-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathurl.py
More file actions
464 lines (361 loc) · 15.1 KB
/
Copy pathurl.py
File metadata and controls
464 lines (361 loc) · 15.1 KB
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
455
456
457
458
459
460
461
462
463
464
### URL ##############################################################################################
# Code for identifying, parsing and retrieving URL's.
# The asynchronous URLAccumulator is subclassed in all other services.
# Author: Tom De Smedt.
# Copyright (c) 2007 by Tom De Smedt.
# See LICENSE.txt for details.
import os
import socket, urllib.request, urllib.parse, urllib.error, urllib.request, urllib.error, urllib.parse, urllib.parse
import _thread, time
from warnings import warn
from .cache import Cache
### SETTINGS #########################################################################################
USER_AGENT = "NodeBox/1.9.4 +http://nodebox.net"
REFERER = "http://nodebox.net"
### URLERROR #########################################################################################
class URLError(Exception):
# A fault in the URL, like a missing t in htp://
def __str__(self): return str(self.__class__)
class URLTimeout(URLError):
# URL took to long to load.
def __str__(self): return str(self.__class__)
class HTTPError(URLError):
# Error on server.
def __str__(self): return str(self.__class__)
class HTTP401Authentication(HTTPError):
# URL requires a login and password.
def __str__(self): return str(self.__class__)
class HTTP403Forbidden(HTTPError):
# No access to this URL (user-agent?)
def __str__(self): return str(self.__class__)
class HTTP404NotFound(HTTPError):
# URL doesn't exist on the internet.
def __str__(self): return str(self.__class__)
### URLPARSER ########################################################################################
class URLParser:
def __init__(self, url="", method="get"):
""" Splits an url string into different parts.
The parts are:
protocol, domain, login, username, password, port, path, page, query, anchor.
The method defaults to get when the url has a query part.
Setting it to post will submit the query by POST
when opening the url.
"""
# If the url is a URLParser, copy POST parameters correctly.
is_post_urlparser = False
if isinstance(url, URLParser) and url.method == "post":
is_post_urlparser = True
url.method = "get"
# If the url is a URLParser, use its string representation.
# See that the original object's method is correctly reset.
urlstr = str(url)
if is_post_urlparser: url.method = "post"
url = urlstr
# Consider the following url:
# http://user:pass@example.com:992/animal/bird?species=seagull#wings
# protocol: http
# domain: example.com
url = urllib.parse.urlsplit(url)
self.protocol = url[0]
self.domain = url[1]
# username: user
# password: pass
self.username = ""
self.password = ""
if self.domain.find("@") >= 0:
login = self.domain.split("@")[0]
if login.find(":") >= 0:
self.username = login.split(":")[0]
self.password = login.split(":")[1]
self.domain = self.domain.split("@")[1]
# port: 992
self.port = ""
if self.domain.find(":") >= 0:
p = self.domain.split(":")
if p[1].isdigit():
self.port = p[1]
self.domain = p[0]
# path: /animal/
# page: bird
self.path = url[2]
self.page = ""
if not self.path.endswith("/"):
if self.path.find("/") >= 0:
self.page = self.path.split("/")[-1]
self.path = self.path[:-len(self.page)]
else:
self.page = self.path
self.path = ""
self.filename = self.page
# query: {"species": "seagull"}
self.query = {}
self.method = method
if url[3] != "":
self.method = "get"
if is_post_urlparser:
self.method = "post"
for param in url[3].split("&"):
key, value = "", ""
if param.find("=") >= 0:
try: (key, value) = param.split("=")
except:
key = param
else:
key = param
if key != "":
self.query[key] = value
# anchor: wings
self.anchor = url[4]
def __str__(self):
""" Reforms a url string from the different parts.
"""
url = ""
if self.protocol != "" : url += self.protocol + "://"
if self.username != "" : url += self.username + ":" + self.password + "@"
if self.domain != "" : url += self.domain
if self.port != "" : url += ":" + self.port
if self.path != "" : url += self.path
if self.page != "" : url += self.page
if self.method == "get" and \
len(self.query) > 0 : url += "?" + urllib.parse.urlencode(self.query)
if self.anchor != "" : url += "#" + self.anchor
return url
def _address(self):
return str(self)
address = property(_address)
def parse(url):
return URLParser(url)
def create(url="", method="get"):
return URLParser(url, method)
#url = parse("http://user:pass@example.com:992/animal/bird?species=seagull#wings")
#print url.domain
#print url.path
#print url.page
#print url
### URL OPENER #######################################################################################
PROXY = None
def set_proxy(host, type="https"):
global PROXY
if host != None:
PROXY = (host, type)
else:
PROXY = None
def open(url, wait=10):
""" Returns a connection to a url which you can read().
When the wait amount is exceeded, raises a URLTimeout.
When an error occurs, raises a URLError.
404 errors specifically return a HTTP404NotFound.
"""
# If the url is a URLParser, get any POST parameters.
post = None
if isinstance(url, URLParser) and url.method == "post":
post = urllib.parse.urlencode(url.query)
# If the url is a URLParser (or a YahooResult or something),
# use its string representation.
url = str(url)
# Use urllib instead of urllib2 for local files.
if os.path.exists(url):
return urllib.request.urlopen(url)
else:
socket.setdefaulttimeout(wait)
try:
#connection = urllib2.urlopen(url, post)
request = urllib.request.Request(url, post, {"User-Agent": USER_AGENT, "Referer": REFERER})
if PROXY:
p = urllib.request.ProxyHandler({PROXY[1]: PROXY[0]})
o = urllib.request.build_opener(p, urllib.request.HTTPHandler)
urllib.request.install_opener(o)
connection = urllib.request.urlopen(request)
except urllib.error.HTTPError as e:
if e.code == 401: raise HTTP401Authentication
if e.code == 403: raise HTTP403Forbidden
if e.code == 404: raise HTTP404NotFound
raise HTTPError
except urllib.error.URLError as e:
if e.reason[0] == 36: raise URLTimeout
raise URLError
return connection
#print open("http://nodebox.net")
#print open("http:/nodebox.net")
#print open("http://ndoebox.net")
#print open("http://nodebox.net/doink")
#print open("url.py").info()
#print open("boink.py").info()
#print open("file://url.py").info()
### URL VALIDATION ###################################################################################
def is_url(url, wait=10):
""" Returns False when no connection can be opened to the url.
"""
try: connection = open(url, wait)
except:
return False
return True
def not_found(url, wait=10):
""" Returns True when the url generates a "404 Not Found" error.
"""
try: connection = open(url, wait)
except HTTP404NotFound:
return True
except:
return False
return False
#url = "http://ndoebox.net"
#print is_url(url)
#print not_found("http://nodebox.net/nonexistent.html")
#print not_found("http://nodebox.net/")
### URL MIMETYPE ###################################################################################
def is_type(url, types=[], wait=10):
""" Determine the MIME-type of the document behind the url.
MIME is more reliable than simply checking the document extension.
Returns True when the MIME-type starts with anything in the list of types.
"""
# Types can also be a single string for convenience.
if isinstance(types, str):
types = [types]
try: connection = open(url, wait)
except:
return False
type = connection.info()["Content-Type"]
for t in types:
if type.startswith(t): return True
return False
def is_webpage(url, wait=10):
return is_type(url, "text/html", wait)
is_page = is_webpage
def is_stylesheet(url, wait=10):
return is_type(url, "text/css", wait)
def is_plaintext(url, wait=10):
return is_type(url, "text/plain", wait)
def is_pdf(url, wait=10):
return is_type(url, "application/pdf", wait)
def is_newsfeed(url, wait=10):
return is_type(url, ["application/rss+xml", "application/atom+xml"], wait)
def is_image(url, wait=10):
return is_type(url, ["image/gif", "image/jpeg", "image/x-png"], wait)
def is_audio(url, wait=10):
return is_type(url, ["audio/mpeg", "audio/x-aiff", "audio/x-wav"], wait)
def is_video(url, wait=10):
return is_type(url, ["video/mpeg", "video/quicktime"], wait)
def is_archive(url, wait=10):
return is_type(url, ["application/x-stuffit", "application/x-tar", "application/zip"], wait)
#print is_webpage("http://nodebox.net")
#print is_archive("http://nodebox.net/code/data/media/coreimage.zip")
### URLACCUMULATOR ###################################################################################
urlaccumulator_throttle = {}
class URLAccumulator:
def __init__(self, url, wait=60, asynchronous=False, cache=None, type=".html", throttle=0):
""" Creates a threaded connection to a url and reads data.
URLAccumulator can run asynchronously which is useful for animations.
The done property is set to True when downloading is complete.
The error attribute contains a URLError exception when no data is found.
URLAccumulator data can be cached.
Downloads that resulted in an error will write an empty file to the cache,
the data property will be an empty string but no error is logged
when the data is read from the cache in later calls.
URLAccumulator can be throttled.
This ensures only a certain amount of requests to a domain
will happen in a given period of time.
URLAccumulator data is loaded.
It has a load() method that is called once when done.
"""
self.url = url
self.data = None
self.redirect = None
self.error = None
if cache != None:
self.cached = True
self._cache = Cache(cache, type)
else:
self.cached = False
self._cache = None
self._domain = URLParser(self.url).domain
self._throttle = throttle
global urlaccumulator_throttle
if not self._domain in urlaccumulator_throttle:
urlaccumulator_throttle[self._domain] = time.time() - self._throttle
self._start = time.time()
self._wait = wait
self._busy = True
self._loaded = False
# Synchronous downloads wait until completed,
# otherwise check the done property.
_thread.start_new_thread(self._retrieve, (self.url,))
if not asynchronous:
while not self._done():
time.sleep(0.1)
def _queued(self):
# Throttles live requests:
# waits until the current time is greater than
# the time of the last request plus the throttle amount.
global urlaccumulator_throttle
if self.cached and self._cache.exists(str(self.url)):
return False
elif time.time() < urlaccumulator_throttle[self._domain] + self._throttle:
return True
else:
urlaccumulator_throttle[self._domain] = time.time()
return False
def _retrieve(self, url):
# When the url data is stored in cache, load that.
# Otherwise, retrieve it from the web.
if self.cached and self._cache.exists(str(url)):
self.data = self._cache.read(str(url))
else:
try:
connection = open(url)
self.data = connection.read()
self.redirect = connection.geturl()
if self.redirect == str(url):
self.redirect = None
except Exception as e:
self.data = ""
self.error = e
self._busy = False
def _done(self):
# Will continue downloading asynchronously.
# 1) When the time limit is exceeded, logs a Timeout error.
# 2) Once uncached data is ready, stores it in cache.
# 3) Loads the data.
# 4) Issues a warning when an error occured.
if (not self._busy or time.time() >= self._start + self._wait) \
and not self._queued(): # 1
if self.data == None and \
self.error == None:
self.data = ""
self.error = URLTimeout()
self.load(self.data)
self._busy = False
if self.cached and not self._cache.exists(str(self.url)) \
and self.data != None and self.data != "": # 2
self._cache.write(str(self.url), str(self.data))
if not self._loaded and self.error == None: # 3
self.load(self.data)
self._loaded = True
if self.error != None: # 4
warn(str(self.error)+" in "+str(self.__class__)+" for "+str(self.url), Warning)
return True
else:
return False
done = property(_done)
def load(self, data):
""" Override this method in subclasses to process downloaded data.
"""
pass
def retrieve(url, wait=60, asynchronous=False, cache=None, type=".html"):
ua = URLAccumulator(url, wait, asynchronous, cache, type)
return ua
#r = retrieve("http://nodebox.net")
#print r.data
#print r.redirect
#url = create("http://api.search.yahoo.com/ContentAnalysisService/V1/termExtraction", method="post")
#url.query["appid"] = "YahooDemo"
#url.query["context"] = "Italian sculptors and painters of the renaissance favored the Virgin Mary for inspiration"
#url.query["query"] = "madonna"
#r = retrieve(url)
#print r.data
#r = retrieve("http://nodebox.net", asynchronous=True)
#while not r.done:
# print "wait...",
# time.sleep(0.1)
#print r.redirect
# XXX - should or should we not do quote_plus() somewhere in here?