forked from pyload/pyload
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathCurlRequest.py
More file actions
323 lines (249 loc) · 10.7 KB
/
Copy pathCurlRequest.py
File metadata and controls
323 lines (249 loc) · 10.7 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
# -*- coding: utf-8 -*-
###############################################################################
# Copyright(c) 2008-2012 pyLoad Team
# http://www.pyload.org
#
# This file is part of pyLoad.
# pyLoad is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as
# published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# Subjected to the terms and conditions in LICENSE
#
# @author: RaNaN
###############################################################################
import pycurl
from codecs import getincrementaldecoder, lookup, BOM_UTF8
from urllib import quote, urlencode
from httplib import responses
from cStringIO import StringIO
from pyload.plugins.Base import Abort
from pyload.network.CookieJar import CookieJar
from ..Request import Request, ResponseException
def myquote(url):
return quote(url.encode('utf8') if isinstance(url, unicode) else url, safe="%/:=&?~#+!$,;'@()*[]")
def myurlencode(data):
data = dict(data)
return urlencode(dict((x.encode('utf8') if isinstance(x, unicode) else x, \
y.encode('utf8') if isinstance(y, unicode) else y ) for x, y in data.iteritems()))
bad_headers = range(400, 418) + range(500, 506)
pycurl.global_init(pycurl.GLOBAL_DEFAULT)
class CurlRequest(Request):
""" Request class based on libcurl """
__version__ = "0.1"
CONTEXT_CLASS = CookieJar
def __init__(self, *args, **kwargs):
self.c = pycurl.Curl()
Request.__init__(self, *args, **kwargs)
self.rep = StringIO()
self.lastURL = None
self.lastEffectiveURL = None
# cookiejar defines the context
self.cj = self.context
self.c.setopt(pycurl.WRITEFUNCTION, self.write)
self.c.setopt(pycurl.HEADERFUNCTION, self.writeHeader)
# TODO: addHeader
@property
def http(self):
print "Deprecated usage of req.http, just use req instead"
return self
def initContext(self):
self.initHandle()
if self.config:
self.setInterface(self.config)
self.initOptions(self.config)
def initHandle(self):
""" sets common options to curl handle """
self.c.setopt(pycurl.FOLLOWLOCATION, 1)
self.c.setopt(pycurl.MAXREDIRS, 5)
self.c.setopt(pycurl.CONNECTTIMEOUT, 30)
self.c.setopt(pycurl.NOSIGNAL, 1)
self.c.setopt(pycurl.NOPROGRESS, 1)
if hasattr(pycurl, "AUTOREFERER"):
self.c.setopt(pycurl.AUTOREFERER, 1)
self.c.setopt(pycurl.SSL_VERIFYPEER, 0)
# Interval for low speed, detects connection loss, but can abort dl if hoster stalls the download
self.c.setopt(pycurl.LOW_SPEED_TIME, 45)
self.c.setopt(pycurl.LOW_SPEED_LIMIT, 5)
# don't save the cookies
self.c.setopt(pycurl.COOKIEFILE, "")
self.c.setopt(pycurl.COOKIEJAR, "")
#self.c.setopt(pycurl.VERBOSE, 1)
self.c.setopt(pycurl.USERAGENT,
"Mozilla/5.0 (Windows NT 6.1; Win64; x64;en; rv:5.0) Gecko/20110619 Firefox/5.0")
if pycurl.version_info()[7]:
self.c.setopt(pycurl.ENCODING, "gzip, deflate")
self.c.setopt(pycurl.HTTPHEADER, ["Accept: */*",
"Accept-Language: en-US,en",
"Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7",
"Connection: keep-alive",
"Keep-Alive: 300",
"Expect:"])
def setInterface(self, options):
interface, proxy, ipv6 = options["interface"], options["proxies"], options["ipv6"]
if interface and interface.lower() != "none":
self.c.setopt(pycurl.INTERFACE, str(interface))
if proxy:
if proxy["type"] == "socks4":
self.c.setopt(pycurl.PROXYTYPE, pycurl.PROXYTYPE_SOCKS4)
elif proxy["type"] == "socks5":
self.c.setopt(pycurl.PROXYTYPE, pycurl.PROXYTYPE_SOCKS5)
else:
self.c.setopt(pycurl.PROXYTYPE, pycurl.PROXYTYPE_HTTP)
self.c.setopt(pycurl.PROXY, str(proxy["address"]))
self.c.setopt(pycurl.PROXYPORT, proxy["port"])
if proxy["username"]:
self.c.setopt(pycurl.PROXYUSERPWD, str("%s:%s" % (proxy["username"], proxy["password"])))
if ipv6:
self.c.setopt(pycurl.IPRESOLVE, pycurl.IPRESOLVE_WHATEVER)
else:
self.c.setopt(pycurl.IPRESOLVE, pycurl.IPRESOLVE_V4)
if "timeout" in options:
self.c.setopt(pycurl.LOW_SPEED_TIME, options["timeout"])
if "auth" in options:
self.c.setopt(pycurl.USERPWD, str(options["auth"]))
def initOptions(self, options):
""" Sets same options as available in pycurl """
for k, v in options.iteritems():
if hasattr(pycurl, k):
self.c.setopt(getattr(pycurl, k), v)
def setRequestContext(self, url, get, post, referer, cookies, multipart=False):
""" sets everything needed for the request """
url = myquote(url)
if get:
get = urlencode(get)
url = "%s?%s" % (url, get)
self.c.setopt(pycurl.URL, url)
if post:
self.c.setopt(pycurl.POST, 1)
if not multipart:
if type(post) == unicode:
post = str(post) #unicode not allowed
elif type(post) == str:
pass
else:
post = myurlencode(post)
self.c.setopt(pycurl.POSTFIELDS, post)
else:
post = [(x, y.encode('utf8') if type(y) == unicode else y ) for x, y in post.iteritems()]
self.c.setopt(pycurl.HTTPPOST, post)
else:
self.c.setopt(pycurl.POST, 0)
if referer and self.lastURL:
self.c.setopt(pycurl.REFERER, str(self.lastURL))
else:
self.c.setopt(pycurl.HTTPHEADER, ["Referer:"])
if cookies:
for c in self.cj.output().splitlines():
self.c.setopt(pycurl.COOKIELIST, c)
else:
# Magic string that erases all cookies
self.c.setopt(pycurl.COOKIELIST, "ALL")
# TODO: remove auth again
if "auth" in self.options:
self.c.setopt(pycurl.USERPWD, str(self.options["auth"]))
def load(self, url, get={}, post={}, referer=True, cookies=True, just_header=False, multipart=False, decode=False):
""" load and returns a given page """
self.setRequestContext(url, get, post, referer, cookies, multipart)
# TODO: use http/rfc message instead
self.header = ""
if "header" in self.options:
self.c.setopt(pycurl.HTTPHEADER, self.options["header"])
if just_header:
self.c.setopt(pycurl.FOLLOWLOCATION, 0)
self.c.setopt(pycurl.NOBODY, 1) #TODO: nobody= no post?
# overwrite HEAD request, we want a common request type
if post:
self.c.setopt(pycurl.CUSTOMREQUEST, "POST")
else:
self.c.setopt(pycurl.CUSTOMREQUEST, "GET")
try:
self.c.perform()
rep = self.header
finally:
self.c.setopt(pycurl.FOLLOWLOCATION, 1)
self.c.setopt(pycurl.NOBODY, 0)
self.c.unsetopt(pycurl.CUSTOMREQUEST)
else:
self.c.perform()
rep = self.getResponse()
self.c.setopt(pycurl.POSTFIELDS, "")
self.lastURL = myquote(url)
self.lastEffectiveURL = self.c.getinfo(pycurl.EFFECTIVE_URL)
self.code = self.verifyHeader()
if cookies:
self.parseCookies()
if decode:
rep = self.decodeResponse(rep)
return rep
def parseCookies(self):
for c in self.c.getinfo(pycurl.INFO_COOKIELIST):
#http://xiix.wordpress.com/2006/03/23/mozillafirefox-cookie-format
domain, flag, path, secure, expires, name, value = c.split("\t")
# http only was added in py 2.6
domain = domain.replace("#HttpOnly_", "")
self.cj.setCookie(domain, name, value, path, expires, secure)
def verifyHeader(self):
""" raise an exceptions on bad headers """
code = int(self.c.getinfo(pycurl.RESPONSE_CODE))
if code in bad_headers:
raise ResponseException(code, responses.get(code, "Unknown statuscode"))
return code
def getResponse(self):
""" retrieve response from string io """
if self.rep is None: return ""
value = self.rep.getvalue()
self.rep.close()
self.rep = StringIO()
return value
def decodeResponse(self, rep):
""" decode with correct encoding, relies on header """
header = self.header.splitlines()
encoding = "utf8" # default encoding
for line in header:
line = line.lower().replace(" ", "")
if not line.startswith("content-type:") or \
("text" not in line and "application" not in line):
continue
none, delemiter, charset = line.rpartition("charset=")
if delemiter:
charset = charset.split(";")
if charset:
encoding = charset[0]
try:
#self.log.debug("Decoded %s" % encoding )
if lookup(encoding).name == 'utf-8' and rep.startswith(BOM_UTF8):
encoding = 'utf-8-sig'
decoder = getincrementaldecoder(encoding)("replace")
rep = decoder.decode(rep, True)
#TODO: html_unescape as default
except LookupError:
self.log.debug("No Decoder found for %s" % encoding)
except Exception:
self.log.debug("Error when decoding string from %s." % encoding)
return rep
def write(self, buf):
""" writes response """
if self.rep.tell() > 1000000 or self.doAbort:
rep = self.getResponse()
if self.doAbort: raise Abort()
f = open("response.dump", "wb")
f.write(rep)
f.close()
raise Exception("Loaded Url exceeded limit")
self.rep.write(buf)
def writeHeader(self, buf):
""" writes header """
self.header += buf
def reset(self):
self.cj.clear()
self.options.clear()
def close(self):
""" cleanup, unusable after this """
self.rep.close()
if hasattr(self, "cj"):
del self.cj
if hasattr(self, "c"):
self.c.close()
del self.c