Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit 23acc95

Browse files
gvanrossumgvanrossum
committed
Towards a standard access mechanism for URLs.
1 parent 3da56c3 commit 23acc95

3 files changed

Lines changed: 546 additions & 0 deletions

File tree

‎Lib/gopherlib.py‎

Lines changed: 195 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,195 @@
1+
# Gopher protocol client interface
2+
3+
import string
4+
5+
# Default selector, host and port
6+
DEF_SELECTOR = '1/'
7+
DEF_HOST = 'gopher.micro.umn.edu'
8+
DEF_PORT = 70
9+
10+
# Recognized file types
11+
A_TEXT = '0'
12+
A_MENU = '1'
13+
A_CSO = '2'
14+
A_ERROR = '3'
15+
A_MACBINHEX = '4'
16+
A_PCBINHEX = '5'
17+
A_UUENCODED = '6'
18+
A_INDEX = '7'
19+
A_TELNET = '8'
20+
A_BINARY = '9'
21+
A_DUPLICATE = '+'
22+
A_SOUND = 's'
23+
A_EVENT = 'e'
24+
A_CALENDAR = 'c'
25+
A_HTML = 'h'
26+
A_TN3270 = 'T'
27+
A_MIME = 'M'
28+
A_IMAGE = 'I'
29+
A_WHOIS = 'w'
30+
A_QUERY = 'q'
31+
A_GIF = 'g'
32+
A_HTML = 'h' # HTML file
33+
A_WWW = 'w' # WWW address
34+
A_PLUS_IMAGE = ':'
35+
A_PLUS_MOVIE = ';'
36+
A_PLUS_SOUND = '<'
37+
38+
39+
# Function mapping all file types to strings; unknown types become TYPE='x'
40+
_names = dir()
41+
_type_to_name_map = None
42+
def type_to_name(gtype):
43+
global _type_to_name_map
44+
if not _type_to_name_map:
45+
for name in _names:
46+
if name[:2] == 'A_':
47+
_type_to_name_map[eval(name)] = name[2:]
48+
if _type_to_name_map.has_key(gtype):
49+
return _type_to_name_map[gtype]
50+
return 'TYPE=' + `gtype`
51+
52+
# Names for characters and strings
53+
CRLF = '\r\n'
54+
TAB = '\t'
55+
56+
# Send a selector to a given host and port, return a file with the reply
57+
def send_selector(selector, host, *args):
58+
import socket
59+
import string
60+
if args:
61+
if args[1:]: raise TypeError, 'too many args'
62+
port = args[0]
63+
else:
64+
port = None
65+
i = string.find(host, ':')
66+
if i >= 0:
67+
host, port = host[:i], string.atoi(host[i+1:])
68+
if not port:
69+
port = DEF_PORT
70+
elif type(port) == type(''):
71+
port = string.atoi(port)
72+
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
73+
s.connect(host, port)
74+
s.send(selector + CRLF)
75+
s.shutdown(1)
76+
return s.makefile('r')
77+
78+
# Send a selector and a query string
79+
def send_query(selector, query, host, *args):
80+
return apply(send_selector, (selector + '\t' + query, host) + args)
81+
82+
# The following functions interpret the data returned by the gopher
83+
# server according to the expected type, e.g. textfile or directory
84+
85+
# Get a directory in the form of a list of entries
86+
def get_directory(f):
87+
import string
88+
list = []
89+
while 1:
90+
line = f.readline()
91+
if not line:
92+
print '(Unexpected EOF from server)'
93+
break
94+
if line[-2:] == CRLF:
95+
line = line[:-2]
96+
elif line[-1:] in CRLF:
97+
line = line[:-1]
98+
if line == '.':
99+
break
100+
if not line:
101+
print '(Empty line from server)'
102+
continue
103+
gtype = line[0]
104+
parts = string.splitfields(line[1:], TAB)
105+
if len(parts) < 4:
106+
print '(Bad line from server:', `line`, ')'
107+
continue
108+
if len(parts) > 4:
109+
if parts[4:] != ['+']:
110+
print '(Extra info from server:', parts[4:], ')'
111+
else:
112+
parts.append('')
113+
parts.insert(0, gtype)
114+
list.append(parts)
115+
return list
116+
117+
# Get a text file as a list of lines, with trailing CRLF stripped
118+
def get_textfile(f):
119+
list = []
120+
get_alt_textfile(f, list.append)
121+
return list
122+
123+
# Get a text file and pass each line to a function, with trailing CRLF stripped
124+
def get_alt_textfile(f, func):
125+
while 1:
126+
line = f.readline()
127+
if not line:
128+
print '(Unexpected EOF from server)'
129+
break
130+
if line[-2:] == CRLF:
131+
line = line[:-2]
132+
elif line[-1:] in CRLF:
133+
line = line[:-1]
134+
if line == '.':
135+
break
136+
if line[:2] == '..':
137+
line = line[1:]
138+
func(line)
139+
140+
# Get a binary file as one solid data block
141+
def get_binary(f):
142+
data = f.read()
143+
return data
144+
145+
# Get a binary file and pass each block to a function
146+
def get_alt_binary(f, func, blocksize):
147+
while 1:
148+
data = f.read(blocksize)
149+
if not data:
150+
break
151+
func(data)
152+
153+
# Trivial test program
154+
def test():
155+
import sys
156+
import getopt
157+
opts, args = getopt.getopt(sys.argv[1:], '')
158+
selector = DEF_SELECTOR
159+
type = selector[0]
160+
host = DEF_HOST
161+
port = DEF_PORT
162+
if args:
163+
host = args[0]
164+
args = args[1:]
165+
if args:
166+
type = args[0]
167+
args = args[1:]
168+
if len(type) > 1:
169+
type, selector = type[0], type
170+
else:
171+
selector = ''
172+
if args:
173+
selector = args[0]
174+
args = args[1:]
175+
query = ''
176+
if args:
177+
query = args[0]
178+
args = args[1:]
179+
if type == A_INDEX:
180+
f = send_query(selector, query, host)
181+
else:
182+
f = send_selector(selector, host)
183+
if type == A_TEXT:
184+
list = get_textfile(f)
185+
for item in list: print item
186+
elif type in (A_MENU, A_INDEX):
187+
list = get_directory(f)
188+
for item in list: print item
189+
else:
190+
data = get_binary(f)
191+
print 'binary data:', len(data), 'bytes:', `data[:100]`[:40]
192+
193+
# Run the test when run as script
194+
if __name__ == '__main__':
195+
test()

‎Lib/httplib.py‎

Lines changed: 129 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,129 @@
1+
# HTTP client class
2+
#
3+
# See the following document for a tentative protocol description:
4+
# Hypertext Transfer Protocol (HTTP) Tim Berners-Lee, CERN
5+
# Internet Draft 5 Nov 1993
6+
# draft-ietf-iiir-http-00.txt Expires 5 May 1994
7+
#
8+
# Example:
9+
#
10+
# >>> from httplib import HTTP
11+
# >>> h = HTTP('www.cwi.nl')
12+
# >>> h.putreqest('GET', '/index.html')
13+
# >>> h.putheader('Accept', 'text/html')
14+
# >>> h.putheader('Accept', 'text/plain')
15+
# >>> errcode, errmsg, headers = h.getreply()
16+
# >>> if errcode == 200:
17+
# ... f = h.getfile()
18+
# ... print f.read() # Print the raw HTML
19+
# ...
20+
# <TITLE>Home Page of CWI, Amsterdam</TITLE>
21+
# [...many more lines...]
22+
# >>>
23+
#
24+
# Note that an HTTP object is used for a single request -- to issue a
25+
# second request to the same server, you create a new HTTP object.
26+
# (This is in accordance with the protocol, which uses a new TCP
27+
# connection for each request.)
28+
29+
30+
import os
31+
import socket
32+
import string
33+
import regex
34+
import regsub
35+
import rfc822
36+
37+
HTTP_VERSION = 'HTTP/1.0'
38+
HTTP_PORT = 80
39+
40+
replypat = regsub.gsub('\\.', '\\\\.', HTTP_VERSION) + \
41+
'[ \t]+\([0-9][0-9][0-9]\)\(.*\)'
42+
replyprog = regex.compile(replypat)
43+
44+
class HTTP:
45+
46+
def __init__(self, *args):
47+
self.debuglevel = 0
48+
if args: apply(self.connect, args)
49+
50+
def set_debuglevel(self, debuglevel):
51+
self.debuglevel = debuglevel
52+
53+
def connect(self, host, *args):
54+
if args:
55+
if args[1:]: raise TypeError, 'too many args'
56+
port = args[0]
57+
else:
58+
i = string.find(host, ':')
59+
if i >= 0:
60+
host, port = host[:i], host[i+1:]
61+
try: port = string.atoi(port)
62+
except string.atoi_error: port = None
63+
if not port: port = HTTP_PORT
64+
self.sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
65+
if self.debuglevel > 0: print 'connect:', (host, port)
66+
self.sock.connect(host, port)
67+
68+
def send(self, str):
69+
if self.debuglevel > 0: print 'send:', `str`
70+
self.sock.send(str)
71+
72+
def putrequest(self, request, selector):
73+
str = '%s %s %s\r\n' % (request, selector, HTTP_VERSION)
74+
self.send(str)
75+
76+
def putheader(self, header, *args):
77+
str = '%s: %s\r\n' % (header, string.joinfields(args,'\r\n\t'))
78+
self.send(str)
79+
80+
def endheaders(self):
81+
self.send('\r\n')
82+
83+
def endrequest(self):
84+
if self.debuglevel > 0: print 'shutdown: 1'
85+
self.sock.shutdown(1)
86+
87+
def getreply(self):
88+
self.endrequest()
89+
self.file = self.sock.makefile('r')
90+
line = self.file.readline()
91+
if self.debuglevel > 0: print 'reply:', `line`
92+
if replyprog.match(line) < 0:
93+
self.headers = None
94+
return -1, line, self.headers
95+
errcode, errmsg = replyprog.group(1, 2)
96+
errcode = string.atoi(errcode)
97+
errmsg = string.strip(errmsg)
98+
self.headers = rfc822.Message(self.file)
99+
return errcode, errmsg, self.headers
100+
101+
def getfile(self):
102+
return self.file
103+
104+
105+
def test():
106+
import sys
107+
import getopt
108+
opts, args = getopt.getopt(sys.argv[1:], 'd')
109+
dl = 0
110+
for o, a in opts:
111+
if o == '-d': dl = dl + 1
112+
host = 'www.cwi.nl:80'
113+
selector = '/index.html'
114+
if args[0:]: host = args[0]
115+
if args[1:]: selector = args[1]
116+
h = HTTP()
117+
h.set_debuglevel(dl)
118+
h.connect(host)
119+
h.putrequest('GET', selector)
120+
errcode, errmsg, headers = h.getreply()
121+
print 'errcode =', errcode
122+
print 'headers =', headers
123+
print 'errmsg =', errmsg
124+
if headers:
125+
for header in headers.headers: print string.strip(header)
126+
print h.getfile().read()
127+
128+
if __name__ == '__main__':
129+
test()

0 commit comments

Comments
 (0)