summaryrefslogtreecommitdiffstats
path: root/Lib/urllib.py
blob: 7350de61e018d82a58eff1b9f20899ceb96aeaab (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
# Open an arbitrary URL
#
# See the following document for a tentative description of URLs:
#     Uniform Resource Locators              Tim Berners-Lee
#     INTERNET DRAFT                                    CERN
#     IETF URL Working Group                    14 July 1993
#     draft-ietf-uri-url-01.txt
#
# 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. 
# The info() method returns an rfc822.Message object which can be
# used to query various info about the object, if available.
# (rfc822.Message objects are queried with the getheader() method.)

import socket
import regex


# 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
def urlopen(url):
	global _urlopener
	if not _urlopener:
		_urlopener = URLopener()
	return _urlopener.open(url)
def urlretrieve(url):
	global _urlopener
	if not _urlopener:
		_urlopener = URLopener()
	return _urlopener.retrieve(url)
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.
ftpcache = {}
class URLopener:

	# Constructor
	def __init__(self):
		self.addheaders = []
		self.tempcache = {}
		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):
		import os
		for url in self.tempcache.keys():
			try:
				os.unlink(self.tempcache[url][0])
			except os.error:
				pass
			del self.tempcache[url]

	# 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')
	def open(self, url):
		type, url = splittype(unwrap(url))
 		if not type: type = 'file'
		name = 'open_' + type
		if '-' in name:
			import regsub
			name = regsub.gsub('-', '_', name)
		if not hasattr(self, name):
			raise IOError, ('url error', 'unknown url type', type)
		try:
			return getattr(self, name)(url)
		except socket.error, msg:
			raise IOError, ('socket error', msg)

	# External interface
	# retrieve(url) returns (filename, None) for a local object
	# or (tempfilename, headers) for a remote object
	def retrieve(self, url):
		if self.tempcache.has_key(url):
			return self.tempcache[url]
		url1 = unwrap(url)
		if self.tempcache.has_key(url1):
			self.tempcache[url] = self.tempcache[url1]
			return self.tempcache[url1]
		type, url1 = splittype(url1)
		if not type or type == 'file':
			try:
				fp = self.open_local_file(url1)
				del fp
				return splithost(url1)[1], None
			except IOError, msg:
				pass
		fp = self.open(url)
		headers = fp.info()
		import tempfile
		tfn = tempfile.mktemp()
		self.tempcache[url] = result = tfn, headers
		tfp = open(tfn, 'w')
		bs = 1024*8
		block = fp.read(bs)
		while block:
			tfp.write(block)
			block = fp.read(bs)
		del fp
		del tfp
		return result

	# Each method named open_<type> knows how to open that type of URL

	# Use HTTP protocol
	def open_http(self, url):
		import httplib
		host, selector = splithost(url)
		h = httplib.HTTP(host)
		h.putrequest('GET', selector)
		for args in self.addheaders: apply(h.putheader, args)
		errcode, errmsg, headers = h.getreply()
		if errcode == 200: return addinfo(h.getfile(), headers)
		else: raise IOError, ('http error', errcode, errmsg, headers)

	# Use Gopher protocol
	def open_gopher(self, url):
		import gopherlib
		host, selector = splithost(url)
		type, selector = splitgophertype(selector)
		selector, query = splitquery(selector)
		if query: fp = gopherlib.send_query(selector, query, host)
		else: fp = gopherlib.send_selector(selector, host)
		return addinfo(fp, noheaders())

	# Use local file or FTP depending on form of URL
	def open_file(self, url):
		try:
			return self.open_local_file(url)
		except IOError:
			return self.open_ftp(url)

	# Use local file
	def open_local_file(self, url):
		host, file = splithost(url)
		if not host: return addinfo(open(file, 'r'), noheaders())
		host, port = splitport(host)
		if not port and socket.gethostbyname(host) in (
			  localhost(), thishost()):
			return addinfo(open(file, 'r'), noheaders())
		raise IOError, ('local file error', 'not on local host')

	# Use FTP protocol
	def open_ftp(self, url):
		host, file = splithost(url)
		if not host: raise IOError, ('ftp error', 'no host given')
		host, port = splitport(host)
		host = socket.gethostbyname(host)
		if not port:
			import ftplib
			port = ftplib.FTP_PORT
		key = (host, port)
		try:
			if not self.ftpcache.has_key(key):
				self.ftpcache[key] = ftpwrapper(host, port)
			return addinfo(self.ftpcache[key].retrfile(file),
				  noheaders())
		except ftperrors(), msg:
			raise IOError, ('ftp error', msg)


# 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
		_ftperrors = (ftplib.error_reply,
			      ftplib.error_temp,
			      ftplib.error_perm,
			      ftplib.error_proto)
	return _ftperrors

# Return an empty rfc822.Message object
_noheaders = None
def noheaders():
	global _noheaders
	if not _noheaders:
		import rfc822
		_noheaders = rfc822.Message(open('/dev/null', 'r'))
		_noheaders.fp.close()	# Recycle file descriptor
	return _noheaders


# Utility classes

# Class used by open_ftp() for cache of open FTP connections
class ftpwrapper:
	def __init__(self, host, port):
		self.host = host
		self.port = port
		self.init()
	def init(self):
		import ftplib
		self.ftp = ftplib.FTP()
		self.ftp.connect(self.host, self.port)
		self.ftp.login()
	def retrfile(self, file):
		import ftplib
		try:
			self.ftp.voidcmd('TYPE I')
		except ftplib.all_errors:
			self.init()
			self.ftp.voidcmd('TYPE I')
		conn = None
		if file:
			try:
				cmd = 'RETR ' + file
				conn = self.ftp.transfercmd(cmd)
			except ftplib.error_perm, reason:
				if reason[:3] != '550':
					raise IOError, ('ftp error', reason)
		if not conn:
			# Try a directory listing
			if file: cmd = 'LIST ' + file
			else: cmd = 'LIST'
			conn = self.ftp.transfercmd(cmd)
		return addclosehook(conn.makefile('r'), self.ftp.voidresp)

# 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 __del__(self):
		self.close()
	def close(self):
		self.read = None
		self.readline = None
		self.readlines = None
		self.fileno = None
		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


# Utility to combine a URL with a base URL to form a new URL

def basejoin(base, url):
	type, path = splittype(url)
	if type: return url
	host, path = splithost(path)
	basetype, basepath = splittype(base)
	basehost, basepath = splithost(basepath)
	basepath, basetag = splittag(basepath)
	basepath, basequery = splitquery(basepath)
	type = basetype or 'file'
	if path[:1] != '/':
		import string
		i = string.rfind(basepath, '/')
		if i < 0: basepath = '/'
		else: basepath = basepath[:i+1]
		path = basepath + path
	if not host: host = basehost
	if host: return type + '://' + host + path
	else: return type + ':' + path


# Utilities to parse URLs:
# unwrap('<URL:type//host/path>') --> 'type//host/path'
# splittype('type:opaquestring') --> 'type', 'opaquestring'
# splithost('//host[:port]/path') --> 'host[:port]', '/path'
# splitport('host:port') --> 'host', 'port'
# splitquery('/path?query') --> '/path', 'query'
# splittag('/path#tag') --> '/path', 'tag'
# splitgophertype('/Xselector') --> 'X', 'selector'
# unquote('abc%20def') -> 'abc def'
# quote('abc def') -> 'abc%20def')

def unwrap(url):
	import string
	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

_typeprog = regex.compile('^\([^/:]+\):\(.*\)$')
def splittype(url):
	if _typeprog.match(url) >= 0: return _typeprog.group(1, 2)
	return None, url

_hostprog = regex.compile('^//\([^/]+\)\(.*\)$')
def splithost(url):
	if _hostprog.match(url) >= 0: return _hostprog.group(1, 2)
	return None, url

_portprog = regex.compile('^\(.*\):\([0-9]+\)$')
def splitport(host):
	if _portprog.match(host) >= 0: return _portprog.group(1, 2)
	return host, None

_queryprog = regex.compile('^\(.*\)\?\([^?]*\)$')
def splitquery(url):
	if _queryprog.match(url) >= 0: return _queryprog.group(1, 2)
	return url, None

_tagprog = regex.compile('^\(.*\)#\([^#]*\)$')
def splittag(url):
	if _tagprog.match(url) >= 0: return _tagprog.group(1, 2)
	return url, None

def splitgophertype(selector):
	if selector[:1] == '/' and selector[1:2]:
		return selector[1], selector[2:]
	return None, selector

_quoteprog = regex.compile('%[0-9a-fA-F][0-9a-fA-F]')
def unquote(s):
	import string
	i = 0
	n = len(s)
	res = ''
	while 0 <= i < n:
		j = _quoteprog.search(s, i)
		if j < 0:
			res = res + s[i:]
			break
		res = res + (s[i:j] + chr(eval('0x' + s[j+1:j+3])))
		i = j+3
	return res

_acceptable = \
	  'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-._@'
def quote(s):
	res = ''
	for c in s:
		if c in _acceptable: res = res + c
		else: res = res + '%%%02x' % ord(c)
	return res

# 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
	import regsub
	args = sys.argv[1:]
	if not args:
		args = [
			'/etc/passwd',
			'file:/etc/passwd',
			'file://localhost/etc/passwd',
			'ftp://ftp.cwi.nl/etc/passwd',
			'gopher://gopher.cwi.nl/11/',
			'http://www.cwi.nl/index.html',
			]
	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 '======'
			fp = open(fn, 'r')
			data = fp.read()
			del fp
			print regsub.gsub('\r', '', data)
			fn, h = None, None
		print '-'*40
	finally:
		urlcleanup()

# Run test program when run as a script
if __name__ == '__main__':
	test1()
	test()