/usr/share/pyshared/twill/utils.py is in python-twill 0.9-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 | """
Various ugly utility functions for twill.
Apart from various simple utility functions, twill's robust parsing
code is implemented in the ConfigurableParsingFactory class.
"""
from cStringIO import StringIO
import os
import base64
import subprocess
import mechanize
import mechanize
from mechanize._util import time
from mechanize._http import HTTPRefreshProcessor
from mechanize import BrowserStateError
from errors import TwillException
class ResultWrapper:
"""
Deal with mechanize/urllib2/whatever results, and present them in a
unified form. Returned by 'journey'-wrapped functions.
"""
def __init__(self, http_code, url, page):
if http_code is not None:
self.http_code = int(http_code)
else:
self.http_code = 200
self.url = url
self.page = page
def get_url(self):
return self.url
def get_http_code(self):
return self.http_code
def get_page(self):
return self.page
def trunc(s, length):
"""
Truncate a string s to length length, by cutting off the last
(length-4) characters and replacing them with ' ...'
"""
if not s:
return ''
if len(s) > length:
return s[:length-4] + ' ...'
return s
def print_form(n, f, OUT):
"""
Pretty-print the given form, assigned # n.
"""
if f.name:
print>>OUT, '\nForm name=%s (#%d)' % (f.name, n + 1)
else:
print>>OUT, '\nForm #%d' % (n + 1,)
if f.controls:
print>>OUT, "## ## __Name__________________ __Type___ __ID________ __Value__________________"
submit_indices = {}
n = 1
for c in f.controls:
if c.is_of_kind('clickable'):
submit_indices[c] = n
n += 1
clickies = [c for c in f.controls if c.is_of_kind('clickable')]
nonclickies = [c for c in f.controls if c not in clickies]
for n, field in enumerate(f.controls):
if hasattr(field, 'items'):
items = [ i.name for i in field.items ]
value_displayed = "%s of %s" % (field.value, items)
else:
value_displayed = "%s" % (field.value,)
if field.is_of_kind('clickable'):
submit_index = "%-2s" % (submit_indices[field],)
else:
submit_index = " "
strings = ("%-2s" % (n + 1,),
submit_index,
"%-24s %-9s" % (trunc(str(field.name), 24),
trunc(field.type, 9)),
"%-12s" % (trunc(field.id or "(None)", 12),),
trunc(value_displayed, 40),
)
for s in strings:
print>>OUT, s,
print>>OUT, ''
print ''
def make_boolean(value):
"""
Convert the input value into a boolean like so:
>> make_boolean('true')
True
>> make_boolean('false')
False
>> make_boolean('1')
True
>> make_boolean('0')
False
>> make_boolean('+')
True
>> make_boolean('-')
False
"""
value = str(value)
value = value.lower().strip()
# true/false
if value in ('true', 'false'):
if value == 'true':
return True
return False
# 0/nonzero
try:
ival = int(value)
return bool(ival)
except ValueError:
pass
# +/-
if value in ('+', '-'):
if value == '+':
return True
return False
# on/off
if value in ('on', 'off'):
if value == 'on':
return True
return False
raise TwillException("unable to convert '%s' into true/false" % (value,))
def set_form_control_value(control, val):
"""
Helper function to deal with setting form values on checkboxes, lists etc.
"""
if isinstance(control, mechanize.CheckboxControl):
try:
checkbox = control.get()
checkbox.selected = make_boolean(val)
return
except mechanize.AmbiguityError:
# if there's more than one checkbox, use the behaviour for
# mechanize.ListControl, below.
pass
if isinstance(control, mechanize.ListControl):
#
# for ListControls (checkboxes, multiselect, etc.) we first need
# to find the right *value*. Then we need to set it +/-.
#
# figure out if we want to *select* it, or if we want to *deselect*
# it (flag T/F). By default (no +/-) select...
if val.startswith('-'):
val = val[1:]
flag = False
else:
flag = True
if val.startswith('+'):
val = val[1:]
# now, select the value.
try:
item = control.get(name=val)
except mechanize.ItemNotFoundError:
try:
item = control.get(label=val)
except mechanize.AmbiguityError:
raise mechanize.ItemNotFoundError('multiple matches to value/label "%s" in list control' % (val,))
except mechanize.ItemNotFoundError:
raise mechanize.ItemNotFoundError('cannot find value/label "%s" in list control' % (val,))
if flag:
item.selected = 1
else:
item.selected = 0
else:
control.value = val
def _all_the_same_submit(matches):
"""
Utility function to check to see if a list of controls all really
belong to the same control: for use with checkboxes, hidden, and
submit buttons.
"""
name = None
value = None
for match in matches:
if match.type not in ['submit', 'hidden']:
return False
if name is None:
name = match.name
value = match.value
else:
if match.name != name or match.value!= value:
return False
return True
def _all_the_same_checkbox(matches):
"""
Check whether all these controls are actually the the same
checkbox.
Hidden controls can combine with checkboxes, to allow form
processors to ensure a False value is returned even if user
does not check the checkbox. Without the hidden control, no
value would be returned.
"""
name = None
for match in matches:
if match.type not in ['checkbox', 'hidden']:
return False
if name is None:
name = match.name
else:
if match.name != name:
return False
return True
def unique_match(matches):
return len(matches) == 1 or \
_all_the_same_checkbox(matches) or \
_all_the_same_submit(matches)
#
# stuff to run 'tidy'...
#
_tidy_cmd = ["tidy", "-q", "-ashtml"]
_tidy_exists = True
def run_tidy(html):
"""
Run the 'tidy' command-line program on the given HTML string.
Return a 2-tuple (output, errors). (None, None) will be returned if
'tidy' doesn't exist or otherwise fails.
"""
global _tidy_cmd, _tidy_exists
from commands import _options
require_tidy = _options.get('require_tidy')
if not _tidy_exists:
if require_tidy:
raise TwillException("tidy does not exist and require_tidy is set")
return (None, None)
#
# run the command, if we think it exists
#
clean_html = None
if _tidy_exists:
try:
process = subprocess.Popen(_tidy_cmd, stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE, bufsize=0,
shell=False)
(stdout, stderr) = process.communicate(html)
clean_html = stdout
errors = stderr
except OSError:
_tidy_exists = False
errors = None
if require_tidy and clean_html is None:
raise TwillException("tidy does not exist and require_tidy is set")
return (clean_html, errors)
class ConfigurableParsingFactory(mechanize.Factory):
"""
A factory that listens to twill config options regarding parsing.
First: clean up passed-in HTML using tidy?
Second: parse using the regular parser, or BeautifulSoup?
Third: should we fail on, or ignore, parse errors?
"""
def __init__(self):
self.basic_factory = mechanize.DefaultFactory()
self.soup_factory = mechanize.RobustFactory()
self.set_response(None)
def set_request_class(self, request_class):
self.basic_factory.set_request_class(request_class)
self.soup_factory.set_request_class(request_class)
def set_response(self, response):
if not response:
self.factory = None
self._orig_html = self._html = self._url = None
return
###
if self.use_BS():
self.factory = self.soup_factory
else:
self.factory = self.basic_factory
cleaned_response = self._cleanup_html(response)
self.factory.set_response(cleaned_response)
def links(self):
return self.factory.links()
def forms(self):
return self.factory.forms()
def get_global_form(self):
return self.factory.global_form
global_form = property(get_global_form)
def _get_title(self):
return self.factory.title
title = property(_get_title)
def _get_encoding(self):
return self.factory.encoding
encoding = property(_get_encoding)
def _get_is_html(self):
return self.factory.is_html
is_html = property(_get_is_html)
def _cleanup_html(self, response):
response.seek(0)
self._orig_html = response.read()
self._url = response.geturl()
response.seek(0)
self._html = self._orig_html
from twill.commands import _options
use_tidy = _options.get('use_tidy')
if use_tidy:
(new_html, errors) = run_tidy(self._html)
if new_html:
self._html = new_html
return mechanize.make_response(self._html, response._headers.items(),
response._url, response.code,
response.msg)
def use_BS(self):
from twill.commands import _options
flag = _options.get('use_BeautifulSoup')
return flag
###
class FixedHTTPBasicAuthHandler(mechanize.HTTPBasicAuthHandler):
"""
Fix a bug that exists through Python 2.4 (but NOT in 2.5!)
"""
def retry_http_basic_auth(self, host, req, realm):
user,pw = self.passwd.find_user_password(realm, req.get_full_url())
# ----------------------------------------------^^^^^^^^^^^^^^^^^^ CTB
if pw is not None:
raw = "%s:%s" % (user, pw)
auth = 'Basic %s' % base64.encodestring(raw).strip()
if req.headers.get(self.auth_header, None) == auth:
return None
req.add_header(self.auth_header, auth)
return self.parent.open(req)
else:
return None
###
_debug_print_refresh = False
class FunctioningHTTPRefreshProcessor(HTTPRefreshProcessor):
"""
Fix an issue where the 'content' component of the http-equiv=refresh
tag may not contain 'url='. CTB hack.
"""
def http_response(self, request, response):
from twill.commands import OUT, _options
do_refresh = _options.get('acknowledge_equiv_refresh')
code, msg, hdrs = response.code, response.msg, response.info()
if code == 200 and hdrs.has_key("refresh") and do_refresh:
refresh = hdrs.getheaders("refresh")[0]
if _debug_print_refresh:
print>>OUT, "equiv-refresh DEBUG: code 200, hdrs has 'refresh'"
print>>OUT, "equiv-refresh DEBUG: refresh header is", refresh
i = refresh.find(";")
if i != -1:
pause, newurl_spec = refresh[:i], refresh[i+1:]
pause = int(pause)
if _debug_print_refresh:
print>>OUT, "equiv-refresh DEBUG: pause:", pause
print>>OUT, "equiv-refresh DEBUG: new url:", newurl_spec
j = newurl_spec.find("=")
if j != -1:
newurl = newurl_spec[j+1:]
else:
newurl = newurl_spec
if _debug_print_refresh:
print>>OUT, "equiv-refresh DEBUG: final url:", newurl
print>>OUT, "Following HTTP-EQUIV=REFRESH to %s" % (newurl,)
if (self.max_time is None) or (pause <= self.max_time):
if pause != 0 and 0: # CTB hack! ==# and self.honor_time:
time.sleep(pause)
hdrs["location"] = newurl
# hardcoded http is NOT a bug
response = self.parent.error(
"http", request, response,
"refresh", msg, hdrs)
return response
https_response = http_response
####
class HistoryStack(mechanize._mechanize.History):
def __len__(self):
return len(self._history)
def __getitem__(self, i):
return self._history[i]
####
def _is_valid_filename(f):
return not (f.endswith('~') or f.endswith('.bak') or f.endswith('.old'))
def gather_filenames(arglist):
"""
Collect script files from within directories.
"""
l = []
for filename in arglist:
if os.path.isdir(filename):
thislist = []
for (dirpath, dirnames, filenames) in os.walk(filename):
for f in filenames:
if _is_valid_filename(f):
f = os.path.join(dirpath, f)
thislist.append(f)
thislist.sort()
l.extend(thislist)
else:
l.append(filename)
return l
|