/usr/share/pyshared/twill/browser.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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 | """
Implements TwillBrowser, a simple stateful wrapper for mechanize.Browser.
See _browser.py for mechanize code.
"""
OUT=None
# Python imports
import re
# wwwsearch imports
import mechanize
import mechanize
from mechanize import BrowserStateError, LinkNotFoundError
# twill package imports
from _browser import PatchedMechanizeBrowser
from utils import print_form, ConfigurableParsingFactory, \
ResultWrapper, unique_match, HistoryStack
from errors import TwillException
#
# TwillBrowser
#
class TwillBrowser(object):
"""
Wrap mechanize behavior in a simple stateful way.
Public variables:
* result -- mechanize-style 'result' object.
"""
def __init__(self):
#
# create special link/forms parsing code to run tidy on HTML first.
#
factory = ConfigurableParsingFactory()
#
# Create the mechanize browser.
#
b = PatchedMechanizeBrowser(history=HistoryStack(), factory=factory)
self._browser = b
self.result = None
self.last_submit_button = None
#
# create & set a cookie jar.
#
policy = mechanize.DefaultCookiePolicy(rfc2965=True)
cj = mechanize.LWPCookieJar(policy=policy)
self._browser.set_cookiejar(cj)
self.cj = cj
# Ask for MIME type 'text/html' by preference.
self._browser.addheaders = [("Accept", "text/html; */*")]
# ignore robots.txt
self._browser.set_handle_robots(None)
# create an HTTP auth handler
self.creds = mechanize.HTTPPasswordMgr()
# do handle HTTP-EQUIV properly.
self._browser.set_handle_equiv(True)
# callables to be called after each page load.
self._post_load_hooks = []
### get/set HTTP authentication stuff.
def _set_creds(self, creds):
self._creds = creds
self._browser.set_password_manager(creds)
def _get_creds(self):
return self._creds
creds = property(_get_creds, _set_creds)
def go(self, url):
"""
Visit given URL.
"""
try_urls = [ url, ]
# if this is an absolute URL that is just missing the 'http://' at
# the beginning, try fixing that.
if url.find('://') == -1:
full_url = 'http://%s' % (url,) # mimic browser behavior
try_urls.append(full_url)
# if this is a '?' URL, then assume that we want to tack it onto
# the end of the current URL.
if url.startswith('?'):
current_url = self.get_url()
current_url = current_url.split('?')[0]
try_urls = [ current_url + url, ]
success = False
for u in try_urls:
try:
self._journey('open', u)
success = True
break
except IOError: # @CTB test this!
pass
if success:
print>>OUT, '==> at', self.get_url()
else:
raise BrowserStateError("cannot go to '%s'" % (url,))
def reload(self):
"""
Tell the browser to reload the current page.
"""
self._journey('reload')
print>>OUT, '==> reloaded'
def back(self):
"""
Return to previous page, if possible.
"""
try:
self._journey('back')
print>>OUT, '==> back to', self.get_url()
except BrowserStateError:
print>>OUT, '==> back at empty page.'
def get_code(self):
"""
Get the HTTP status code received for the current page.
"""
if self.result:
return self.result.get_http_code()
return None
def get_html(self):
"""
Get the HTML for the current page.
"""
if self.result:
return self.result.get_page()
return None
def get_title(self):
"""
Get content of the HTML title element for the current page.
"""
return self._browser.title()
def get_url(self):
"""
Get the URL of the current page.
"""
if self.result:
return self.result.get_url()
return None
def find_link(self, pattern):
"""
Find the first link with a URL, link text, or name matching the
given pattern.
"""
#
# first, try to find a link matching that regexp.
#
try:
l = self._browser.find_link(url_regex=pattern)
except LinkNotFoundError:
#
# then, look for a text match.
#
try:
l = self._browser.find_link(text_regex=pattern)
except LinkNotFoundError:
#
# finally, look for a name match.
#
try:
l = self._browser.find_link(name_regex=pattern)
except LinkNotFoundError:
l = None
return l
def follow_link(self, link):
"""
Follow the given link.
"""
self._journey('follow_link', link)
print>>OUT, '==> at', self.get_url()
def set_agent_string(self, agent):
"""
Set the agent string to the given value.
"""
for i in xrange(len(self._browser.addheaders)):
if self._browser.addheaders[i][0] == "User-agent":
del self._browser.addheaders[i]
break
self._browser.addheaders += [("User-agent", agent)]
def showforms(self):
"""
Pretty-print all of the forms. Include the global form (form
elements outside of <form> pairs) as forms[0] iff present.
"""
forms = self.get_all_forms()
for n, f in enumerate(forms):
print_form(n, f, OUT)
def showlinks(self):
"""
Pretty-print all of the links.
"""
print>>OUT, 'Links:\n'
for n, link in enumerate(self._browser.links()):
print>>OUT, "%d. %s ==> %s" % (n, link.text, link.url,)
print>>OUT, ''
def showhistory(self):
"""
Pretty-print the history of links visited.
"""
print>>OUT, ''
print>>OUT, 'History: (%d pages total) ' % (len(self._browser._history))
n = 1
for (req, resp) in self._browser._history:
if req and resp: # only print those that back() will go
print>>OUT, "\t%d. %s" % (n, resp.geturl())
n += 1
print>>OUT, ''
def get_all_forms(self):
"""
Return a list of all of the forms, with global_form at index 0
iff present.
"""
global_form = self._browser.global_form()
forms = list(self._browser.forms())
if global_form.controls:
forms.insert(0, global_form)
return forms
def get_form(self, formname):
"""
Return the first form that matches 'formname'.
"""
formname = str(formname)
forms = self.get_all_forms()
# first try ID
for f in forms:
id = f.attrs.get("id")
if id and str(id) == formname:
return f
# next try regexps
regexp = re.compile(formname)
for f in forms:
if f.name and regexp.search(f.name):
return f
# ok, try number
try:
formnum = int(formname)
if formnum >= 1 and formnum <= len(forms):
return forms[formnum - 1]
except ValueError: # int() failed
pass
except IndexError: # formnum was incorrect
pass
return None
def get_form_field(self, form, fieldname):
"""
Return the control that matches 'fieldname'. Must be
a *unique* regexp/exact string match.
"""
fieldname = str(fieldname)
found = None
found_multiple = False
matches = [ c for c in form.controls if str(c.id) == fieldname ]
# test exact match.
if matches:
if unique_match(matches):
found = matches[0]
else:
found_multiple = True # record for error reporting.
matches = [ c for c in form.controls if str(c.name) == fieldname ]
# test exact match.
if matches:
if unique_match(matches):
found = matches[0]
else:
found_multiple = True # record for error reporting.
# test index.
if found is None:
# try num
clickies = [c for c in form.controls]
try:
fieldnum = int(fieldname) - 1
found = clickies[fieldnum]
except ValueError: # int() failed
pass
except IndexError: # fieldnum was incorrect
pass
# test regexp match
if found is None:
regexp = re.compile(fieldname)
matches = [ ctl for ctl in form.controls \
if regexp.search(str(ctl.name)) ]
if matches:
if unique_match(matches):
found = matches[0]
else:
found_multiple = True # record for error
if found is None:
# try value, for readonly controls like submit keys
clickies = [ c for c in form.controls if c.value == fieldname \
and c.readonly ]
if clickies:
if len(clickies) == 1:
found = clickies[0]
else:
found_multiple = True # record for error
# error out?
if found is None:
if not found_multiple:
raise TwillException('no field matches "%s"' % (fieldname,))
else:
raise TwillException('multiple matches to "%s"' % (fieldname,))
return found
def clicked(self, form, control):
"""
Record a 'click' in a specific form.
"""
if self._browser.form != form:
# construct a function to choose a particular form; select_form
# can use this to pick out a precise form.
def choose_this_form(test_form, this_form=form):
if test_form is this_form:
return True
return False
self._browser.select_form(predicate=choose_this_form)
assert self._browser.form == form
self.last_submit_button = None
# record the last submit button clicked.
if isinstance(control, mechanize.SubmitControl):
self.last_submit_button = control
def submit(self, fieldname=None):
"""
Submit the currently clicked form using the given field.
"""
if fieldname is not None:
fieldname = str(fieldname)
if not self.get_all_forms():
raise TwillException("no forms on this page!")
ctl = None
form = self._browser.form
if form is None:
forms = [ i for i in self.get_all_forms() ]
if len(forms) == 1:
form = forms[0]
else:
raise TwillException("""\
more than one form; you must select one (use 'fv') before submitting\
""")
# no fieldname? see if we can use the last submit button clicked...
if not fieldname:
if self.last_submit_button:
ctl = self.last_submit_button
else:
# get first submit button in form.
submits = [ c for c in form.controls \
if isinstance(c, mechanize.SubmitControl) ]
if len(submits):
ctl = submits[0]
else:
# fieldname given; find it.
ctl = self.get_form_field(form, fieldname)
#
# now set up the submission by building the request object that
# will be sent in the form submission.
#
if ctl:
# submit w/button
print>>OUT, """\
Note: submit is using submit button: name="%s", value="%s"
""" % (ctl.name, ctl.value)
if isinstance(ctl, mechanize.ImageControl):
request = ctl._click(form, (1,1), "", mechanize.Request)
else:
request = ctl._click(form, True, "", mechanize.Request)
else:
# submit w/o submit button.
request = form._click(None, None, None, None, 0, None,
"", mechanize.Request)
#
# add referer information. this may require upgrading the
# request object to have an 'add_unredirected_header' function.
#
upgrade = self._browser._ua_handlers.get('_http_request_upgrade')
if upgrade:
request = upgrade.http_request(request)
request = self._browser._add_referer_header(request)
#
# now actually GO.
#
self._journey('open', request)
def save_cookies(self, filename):
"""
Save cookies into the given file.
"""
self.cj.save(filename, ignore_discard=True, ignore_expires=True)
def load_cookies(self, filename):
"""
Load cookies from the given file.
"""
self.cj.load(filename, ignore_discard=True, ignore_expires=True)
def clear_cookies(self):
"""
Delete all of the cookies.
"""
self.cj.clear()
def show_cookies(self):
"""
Pretty-print all of the cookies.
"""
print>>OUT, '''
There are %d cookie(s) in the cookiejar.
''' % (len(self.cj,))
if len(self.cj):
for cookie in self.cj:
print>>OUT, '\t', cookie
print>>OUT, ''
#### private functions.
def _journey(self, func_name, *args, **kwargs):
"""
'func_name' should be the name of a mechanize method that either
returns a 'result' object or raises a HTTPError, e.g.
one of 'open', 'reload', 'back', or 'follow_link'.
journey then runs that function with the given arguments and turns
the results into a nice friendly standard ResultWrapper object, which
is stored as 'self.result'.
All exceptions other than HTTPError are unhandled.
(Idea stolen straight from PBP.)
"""
# reset
self.last_submit_button = None
self.result = None
func = getattr(self._browser, func_name)
try:
r = func(*args, **kwargs)
except mechanize.HTTPError, e:
r = e
# seek back to 0 if a seek() function is present.
seek_fn = getattr(r, 'seek', None)
if seek_fn:
seek_fn(0)
# some URLs, like 'file:' URLs, don't have return codes. In this
# case, assume success (code=200) if no such attribute.
code = getattr(r, 'code', 200)
## special case refresh loops!?
if code == 'refresh':
raise TwillException("""\
infinite refresh loop discovered; aborting.
Try turning off acknowledge_equiv_refresh...""")
self.result = ResultWrapper(code, r.geturl(), r.read())
#
# Now call all of the post load hooks with the function name.
#
for callable in self._post_load_hooks:
callable(func_name, *args, **kwargs)
|