def set_clickable_tag(self, tag_name, attr=None, value=None):
self._analyzer['clickable_tags'].append({
'tag': tag_name,
'attr': attr,
'value': value
})
DomAnalyzer.add_clickable_tag(tag_name, attr, value)
def save_state(self, state, depth):
candidate_clickables = {}
inputs = {}
selects = {}
checkboxes = {}
radios = {}
for stateDom in state.get_dom_list(self.configuration):
iframe_path_list = stateDom['iframe_path']
dom = stateDom['dom']
# define iframe_key of dom dict
iframe_key = ';'.join(iframe_path_list) if iframe_path_list else None
candidate_clickables[iframe_key] = DomAnalyzer.get_candidate_clickables_soup(dom)
inputs[iframe_key] = DomAnalyzer.get_inputs(dom)
selects[iframe_key] = DomAnalyzer.get_selects(dom)
checkboxes[iframe_key] = DomAnalyzer.get_checkboxes(dom)
radios[iframe_key] = DomAnalyzer.get_radios(dom)
state.set_candidate_clickables(candidate_clickables)
state.set_inputs(inputs)
state.set_selects(selects)
state.set_checkboxes(checkboxes)
state.set_radios(radios)
state.set_depth(depth)
self.save_dom(state)
def save_state(self, state, depth):
candidate_clickables = {}
inputs = {}
selects = {}
checkboxes = {}
radios = {}
for stateDom in state.get_dom_list(self.configuration):
iframe_path_list = stateDom['iframe_path']
dom = stateDom['dom']
# define iframe_key of dom dict
iframe_key = ';'.join(
iframe_path_list) if iframe_path_list else None
candidate_clickables[
iframe_key] = DomAnalyzer.get_candidate_clickables_soup(dom)
inputs[iframe_key] = DomAnalyzer.get_inputs(dom)
selects[iframe_key] = DomAnalyzer.get_selects(dom)
checkboxes[iframe_key] = DomAnalyzer.get_checkboxes(dom)
radios[iframe_key] = DomAnalyzer.get_radios(dom)
state.set_candidate_clickables(candidate_clickables)
state.set_inputs(inputs)
state.set_selects(selects)
state.set_checkboxes(checkboxes)
state.set_radios(radios)
state.set_depth(depth)
self.save_dom(state)
def get_all_normalize_dom(self, configuration):
if not self._dom_list:
dom_list = self.get_dom_list(configuration)
dom = [ DomAnalyzer.normalize( stateDom['dom'] ) for stateDom in dom_list ]
dom = "\n".join(dom)
return dom
else:
dom = [ DomAnalyzer.normalize( stateDom['dom'] ) for stateDom in self._dom_list ]
dom = "\n".join(dom)
return dom
def crawl(self, depth, prev_state=None):
if depth <= self.configuration.get_max_depth():
cs = self.automata.get_current_state()
if not self.violate_invariant(cs.get_dom(), cs.get_id()):
candidate_clickables = DomAnalyzer.get_clickables(cs.get_dom(), prev_state.get_dom() if prev_state else None)
self.num_clickables['unexamined'] += len(candidate_clickables)
for clickable in candidate_clickables:
# prefetch image of the clickable
time.sleep(0.2) # time for correctly fetching image
img_name = cs.get_id() + '-' + clickable.get_id() + '.png'
img_data = self.executor.get_screenshot(clickable)
# fire the clickable
logger.debug('Fire event in state %s', cs.get_id())
self.executor.empty_form(clickable)
self.executor.fill_form(clickable)
ft = FireEventThread(self.executor, clickable)
ft.start()
ft.join(self.configuration.get_sleep_time()*2) # time out after sleep_time*2 seconds
if ft.is_alive(): # timed out
logger.error('No response while firing an event. Execution sequences:')
self.exe_stack.append(clickable) # add the clickable triggering No Response
for c in self.exe_stack:
logger.error(c)
logger.error('Total clickables found: %d (true: %d, false: %d, unexamined: %d)',
self.num_clickables['unexamined'] + self.num_clickables['true'] + self.num_clickables['false'],
self.num_clickables['true'],
self.num_clickables['false'],
self.num_clickables['unexamined']
)
logger.error('Program terminated.')
sys.exit()
time.sleep(self.configuration.get_sleep_time())
self.num_clickables['unexamined'] -= 1
new_dom = self.executor.get_source()
if DomAnalyzer.is_equal(cs.get_dom(), new_dom):
self.num_clickables['false'] += 1
else:
self.num_clickables['true'] += 1
cs.add_clickable(clickable)
self.exe_stack.append(clickable)
self.save_screenshot(img_name, img_data, 'clickable')
ns, is_newly_added = self.automata.add_state(State(new_dom))
self.automata.add_edge(cs, ns, clickable)
if is_newly_added:
self.save_screenshot(ns.get_id() + '.png', self.executor.get_screenshot(), 'state')
self.save_dom(ns)
self.automata.change_state(ns)
self.crawl(depth+1, cs)
self.exe_stack.pop(-1)
self.automata.change_state(cs)
self.backtrack(cs)
def set_tag_with_attribute_normalizer(self,
tag_name,
attr=None,
value=None,
mode=None):
self._analyzer['tag_with_attribute_normalizers'].append({
'tag': tag_name,
'attr': attr,
'value': value,
'mode': mode
})
DomAnalyzer.add_tag_with_attribute_normalizer(tag_name, attr, value,
mode)
def get_all_normalize_dom(self, configuration):
if not self._dom_list:
dom_list = self.get_dom_list(configuration)
dom = [
DomAnalyzer.normalize(stateDom['dom']) for stateDom in dom_list
]
dom = "\n".join(dom)
return dom
else:
dom = [
DomAnalyzer.normalize(stateDom['dom'])
for stateDom in self._dom_list
]
dom = "\n".join(dom)
return dom
def get_dom_list(self, configuration):
#save dom of iframe in list of StateDom [iframe_path_list, dom, url/src, normalize dom]
dom_list = []
new_dom = self.switch_iframe_and_get_source()
url = self.get_url()
soup = BeautifulSoup(new_dom, 'html5lib')
for frame in configuration.get_frame_tags():
for iframe_tag in soup.find_all(frame):
iframe_xpath = DomAnalyzer._get_xpath(iframe_tag)
iframe_src = iframe_tag['src'] if iframe_tag.has_attr(
'src') else None
try: #not knowing what error in iframe_tag.clear(): no src
if configuration.is_dom_inside_iframe():
self.get_dom_of_iframe(configuration, dom_list,
[iframe_xpath], iframe_src)
iframe_tag.clear()
except Exception as e:
logging.error(
' get_dom_of_iframe: %s \t\t__from crawler.py get_dom_list() ',
str(e))
dom_list.append({
'url': url,
'dom': str(soup),
'iframe_path': None,
})
brID = self.browserID
return dom_list, url
def get_dom_of_iframe(self, configuration, dom_list, iframe_xpath_list,
src):
dom = self.switch_iframe_and_get_source(iframe_xpath_list)
soup = BeautifulSoup(dom, 'html5lib')
for frame in configuration.get_frame_tags():
for iframe_tag in soup.find_all(frame):
iframe_xpath = DomAnalyzer._get_xpath(iframe_tag)
iframe_xpath_list.append(iframe_xpath)
iframe_src = iframe_tag['src'] if iframe_tag.has_attr(
'src') else None
if iframe_src and self.is_same_domain(configuration,
iframe_src):
try:
print('_2:', iframe_xpath, ' : ', iframe_src)
self.get_dom_of_iframe(configuration, dom_list,
iframe_xpath_list, iframe_src)
iframe_tag.clear()
except Exception as e:
logging.error(
' get_dom_of_iframe: %s \t\t__from crawler.py get_dom_list() ',
str(e))
dom_list.append({
'url': src,
'dom': str(soup.prettify()),
'iframe_path': iframe_xpath_list,
})
def get_clickable(self):
dom = '''
<html><body>
<form data-prop="formNode" class="sup-form sup-account-form">
<p>
<input placeholder="Your name" data-prop="nameNode" data-event="input:onInfoInput" class="sup-info-name" data-l10n-id="setup-info-name" x-inputmode="verbatim" inputmode="verbatim" dir="auto" required="" type="text">
<button type="reset"></button>
</p>
<p>
<input placeholder="*****@*****.**" data-prop="emailNode" data-event="input:onInfoInput" class="sup-info-email" data-l10n-id="setup-info-email" dir="auto" required="" type="email">
<button type="reset"></button>
</p>
<p>
<button data-prop="nextButton" data-event="click:onNext" class="sup-info-next-btn recommend" disabled="">
<span data-l10n-id="setup-info-next">Next</span>
</button>
<button data-prop="manualConfig" data-event="click:onClickManualConfig" class="sup-manual-config-btn" disabled="" data-l10n-id="setup-manual-config2">Manual setup</button>
</p>
</form>
</body></html>
'''
clickables = DomAnalyzer.get_clickables(dom)
self.assertEqual(len(clickables), 4)
self.assertEqual(len(clickables[3].get_forms()), 1)
self.assertEqual(len(clickables[3].get_forms()[0].get_inputs()), 2)
self.assertEqual(clickables[3].get_forms()[0].get_inputs()[1].get_xpath(), '//html/body/form[1]/p[2]/input[1]')
self.assertEqual(clickables[3].get_forms()[0].get_inputs()[1].get_type(), 'email')
'''
def analysis_with_other_browser( self ):
# 1. check url is the same or not : should be the same
# 2. check state is the same or not : should be the same
dom_list1,url1 =self.executor.get_dom_list(self.configuration)
dom_list2,url2 =self.other_executor.get_dom_list(self.configuration)
if url1!=url2:
print ("===different pages")
logging.info('CBT:browser 1 page:%s browser 2 page:%s| page are different', url1, url2 )
elif url1==url2:
string="url is same: "+self.executor.get_url()
print(string)
logging.info(' CBT_events : '+ string )
'''
if dom_list1==dom_list2:
string="dom tree is same: "+self.executor.get_url()
print(string)
logging.info(' CBT_events : '+ string )
'''
if DomAnalyzer.is_equal(dom_list1[0]['dom'],dom_list2[0]['dom']):
print("===same dom tree")
logging.info('CBT: same dom tree')
else:
print ("===different dom_tree")
#need domtree mapping
logging.info('CBT: browser 1 dom:%s browser 2 dom:%s| dom trees are different', url1, url2 )
def get_dom_list(self, configuration):
#save dom of iframe in list of StateDom [iframe_path_list, dom, url/src, normalize dom]
dom_list = []
new_dom = self.get_source()
url = self.get_url()
soup = BeautifulSoup(new_dom, 'html5lib')
for frame in configuration.get_frame_tags():
for iframe_tag in soup.find_all(frame):
iframe_xpath = DomAnalyzer._get_xpath(iframe_tag)
iframe_src = iframe_tag['src'] if iframe_tag.has_attr('src') else None
if configuration.is_dom_inside_iframe() and iframe_src and self.is_same_domain( configuration, iframe_src ):
try: #not knowing what error in iframe_tag.clear(): no src
print( '_1:',iframe_xpath,' : ',iframe_src )
self.get_dom_of_iframe(configuration, dom_list, [iframe_xpath], iframe_src)
iframe_tag.clear()
except Exception as e:
logging.error(' get_dom_of_iframe: %s \t\t__from crawler.py get_dom_list() ', str(e))
dom_list.append( {
'url' : url,
'dom' : str(soup.prettify()),
'iframe_path' : None,
} )
return dom_list, url
def add_new_events(self, state, prev_state, depth):
for clickables, iframe_key in DomAnalyzer.get_clickables(state, prev_state if prev_state else None):
for clickable in clickables:
self.crawler.action_events.append( {
'state' : state,
'action' : { 'clickable':clickable, 'iframe_key':iframe_key },
'depth' : depth,
} )
def check_dom_tree(self):
if url1!=url2:
print ("===different pages")
logging.info('CBT:browser 1 page:%s browser 2 page:%s| page are different', url1, url2 )
if DomAnalyzer.is_equal(dom_tree1,dom_tree2):
print("===same dom tree")
logging.info('CBT: same dom tree')
else:
print ("===different dom_tree")
#need domtree mapping
logging.info('CBT: browser 1 dom:%s browser 2 dom:%s| dom trees are different', url1, url2 )
def add_state(self, state):
# check if the automata is empty
if not self._initial_state:
self._initial_state = state
self._current_state = state
else:
# check if the dom is duplicated
for s in self._states:
if DomAnalyzer.is_equal(s.get_dom(), state.get_dom()):
return s, False
state_id = state.get_id() if state.get_id() else str(len(self._states))
state.set_id(state_id)
self._states.append(state)
return state, True
def test_get_xpath(self):
html_doc = '''
<html><body>
<div></div>
<div>
<form>
<input><button></button>
</form>
</div>
</body></html>
'''
soup = BeautifulSoup(html_doc, 'html.parser')
form = soup.find('form')
self.assertEqual(DomAnalyzer._get_xpath(form), '//html/body/div[2]/form[1]')
def add_state(self, state):
# check if the automata is empty
if not self._initial_state:
self._initial_state = state
self._current_state = state
else:
# check if the dom is duplicated
for s in self._states:
if DomAnalyzer.is_equal(s.get_dom(), state.get_dom()):
return s, False
state_id = state.get_id() if state.get_id() else str(len(self._states))
state.set_id(state_id)
self._states.append(state)
return state, True
def add_new_events(self, state, prev_state, depth):
candidate_clickables = []
for clickables, iframe_key in DomAnalyzer.get_clickables(state, prev_state if prev_state else None):
for clickable in clickables:
candidate_clickables.append( (clickable, iframe_key) )
if not candidate_clickables:
return
clickable, iframe_key = random.choice( candidate_clickables )
self.crawler.action_events.append( {
'state' : state,
'action' : { 'clickable':clickable, 'iframe_key':iframe_key },
'depth' : depth,
} )
print(state.get_id(),clickable.get_id(), clickable.get_xpath())
def save_dom(self, state):
try:
#make dir for each state
state_dir = os.path.join( self.configuration.get_abs_path('dom'), state.get_id() )
if not os.path.isdir(state_dir):
os.makedirs(state_dir)
iframe_key_dict = { 'num': 0 }
for stateDom in state.get_dom_list(self.configuration):
iframe_key = ';'.join(stateDom['iframe_path']) if stateDom['iframe_path'] else None
#make new dir for iframe
if stateDom['iframe_path']:
iframe_key_dict['num'] += 1
iframe_key_dict[ str(iframe_key_dict['num']) ] = { 'path' : stateDom['iframe_path'], 'url': stateDom['url'] }
dom_dir = os.path.join( self.configuration.get_abs_path('dom'), state.get_id(), str(iframe_key_dict['num']) )
if not os.path.isdir(dom_dir):
os.makedirs(dom_dir)
else:
iframe_key_dict['basic'] = { 'url' : stateDom['url'] }
dom_dir = os.path.join( self.configuration.get_abs_path('dom'), state.get_id() )
with codecs.open( os.path.join( dom_dir, state.get_id()+'.txt'), 'w', encoding='utf-8' ) as f:
f.write( stateDom['dom'] )
with codecs.open( os.path.join( dom_dir, state.get_id()+'_nor.txt'), 'w', encoding='utf-8' ) as f:
f.write( DomAnalyzer.normalize( stateDom['dom'] ) )
with codecs.open( os.path.join( dom_dir, state.get_id()+'_inputs.txt'), 'w', encoding='utf-8' ) as f:
json.dump(state.get_inputs_json( iframe_key ), f, indent=2, sort_keys=True, ensure_ascii=False)
with codecs.open( os.path.join( dom_dir, state.get_id()+'_selects.txt'), 'w', encoding='utf-8' ) as f:
json.dump(state.get_selects_json(iframe_key ), f, indent=2, sort_keys=True, ensure_ascii=False)
with codecs.open( os.path.join( dom_dir, state.get_id()+'_radios.txt'), 'w', encoding='utf-8' ) as f:
json.dump(state.get_radios_json(iframe_key ), f, indent=2, sort_keys=True, ensure_ascii=False)
with codecs.open( os.path.join( dom_dir, state.get_id()+'_checkboxes.txt'), 'w', encoding='utf-8' ) as f:
json.dump(state.get_checkboxes_json(iframe_key ), f, indent=2, sort_keys=True, ensure_ascii=False)
with codecs.open( os.path.join( dom_dir, state.get_id()+'_clicks.txt'), 'w', encoding='utf-8' ) as f:
json.dump(state.get_candidate_clickables_json( iframe_key ), f, indent=2, sort_keys=True, ensure_ascii=False)
with codecs.open( os.path.join( state_dir, 'iframe_list.json'), 'w', encoding='utf-8' ) as f:
json.dump( iframe_key_dict, f, indent=2, sort_keys=True, ensure_ascii=False)
"""
TODO: turn TempFile stateDom into FilePath stateDom
"""
state.clear_dom()
except Exception as e:
logging.error(' save dom : %s \t\t__from automata.py save_dom()', str(e))
def get_dom_of_iframe(self, configuration, dom_list, iframe_xpath_list, src):
dom = self.switch_iframe_and_get_source(iframe_xpath_list)
soup = BeautifulSoup(dom, 'html5lib')
for frame in configuration.get_frame_tags():
for iframe_tag in soup.find_all(frame):
iframe_xpath = DomAnalyzer._get_xpath(iframe_tag)
iframe_xpath_list.append(iframe_xpath)
iframe_src = iframe_tag['src'] if iframe_tag.has_attr('src') else None
try:
self.get_dom_of_iframe(configuration, dom_list, iframe_xpath_list, iframe_src)
iframe_tag.clear()
except Exception as e:
logging.error(' get_dom_of_iframe: %s \t\t__from crawler.py get_dom_list() ', str(e))
dom_list.append( {
'url' : src,
'dom' : str(soup),
'iframe_path' : iframe_xpath_list,
} )
def set_simple_clickable_tags(self):
self._analyzer['simple_clickable_tags'] = True
DomAnalyzer.set_simple_clickable_tags()
def set_tag_with_attribute_normalizer(self, tag_name, attr=None, value=None, mode=None):
self._analyzer['tag_with_attribute_normalizers'].append({'tag':tag_name, 'attr':attr, 'value':value, 'mode':mode})
DomAnalyzer.add_tag_with_attribute_normalizer(tag_name, attr, value, mode)
def set_attributes_normalizer(self, attrs):
self._analyzer['attributes_normalizer'] += attrs
DomAnalyzer.add_attributes_normalizer(attrs)
def set_tags_normalizer(self, tags):
self._analyzer['tag_normalizers'] += tags
DomAnalyzer.add_tags_normalizer(tags)
def set_tags_normalizer(self, tags):
self._analyzer['tag_normalizers'] += tags
DomAnalyzer.add_tags_normalizer(tags)
def add_remove_clickable_tags(self):
return
dom = '''
<html><body>
<form data-prop="formNode" class="sup-form sup-account-form">
<p>
<input placeholder="Your name" data-prop="nameNode" data-event="input:onInfoInput" class="sup-info-name" data-l10n-id="setup-info-name" x-inputmode="verbatim" inputmode="verbatim" dir="auto" required="" type="text">
<button type="reset">reset1</button>
</p>
<p>
<input placeholder="*****@*****.**" data-prop="emailNode" data-event="input:onInfoInput" class="sup-info-email" data-l10n-id="setup-info-email" dir="auto" required="" type="email">
<button type="reset">reset2</button>
</p>
<p>
<button data-prop="nextButton" data-event="click:onNext" class="sup-info-next-btn recommend" disabled="">
<span data-l10n-id="setup-info-next">Next</span>
</button>
<button data-prop="manualConfig" data-event="click:onClickManualConfig" class="sup-manual-config-btn" disabled="" data-l10n-id="setup-manual-config2">Manual setup</button>
</p>
</form>
</body></html>
'''
# Tag('a'), Tag('button'), Tag('input', {'type': 'submit'}), Tag('input', {'type': 'button'})
self.assertEqual(len(DomAnalyzer.get_clickable_tags()), 4)
DomAnalyzer.remove_clickable_tags(Tag('a'))
DomAnalyzer.remove_clickable_tags(Tag('button'))
DomAnalyzer.remove_clickable_tags(Tag('button'))
DomAnalyzer.remove_clickable_tags(Tag('input', {'type': 'submit'}))
DomAnalyzer.remove_clickable_tags(Tag('input', {'type': 'button'}))
self.assertEqual(len(DomAnalyzer.get_clickable_tags()), 0)
DomAnalyzer.add_clickable_tags(Tag('button', {'type': 'reset'}))
self.assertEqual(len(DomAnalyzer.get_clickables(dom)), 2)
def set_simple_inputs_tags(self):
self._analyzer['simple_inputs_tags'] = True
DomAnalyzer.set_simple_inputs_tags()
def set_simple_inputs_tags(self):
self._analyzer['simple_inputs_tags'] = True
DomAnalyzer.set_simple_inputs_tags()
def set_simple_normalizers(self):
self._analyzer['simple_normalizers'] = True
DomAnalyzer.set_simple_normalizers()
def crawl(self, depth, prev_state=None):
if depth <= self.configuration.get_max_depth():
cs = self.automata.get_current_state()
if not self.violate_invariant(cs.get_dom(), cs.get_id()):
candidate_clickables = DomAnalyzer.get_clickables(
cs.get_dom(),
prev_state.get_dom() if prev_state else None)
self.num_clickables['unexamined'] += len(candidate_clickables)
for clickable in candidate_clickables:
# prefetch image of the clickable
time.sleep(0.2) # time for correctly fetching image
img_name = cs.get_id() + '-' + clickable.get_id() + '.png'
img_data = self.executor.get_screenshot(clickable)
# fire the clickable
logger.debug('Fire event in state %s', cs.get_id())
self.executor.empty_form(clickable)
self.executor.fill_form(clickable)
ft = FireEventThread(self.executor, clickable)
ft.start()
ft.join(self.configuration.get_sleep_time() *
2) # time out after sleep_time*2 seconds
if ft.is_alive(): # timed out
logger.error(
'No response while firing an event. Execution sequences:'
)
self.exe_stack.append(
clickable
) # add the clickable triggering No Response
for c in self.exe_stack:
logger.error(c)
logger.error(
'Total clickables found: %d (true: %d, false: %d, unexamined: %d)',
self.num_clickables['unexamined'] +
self.num_clickables['true'] +
self.num_clickables['false'],
self.num_clickables['true'],
self.num_clickables['false'],
self.num_clickables['unexamined'])
logger.error('Program terminated.')
sys.exit()
time.sleep(self.configuration.get_sleep_time())
self.num_clickables['unexamined'] -= 1
new_dom = self.executor.get_source()
if DomAnalyzer.is_equal(cs.get_dom(), new_dom):
self.num_clickables['false'] += 1
else:
self.num_clickables['true'] += 1
cs.add_clickable(clickable)
self.exe_stack.append(clickable)
self.save_screenshot(img_name, img_data, 'clickable')
ns, is_newly_added = self.automata.add_state(
State(new_dom))
self.automata.add_edge(cs, ns, clickable)
if is_newly_added:
self.save_screenshot(
ns.get_id() + '.png',
self.executor.get_screenshot(), 'state')
self.save_dom(ns)
self.automata.change_state(ns)
self.crawl(depth + 1, cs)
self.exe_stack.pop(-1)
self.automata.change_state(cs)
self.backtrack(cs)
def set_inputs_tag(self, input_type):
self._analyzer['inputs_tags'].append(input_type)
DomAnalyzer.add_inputs_tag(input_type)
def set_clickable_tag(self, tag_name, attr=None, value=None):
self._analyzer['clickable_tags'].append({'tag':tag_name, 'attr':attr, 'value':value})
DomAnalyzer.add_clickable_tag(tag_name, attr, value)
def set_attributes_normalizer(self, attrs):
self._analyzer['attributes_normalizer'] += attrs
DomAnalyzer.add_attributes_normalizer(attrs)
def set_inputs_tag(self, input_type):
self._analyzer['inputs_tags'].append(input_type)
DomAnalyzer.add_inputs_tag(input_type)
def set_simple_clickable_tags(self):
self._analyzer['simple_clickable_tags'] = True
DomAnalyzer.set_simple_clickable_tags()
def is_normalize_equal(self, list_dom, new_dom):
return DomAnalyzer.is_normalize_equal(list_dom, new_dom)
def set_simple_normalizers(self):
self._analyzer['simple_normalizers'] = True
DomAnalyzer.set_simple_normalizers()
def save_dom(self, state):
try:
#make dir for each state
state_dir = os.path.join(self.configuration.get_abs_path('dom'),
state.get_id())
if not os.path.isdir(state_dir):
os.makedirs(state_dir)
iframe_key_dict = {'num': 0}
for stateDom in state.get_dom_list(self.configuration):
iframe_key = ';'.join(stateDom['iframe_path']
) if stateDom['iframe_path'] else None
#make new dir for iframe
if stateDom['iframe_path']:
iframe_key_dict['num'] += 1
iframe_key_dict[str(iframe_key_dict['num'])] = {
'path': stateDom['iframe_path'],
'url': stateDom['url']
}
dom_dir = os.path.join(
self.configuration.get_abs_path('dom'), state.get_id(),
str(iframe_key_dict['num']))
if not os.path.isdir(dom_dir):
os.makedirs(dom_dir)
else:
iframe_key_dict['basic'] = {'url': stateDom['url']}
dom_dir = os.path.join(
self.configuration.get_abs_path('dom'), state.get_id())
with codecs.open(os.path.join(dom_dir,
state.get_id() + '.txt'),
'w',
encoding='utf-8') as f:
f.write(stateDom['dom'])
with codecs.open(os.path.join(dom_dir,
state.get_id() + '_nor.txt'),
'w',
encoding='utf-8') as f:
f.write(DomAnalyzer.normalize(stateDom['dom']))
with codecs.open(os.path.join(dom_dir,
state.get_id() + '_inputs.txt'),
'w',
encoding='utf-8') as f:
json.dump(state.get_inputs_json(iframe_key),
f,
indent=2,
sort_keys=True,
ensure_ascii=False)
with codecs.open(os.path.join(dom_dir,
state.get_id() + '_selects.txt'),
'w',
encoding='utf-8') as f:
json.dump(state.get_selects_json(iframe_key),
f,
indent=2,
sort_keys=True,
ensure_ascii=False)
with codecs.open(os.path.join(dom_dir,
state.get_id() + '_radios.txt'),
'w',
encoding='utf-8') as f:
json.dump(state.get_radios_json(iframe_key),
f,
indent=2,
sort_keys=True,
ensure_ascii=False)
with codecs.open(os.path.join(
dom_dir,
state.get_id() + '_checkboxes.txt'),
'w',
encoding='utf-8') as f:
json.dump(state.get_checkboxes_json(iframe_key),
f,
indent=2,
sort_keys=True,
ensure_ascii=False)
with codecs.open(os.path.join(dom_dir,
state.get_id() + '_clicks.txt'),
'w',
encoding='utf-8') as f:
json.dump(state.get_candidate_clickables_json(iframe_key),
f,
indent=2,
sort_keys=True,
ensure_ascii=False)
with codecs.open(os.path.join(state_dir, 'iframe_list.json'),
'w',
encoding='utf-8') as f:
json.dump(iframe_key_dict,
f,
indent=2,
sort_keys=True,
ensure_ascii=False)
"""
TODO: turn TempFile stateDom into FilePath stateDom
"""
state.clear_dom()
except Exception as e:
logging.error(' save dom : %s \t\t__from automata.py save_dom()',
str(e))
