or passwd: self.auth_cache[key] = (user, passwd)
|
|
|
|
return user, passwd
|
|
|
|
|
|
|
|
def prompt_user_passwd(self, host, realm):
|
|
|
|
# Override this in a GUI environment!
|
|
|
|
try:
|
|
|
|
user = raw_input("Enter username for %s at %s: " %
|
|
|
|
(realm, host))
|
|
|
|
self.echo_off()
|
|
|
|
try:
|
|
|
|
passwd = raw_input(
|
|
|
|
"Enter password for %s in %s at %s: " %
|
|
|
|
(user, realm, host))
|
|
|
|
finally:
|
|
|
|
self.echo_on()
|
|
|
|
return user, passwd
|
|
|
|
except KeyboardInterrupt:
|
|
|
|
return None, None
|
|
|
|
|
|
|
|
def echo_off(self):
|
1998-02-05 16:21:28 +00:00
|
|
|
# XXX Is this sufficient???
|
|
|
|
if hasattr(os, "system"):
|
|
|
|
os.system("stty -echo")
|
1995-08-04 04:29:05 +00:00
|
|
|
|
|
|
|
def echo_on(self):
|
1998-02-05 16:21:28 +00:00
|
|
|
# XXX Is this sufficient???
|
|
|
|
if hasattr(os, "system"):
|
|
|
|
print
|
|
|
|
os.system("stty echo")
|
1995-08-04 04:29:05 +00:00
|
|
|
|
|
|
|
|
1994-03-22 12:05:32 +00:00
|
|
|
# Utility functions
|
|
|
|
|
|
|
|
# Return the IP address of the magic hostname 'localhost'
|
|
|
|
_localhost = None
|
|
|
|
def localhost():
|
|
|
|
global _localhost
|
|
|
|
if not _localhost:
|
|
|
|
_localhost = socket.gethostbyname('localhost')
|
|
|
|
return _localhost
|
|
|
|
|
|
|
|
# Return the IP address of the current host
|
|
|
|
_thishost = None
|
|
|
|
def thishost():
|
|
|
|
global _thishost
|
|
|
|
if not _thishost:
|
|
|
|
_thishost = socket.gethostbyname(socket.gethostname())
|
|
|
|
return _thishost
|
|
|
|
|
|
|
|
# Return the set of errors raised by the FTP class
|
|
|
|
_ftperrors = None
|
|
|
|
def ftperrors():
|
|
|
|
global _ftperrors
|
|
|
|
if not _ftperrors:
|
|
|
|
import ftplib
|
1997-06-06 17:44:07 +00:00
|
|
|
_ftperrors = ftplib.all_errors
|
1994-03-22 12:05:32 +00:00
|
|
|
return _ftperrors
|
|
|
|
|
1995-08-04 04:29:05 +00:00
|
|
|
# Return an empty mimetools.Message object
|
1994-03-22 12:05:32 +00:00
|
|
|
_noheaders = None
|
|
|
|
def noheaders():
|
|
|
|
global _noheaders
|
|
|
|
if not _noheaders:
|
1995-08-04 04:29:05 +00:00
|
|
|
import mimetools
|
|
|
|
import StringIO
|
|
|
|
_noheaders = mimetools.Message(StringIO.StringIO(), 0)
|
1994-03-22 12:05:32 +00:00
|
|
|
_noheaders.fp.close() # Recycle file descriptor
|
|
|
|
return _noheaders
|
|
|
|
|
|
|
|
|
|
|
|
# Utility classes
|
|
|
|
|
|
|
|
# Class used by open_ftp() for cache of open FTP connections
|
|
|
|
class ftpwrapper:
|
1994-07-04 22:14:49 +00:00
|
|
|
def __init__(self, user, passwd, host, port, dirs):
|
|
|
|
self.user = unquote(user or '')
|
|
|
|
self.passwd = unquote(passwd or '')
|
1994-03-22 12:05:32 +00:00
|
|
|
self.host = host
|
|
|
|
self.port = port
|
1994-07-04 22:14:49 +00:00
|
|
|
self.dirs = []
|
|
|
|
for dir in dirs:
|
|
|
|
self.dirs.append(unquote(dir))
|
1994-03-22 12:05:32 +00:00
|
|
|
self.init()
|
|
|
|
def init(self):
|
|
|
|
import ftplib
|
1997-12-28 04:21:20 +00:00
|
|
|
self.busy = 0
|
1994-03-22 12:05:32 +00:00
|
|
|
self.ftp = ftplib.FTP()
|
|
|
|
self.ftp.connect(self.host, self.port)
|
1994-07-04 22:14:49 +00:00
|
|
|
self.ftp.login(self.user, self.passwd)
|
|
|
|
for dir in self.dirs:
|
|
|
|
self.ftp.cwd(dir)
|
|
|
|
def retrfile(self, file, type):
|
1994-03-22 12:05:32 +00:00
|
|
|
import ftplib
|
1997-12-28 04:21:20 +00:00
|
|
|
self.endtransfer()
|
1994-07-04 22:14:49 +00:00
|
|
|
if type in ('d', 'D'): cmd = 'TYPE A'; isdir = 1
|
|
|
|
else: cmd = 'TYPE ' + type; isdir = 0
|
1994-03-22 12:05:32 +00:00
|
|
|
try:
|
1994-07-04 22:14:49 +00:00
|
|
|
self.ftp.voidcmd(cmd)
|
1994-03-22 12:05:32 +00:00
|
|
|
except ftplib.all_errors:
|
|
|
|
self.init()
|
1994-07-04 22:14:49 +00:00
|
|
|
self.ftp.voidcmd(cmd)
|
1994-03-22 12:05:32 +00:00
|
|
|
conn = None
|
1994-07-04 22:14:49 +00:00
|
|
|
if file and not isdir:
|
1997-12-28 04:21:20 +00:00
|
|
|
# Use nlst to see if the file exists at all
|
|
|
|
try:
|
|
|
|
self.ftp.nlst(file)
|
|
|
|
except ftplib.error_perm, reason:
|
|
|
|
raise IOError, ('ftp error', reason), \
|
|
|
|
sys.exc_info()[2]
|
1998-01-19 22:26:54 +00:00
|
|
|
# Restore the transfer mode!
|
|
|
|
self.ftp.voidcmd(cmd)
|
1997-12-28 04:21:20 +00:00
|
|
|
# Try to retrieve as a file
|
1994-03-22 12:05:32 +00:00
|
|
|
try:
|
|
|
|
cmd = 'RETR ' + file
|
|
|
|
conn = self.ftp.transfercmd(cmd)
|
|
|
|
except ftplib.error_perm, reason:
|
|
|
|
if reason[:3] != '550':
|
1996-11-20 22:02:24 +00:00
|
|
|
raise IOError, ('ftp error', reason), \
|
1997-09-29 23:23:46 +00:00
|
|
|
sys.exc_info()[2]
|
1994-03-22 12:05:32 +00:00
|
|
|
if not conn:
|
1998-01-19 22:26:54 +00:00
|
|
|
# Set transfer mode to ASCII!
|
|
|
|
self.ftp.voidcmd('TYPE A')
|
1994-03-22 12:05:32 +00:00
|
|
|
# Try a directory listing
|
|
|
|
if file: cmd = 'LIST ' + file
|
|
|
|
else: cmd = 'LIST'
|
|
|
|
conn = self.ftp.transfercmd(cmd)
|
1997-12-28 04:21:20 +00:00
|
|
|
self.busy = 1
|
1997-06-06 21:11:11 +00:00
|
|
|
return addclosehook(conn.makefile('rb'), self.endtransfer)
|
|
|
|
def endtransfer(self):
|
1997-12-28 04:21:20 +00:00
|
|
|
if not self.busy:
|
|
|
|
return
|
|
|
|
self.busy = 0
|
1997-06-06 21:11:11 +00:00
|
|
|
try:
|
|
|
|
self.ftp.voidresp()
|
|
|
|
except ftperrors():
|
|
|
|
pass
|
|
|
|
def close(self):
|
1997-12-28 04:21:20 +00:00
|
|
|
self.endtransfer()
|
1997-06-06 21:11:11 +00:00
|
|
|
try:
|
|
|
|
self.ftp.close()
|
|
|
|
except ftperrors():
|
|
|
|
pass
|
1994-03-22 12:05:32 +00:00
|
|
|
|
|
|
|
# Base class for addinfo and addclosehook
|
|
|
|
class addbase:
|
|
|
|
def __init__(self, fp):
|
|
|
|
self.fp = fp
|
|
|
|
self.read = self.fp.read
|
|
|
|
self.readline = self.fp.readline
|
|
|
|
self.readlines = self.fp.readlines
|
|
|
|
self.fileno = self.fp.fileno
|
|
|
|
def __repr__(self):
|
|
|
|
return '<%s at %s whose fp = %s>' % (
|
|
|
|
self.__class__.__name__, `id(self)`, `self.fp`)
|
|
|
|
def close(self):
|
|
|
|
self.read = None
|
|
|
|
self.readline = None
|
|
|
|
self.readlines = None
|
|
|
|
self.fileno = None
|
1995-06-22 19:00:13 +00:00
|
|
|
if self.fp: self.fp.close()
|
1994-03-22 12:05:32 +00:00
|
|
|
self.fp = None
|
|
|
|
|
|
|
|
# Class to add a close hook to an open file
|
|
|
|
class addclosehook(addbase):
|
|
|
|
def __init__(self, fp, closehook, *hookargs):
|
|
|
|
addbase.__init__(self, fp)
|
|
|
|
self.closehook = closehook
|
|
|
|
self.hookargs = hookargs
|
|
|
|
def close(self):
|
|
|
|
if self.closehook:
|
|
|
|
apply(self.closehook, self.hookargs)
|
|
|
|
self.closehook = None
|
|
|
|
self.hookargs = None
|
|
|
|
addbase.close(self)
|
|
|
|
|
|
|
|
# class to add an info() method to an open file
|
|
|
|
class addinfo(addbase):
|
|
|
|
def __init__(self, fp, headers):
|
|
|
|
addbase.__init__(self, fp)
|
|
|
|
self.headers = headers
|
|
|
|
def info(self):
|
|
|
|
return self.headers
|
|
|
|
|
1996-09-10 17:02:56 +00:00
|
|
|
# class to add info() and geturl() methods to an open file
|
|
|
|
class addinfourl(addbase):
|
|
|
|
def __init__(self, fp, headers, url):
|
|
|
|
addbase.__init__(self, fp)
|
|
|
|
self.headers = headers
|
|
|
|
self.url = url
|
|
|
|
def info(self):
|
|
|
|
return self.headers
|
|
|
|
def geturl(self):
|
|
|
|
return self.url
|
|
|
|
|
1994-03-22 12:05:32 +00:00
|
|
|
|
|
|
|
# Utility to combine a URL with a base URL to form a new URL
|
|
|
|
|
|
|
|
def basejoin(base, url):
|
|
|
|
type, path = splittype(url)
|
1995-11-10 10:36:07 +00:00
|
|
|
if type:
|
|
|
|
# if url is complete (i.e., it contains a type), return it
|
|
|
|
return url
|
1994-03-22 12:05:32 +00:00
|
|
|
host, path = splithost(path)
|
1995-11-10 10:36:07 +00:00
|
|
|
type, basepath = splittype(base) # inherit type from base
|
|
|
|
if host:
|
|
|
|
# if url contains host, just inherit type
|
|
|
|
if type: return type + '://' + host + path
|
|
|
|
else:
|
|
|
|
# no type inherited, so url must have started with //
|
|
|
|
# just return it
|
|
|
|
return url
|
|
|
|
host, basepath = splithost(basepath) # inherit host
|
|
|
|
basepath, basetag = splittag(basepath) # remove extraneuous cruft
|
|
|
|
basepath, basequery = splitquery(basepath) # idem
|
1994-03-22 12:05:32 +00:00
|
|
|
if path[:1] != '/':
|
1995-11-10 10:36:07 +00:00
|
|
|
# non-absolute path name
|
|
|
|
if path[:1] in ('#', '?'):
|
|
|
|
# path is just a tag or query, attach to basepath
|
|
|
|
i = len(basepath)
|
|
|
|
else:
|
|
|
|
# else replace last component
|
|
|
|
i = string.rfind(basepath, '/')
|
|
|
|
if i < 0:
|
|
|
|
# basepath not absolute
|
|
|
|
if host:
|
|
|
|
# host present, make absolute
|
|
|
|
basepath = '/'
|
|
|
|
else:
|
|
|
|
# else keep non-absolute
|
|
|
|
basepath = ''
|
|
|
|
else:
|
|
|
|
# remove last file component
|
|
|
|
basepath = basepath[:i+1]
|
1997-04-11 19:09:51 +00:00
|
|
|
# Interpret ../ (important because of symlinks)
|
|
|
|
while basepath and path[:3] == '../':
|
|
|
|
path = path[3:]
|
1997-09-03 22:36:15 +00:00
|
|
|
i = string.rfind(basepath[:-1], '/')
|
1997-04-11 19:09:51 +00:00
|
|
|
if i > 0:
|
1997-09-03 22:36:15 +00:00
|
|
|
basepath = basepath[:i+1]
|
|
|
|
elif i == 0:
|
|
|
|
basepath = '/'
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
basepath = ''
|
1997-04-11 19:09:51 +00:00
|
|
|
|
1994-03-22 12:05:32 +00:00
|
|
|
path = basepath + path
|
1995-11-10 10:36:07 +00:00
|
|
|
if type and host: return type + '://' + host + path
|
|
|
|
elif type: return type + ':' + path
|
|
|
|
elif host: return '//' + host + path # don't know what this means
|
|
|
|
else: return path
|
1994-03-22 12:05:32 +00:00
|
|
|
|
|
|
|
|
1994-07-04 22:14:49 +00:00
|
|
|
# Utilities to parse URLs (most of these return None for missing parts):
|
1995-11-10 10:36:07 +00:00
|
|
|
# unwrap('<URL:type://host/path>') --> 'type://host/path'
|
1994-03-22 12:05:32 +00:00
|
|
|
# splittype('type:opaquestring') --> 'type', 'opaquestring'
|
|
|
|
# splithost('//host[:port]/path') --> 'host[:port]', '/path'
|
1994-07-04 22:14:49 +00:00
|
|
|
# splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'
|
|
|
|
# splitpasswd('user:passwd') -> 'user', 'passwd'
|
1994-03-22 12:05:32 +00:00
|
|
|
# splitport('host:port') --> 'host', 'port'
|
|
|
|
# splitquery('/path?query') --> '/path', 'query'
|
|
|
|
# splittag('/path#tag') --> '/path', 'tag'
|
1994-07-04 22:14:49 +00:00
|
|
|
# splitattr('/path;attr1=value1;attr2=value2;...') ->
|
|
|
|
# '/path', ['attr1=value1', 'attr2=value2', ...]
|
|
|
|
# splitvalue('attr=value') --> 'attr', 'value'
|
1994-03-22 12:05:32 +00:00
|
|
|
# splitgophertype('/Xselector') --> 'X', 'selector'
|
|
|
|
# unquote('abc%20def') -> 'abc def'
|
|
|
|
# quote('abc def') -> 'abc%20def')
|
|
|
|
|
|
|
|
def unwrap(url):
|
|
|
|
url = string.strip(url)
|
|
|
|
if url[:1] == '<' and url[-1:] == '>':
|
|
|
|
url = string.strip(url[1:-1])
|
|
|
|
if url[:4] == 'URL:': url = string.strip(url[4:])
|
|
|
|
return url
|
|
|
|
|
1997-09-29 23:23:46 +00:00
|
|
|
_typeprog = None
|
1994-03-22 12:05:32 +00:00
|
|
|
def splittype(url):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _typeprog
|
|
|
|
if _typeprog is None:
|
|
|
|
import re
|
|
|
|
_typeprog = re.compile('^([^/:]+):')
|
|
|
|
|
|
|
|
match = _typeprog.match(url)
|
|
|
|
if match:
|
|
|
|
scheme = match.group(1)
|
1997-04-16 15:17:06 +00:00
|
|
|
return scheme, url[len(scheme) + 1:]
|
1994-03-22 12:05:32 +00:00
|
|
|
return None, url
|
|
|
|
|
1997-09-29 23:23:46 +00:00
|
|
|
_hostprog = None
|
1994-03-22 12:05:32 +00:00
|
|
|
def splithost(url):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _hostprog
|
|
|
|
if _hostprog is None:
|
|
|
|
import re
|
|
|
|
_hostprog = re.compile('^//([^/]+)(.*)$')
|
|
|
|
|
|
|
|
match = _hostprog.match(url)
|
|
|
|
if match: return match.group(1, 2)
|
1994-03-22 12:05:32 +00:00
|
|
|
return None, url
|
|
|
|
|
1997-09-29 23:23:46 +00:00
|
|
|
_userprog = None
|
1994-07-04 22:14:49 +00:00
|
|
|
def splituser(host):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _userprog
|
|
|
|
if _userprog is None:
|
|
|
|
import re
|
|
|
|
_userprog = re.compile('^([^@]*)@(.*)$')
|
|
|
|
|
|
|
|
match = _userprog.match(host)
|
|
|
|
if match: return match.group(1, 2)
|
1994-07-04 22:14:49 +00:00
|
|
|
return None, host
|
|
|
|
|
1997-09-29 23:23:46 +00:00
|
|
|
_passwdprog = None
|
1994-07-04 22:14:49 +00:00
|
|
|
def splitpasswd(user):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _passwdprog
|
|
|
|
if _passwdprog is None:
|
|
|
|
import re
|
|
|
|
_passwdprog = re.compile('^([^:]*):(.*)$')
|
|
|
|
|
1997-10-14 13:30:57 +00:00
|
|
|
match = _passwdprog.match(user)
|
1997-09-29 23:23:46 +00:00
|
|
|
if match: return match.group(1, 2)
|
1994-07-04 22:14:49 +00:00
|
|
|
return user, None
|
|
|
|
|
1997-09-29 23:23:46 +00:00
|
|
|
_portprog = None
|
1994-03-22 12:05:32 +00:00
|
|
|
def splitport(host):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _portprog
|
|
|
|
if _portprog is None:
|
|
|
|
import re
|
|
|
|
_portprog = re.compile('^(.*):([0-9]+)$')
|
|
|
|
|
|
|
|
match = _portprog.match(host)
|
|
|
|
if match: return match.group(1, 2)
|
1994-03-22 12:05:32 +00:00
|
|
|
return host, None
|
|
|
|
|
1996-06-13 19:12:35 +00:00
|
|
|
# Split host and port, returning numeric port.
|
|
|
|
# Return given default port if no ':' found; defaults to -1.
|
1996-06-17 17:11:40 +00:00
|
|
|
# Return numerical port if a valid number are found after ':'.
|
|
|
|
# Return None if ':' but not a valid number.
|
1997-09-29 23:23:46 +00:00
|
|
|
_nportprog = None
|
1996-06-13 19:12:35 +00:00
|
|
|
def splitnport(host, defport=-1):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _nportprog
|
|
|
|
if _nportprog is None:
|
|
|
|
import re
|
|
|
|
_nportprog = re.compile('^(.*):(.*)$')
|
|
|
|
|
|
|
|
match = _nportprog.match(host)
|
|
|
|
if match:
|
|
|
|
host, port = match.group(1, 2)
|
1996-06-17 17:11:40 +00:00
|
|
|
try:
|
|
|
|
if not port: raise string.atoi_error, "no digits"
|
|
|
|
nport = string.atoi(port)
|
|
|
|
except string.atoi_error:
|
|
|
|
nport = None
|
1996-06-13 19:12:35 +00:00
|
|
|
return host, nport
|
|
|
|
return host, defport
|
|
|
|
|
1997-09-29 23:23:46 +00:00
|
|
|
_queryprog = None
|
1994-03-22 12:05:32 +00:00
|
|
|
def splitquery(url):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _queryprog
|
|
|
|
if _queryprog is None:
|
|
|
|
import re
|
|
|
|
_queryprog = re.compile('^(.*)\?([^?]*)$')
|
|
|
|
|
|
|
|
match = _queryprog.match(url)
|
|
|
|
if match: return match.group(1, 2)
|
1994-03-22 12:05:32 +00:00
|
|
|
return url, None
|
|
|
|
|
1997-09-29 23:23:46 +00:00
|
|
|
_tagprog = None
|
1994-03-22 12:05:32 +00:00
|
|
|
def splittag(url):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _tagprog
|
|
|
|
if _tagprog is None:
|
|
|
|
import re
|
|
|
|
_tagprog = re.compile('^(.*)#([^#]*)$')
|
|
|
|
|
|
|
|
match = _tagprog.match(url)
|
|
|
|
if match: return match.group(1, 2)
|
1994-03-22 12:05:32 +00:00
|
|
|
return url, None
|
|
|
|
|
1994-07-04 22:14:49 +00:00
|
|
|
def splitattr(url):
|
|
|
|
words = string.splitfields(url, ';')
|
|
|
|
return words[0], words[1:]
|
|
|
|
|
1997-09-29 23:23:46 +00:00
|
|
|
_valueprog = None
|
1994-07-04 22:14:49 +00:00
|
|
|
def splitvalue(attr):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _valueprog
|
|
|
|
if _valueprog is None:
|
|
|
|
import re
|
|
|
|
_valueprog = re.compile('^([^=]*)=(.*)$')
|
|
|
|
|
|
|
|
match = _valueprog.match(attr)
|
|
|
|
if match: return match.group(1, 2)
|
1994-07-04 22:14:49 +00:00
|
|
|
return attr, None
|
|
|
|
|
1994-03-22 12:05:32 +00:00
|
|
|
def splitgophertype(selector):
|
|
|
|
if selector[:1] == '/' and selector[1:2]:
|
|
|
|
return selector[1], selector[2:]
|
|
|
|
return None, selector
|
|
|
|
|
1997-09-29 23:23:46 +00:00
|
|
|
_quoteprog = None
|
1994-03-22 12:05:32 +00:00
|
|
|
def unquote(s):
|
1997-09-29 23:23:46 +00:00
|
|
|
global _quoteprog
|
|
|
|
if _quoteprog is None:
|
|
|
|
import re
|
|
|
|
_quoteprog = re.compile('%[0-9a-fA-F][0-9a-fA-F]')
|
|
|
|
|
1994-03-22 12:05:32 +00:00
|
|
|
i = 0
|
|
|
|
n = len(s)
|
1996-08-26 15:56:12 +00:00
|
|
|
res = []
|
1994-03-22 12:05:32 +00:00
|
|
|
while 0 <= i < n:
|
1997-09-29 23:23:46 +00:00
|
|
|
match = _quoteprog.search(s, i)
|
|
|
|
if not match:
|
1996-08-26 15:56:12 +00:00
|
|
|
res.append(s[i:])
|
1994-03-22 12:05:32 +00:00
|
|
|
break
|
1997-09-29 23:23:46 +00:00
|
|
|
j = match.start(0)
|
1996-08-26 15:56:12 +00:00
|
|
|
res.append(s[i:j] + chr(string.atoi(s[j+1:j+3], 16)))
|
1994-03-22 12:05:32 +00:00
|
|
|
i = j+3
|
1996-08-26 15:56:12 +00:00
|
|
|
return string.joinfields(res, '')
|
1994-03-22 12:05:32 +00:00
|
|
|
|
1996-12-13 14:47:36 +00:00
|
|
|
def unquote_plus(s):
|
|
|
|
if '+' in s:
|
1997-09-29 23:23:46 +00:00
|
|
|
# replace '+' with ' '
|
|
|
|
s = string.join(string.split(s, '+'), ' ')
|
1996-12-13 14:47:36 +00:00
|
|
|
return unquote(s)
|
|
|
|
|
1994-08-29 10:52:58 +00:00
|
|
|
always_safe = string.letters + string.digits + '_,.-'
|
1994-07-04 22:14:49 +00:00
|
|
|
def quote(s, safe = '/'):
|
|
|
|
safe = always_safe + safe
|
1996-08-26 15:56:12 +00:00
|
|
|
res = []
|
1994-03-22 12:05:32 +00:00
|
|
|
for c in s:
|
1994-07-04 22:14:49 +00:00
|
|
|
if c in safe:
|
1996-08-26 15:56:12 +00:00
|
|
|
res.append(c)
|
1994-07-04 22:14:49 +00:00
|
|
|
else:
|
1996-08-26 15:56:12 +00:00
|
|
|
res.append('%%%02x' % ord(c))
|
|
|
|
return string.joinfields(res, '')
|
1994-03-22 12:05:32 +00:00
|
|
|
|
1996-12-13 14:47:36 +00:00
|
|
|
def quote_plus(s, safe = '/'):
|
|
|
|
if ' ' in s:
|
1997-09-29 23:23:46 +00:00
|
|
|
# replace ' ' with '+'
|
|
|
|
s = string.join(string.split(s, ' '), '+')
|
1996-12-13 14:47:36 +00:00
|
|
|
return quote(s, safe + '+')
|
|
|
|
else:
|
|
|
|
return quote(s, safe)
|
|
|
|
|
1996-03-20 15:33:11 +00:00
|
|
|
|
|
|
|
# Proxy handling
|
|
|
|
def getproxies():
|
|
|
|
"""Return a dictionary of protocol scheme -> proxy server URL mappings.
|
|
|
|
|
|
|
|
Scan the environment for variables named <scheme>_proxy;
|
|
|
|
this seems to be the standard convention. If you need a
|
|
|
|
different way, you can pass a proxies dictionary to the
|
|
|
|
[Fancy]URLopener constructor.
|
|
|
|
|
|
|
|
"""
|
|
|
|
proxies = {}
|
|
|
|
for name, value in os.environ.items():
|
1997-05-28 15:37:19 +00:00
|
|
|
name = string.lower(name)
|
1996-03-20 15:33:11 +00:00
|
|
|
if value and name[-6:] == '_proxy':
|
|
|
|
proxies[name[:-6]] = value
|
|
|
|
return proxies
|
|
|
|
|
|
|
|
|
1994-03-22 12:05:32 +00:00
|
|
|
# Test and time quote() and unquote()
|
|
|
|
def test1():
|
|
|
|
import time
|
|
|
|
s = ''
|
|
|
|
for i in range(256): s = s + chr(i)
|
|
|
|
s = s*4
|
|
|
|
t0 = time.time()
|
|
|
|
qs = quote(s)
|
|
|
|
uqs = unquote(qs)
|
|
|
|
t1 = time.time()
|
|
|
|
if uqs != s:
|
|
|
|
print 'Wrong!'
|
|
|
|
print `s`
|
|
|
|
print `qs`
|
|
|
|
print `uqs`
|
|
|
|
print round(t1 - t0, 3), 'sec'
|
|
|
|
|
|
|
|
|
|
|
|
# Test program
|
|
|
|
def test():
|
|
|
|
import sys
|
|
|
|
args = sys.argv[1:]
|
|
|
|
if not args:
|
|
|
|
args = [
|
|
|
|
'/etc/passwd',
|
|
|
|
'file:/etc/passwd',
|
|
|
|
'file://localhost/etc/passwd',
|
1997-09-29 23:23:46 +00:00
|
|
|
'ftp://ftp.python.org/etc/passwd',
|
|
|
|
'gopher://gopher.micro.umn.edu/1/',
|
|
|
|
'http://www.python.org/index.html',
|
1994-03-22 12:05:32 +00:00
|
|
|
]
|
|
|
|
try:
|
|
|
|
for url in args:
|
|
|
|
print '-'*10, url, '-'*10
|
|
|
|
fn, h = urlretrieve(url)
|
|
|
|
print fn, h
|
|
|
|
if h:
|
|
|
|
print '======'
|
|
|
|
for k in h.keys(): print k + ':', h[k]
|
|
|
|
print '======'
|
1997-04-11 19:01:48 +00:00
|
|
|
fp = open(fn, 'rb')
|
1994-03-22 12:05:32 +00:00
|
|
|
data = fp.read()
|
|
|
|
del fp
|
1997-09-29 23:23:46 +00:00
|
|
|
if '\r' in data:
|
|
|
|
table = string.maketrans("", "")
|
|
|
|
data = string.translate(data, table, "\r")
|
|
|
|
print data
|
1994-03-22 12:05:32 +00:00
|
|
|
fn, h = None, None
|
|
|
|
print '-'*40
|
|
|
|
finally:
|
|
|
|
urlcleanup()
|
|
|
|
|
|
|
|
# Run test program when run as a script
|
|
|
|
if __name__ == '__main__':
|
1997-09-29 23:23:46 +00:00
|
|
|
test1()
|
1994-03-22 12:05:32 +00:00
|
|
|
test()
|