def main(script, seed_url, limit = -1): limit = int(limit) import crawler crawler.init(seed_url) crawler.run(limit)
def main():
"""
Tester entry point
"""
crawler = VulnerabilitiesCrawler('http://web/')
# Show the obtained information
print("\n \n >>>>>>>" + crawler.run())
def _click():
split_url = entry_url_entered.get().split('/')
is_url_valid = False
for w in split_url:
if w == 'question':
is_url_valid = True
continue
if (is_url_valid is True):
app_ctx.question_id = w
break
if not is_url_valid:
label_download_result['text'] = '网址有误，请重新输入。'
else:
label_download_result['text'] = '正在缓存...'
crawler.run(app_ctx)
label_download_result['text'] = '缓存完成'
def test_crawl_echo_server(self):
urls = [
f'http://{self.client.host}:{self.client.port}/{id_}'
for id_ in range(10)
]
results = crawler.run(urls=urls, limit=5, loop=self.loop)
self.assertSetEqual(set(results), set(map(str, range(10))))
def hello_world():
hotels_data = []
start_date = request.args.get('start_date', '').replace('-', "")
final_date = request.args.get('final_date', '').replace('-', "")
db_data = run(start_date, final_date, 0)
for hotel in db_data:
hotels_data.append(hotel.to_json())
return jsonify(hotels_data)
def run():
try:
optlist, args = getopt.getopt(sys.argv[1:], OPTIONS, LONG_OPTIONS)
except getopt.GetoptError as e:
print str(e)
sys.exit(2)
thread_num = 10
output_path = "pics"
capicity = -1
begin_url = "22mm.cc"
for option, value in optlist:
if option == "-h":
usage()
sys.exit()
elif option == "-n":
try:
thread_num = int(value)
except Exception as e:
print "command error"
usage()
sys.exit(2)
elif option == "-o":
output_path = value
elif option == "-l":
try:
capicity = int(value)
except Exception as e:
print "command error"
usage()
sys.exit(2)
# elif option == "-s":
# begin_url = value
try:
if not os.path.isdir(output_path):
os.makedirs(output_path)
except Exception as e:
print "invalid path"
sys.exit(2)
type, host = urllib.splittype(begin_url)
if not type:
begin_url = "http://" + begin_url
crawler.run(begin_url, capicity, output_path, thread_num)
def run():
try:
optlist, args = getopt.getopt(sys.argv[1:], OPTIONS, LONG_OPTIONS)
except getopt.GetoptError as e:
print str(e)
sys.exit(2)
thread_num = 10
output_path = "pics"
capicity = -1
begin_url = "22mm.cc"
for option, value in optlist:
if option == "-h":
usage()
sys.exit()
elif option == "-n":
try:
thread_num = int(value)
except Exception as e:
print "command error"
usage()
sys.exit(2)
elif option == "-o":
output_path = value
elif option == "-l":
try:
capicity = int(value)
except Exception as e:
print "command error"
usage()
sys.exit(2)
# elif option == "-s":
# begin_url = value
try:
if not os.path.isdir(output_path):
os.makedirs(output_path)
except Exception as e:
print "invalid path"
sys.exit(2)
type, host = urllib.splittype(begin_url)
if not type:
begin_url = "http://" + begin_url
crawler.run(begin_url, capicity, output_path, thread_num)
def crawl (): '' ' Suatu fungsi untuk menggunakan src / crawler.py ' '' vprint ( " Perayap dimulai " , " hijau " , " info " ) untuk situs di sitesFromReverse: vprint ( " Merangkak -> " + situs, " yellow " , " info " ) sites = crawler.run (situs) if type (situs) ! = daftar : vprint (situs, " red " , " err " ) terus
def post(request):
if request.method == "POST":
user_url = request.POST.get("user-code")
print("사용자 요청 URL : " + user_url)
timetable_list = crawler.run(user_url)
if timetable_list == None:
return render(request, 'error-url.html', {'user_url': user_url})
info_list = crawler.lecture_list(timetable_list)
# print(info_list)
this_monday = datetime.date(2019, 9, 2)
while this_monday < datetime.date(2019, 12, 31):
for i in timetable_list: #과목별
for j in i.dates: #날자별
d = this_monday + datetime.timedelta(days=int(j['day']))
hour, min = crawler.calc_time(int(j['start_time']))
s = datetime.time(hour, min, 0)
hour, min = crawler.calc_time(int(j['end_time']))
e = datetime.time(hour, min, 0)
start = datetime.datetime.combine(d, s)
end = datetime.datetime.combine(d, e)
Event(owner=request.user,
title=i.name,
place=i.place,
start=start,
end=end,
is_from_timetable=True).save()
this_monday += datetime.timedelta(days=7)
return render(request, 'check-info.html', {'info_list': info_list})
# form = PostForm(request.POST)
# if form.is_valid():
# lotto = form.save(commit = False)
# lotto.generate()
# return redirect('connect-everytime')
else:
return render(request, "error.html")
dft = False
bft = False
if formData.getvalue('startingSite'):
startingSite = formData.getvalue('startingSite')
else:
startingSite = None
if formData.getvalue('crawlLimit'):
crawlLimit = int(formData.getvalue('crawlLimit'))
else:
crawlLimit = 0
if formData.getvalue('kWord'):
kWord = formData.getvalue('kWord')
else:
kWord = None
return dft, bft, startingSite, crawlLimit, kWord
###############################################################################
# Main Function
###############################################################################
# Get the data from the user-submitted form and set the global variable values
formData = cgi.FieldStorage()
dft, bft, startingSite, crawlLimit, kWord = getFormData(formData)
# Output results
print "Content-Type: text/html;charset=utf-8\n"
print crawler.run(startingSite, bft, crawlLimit, kWord)
buffer_handler = BufferingLogHandler(capacity=500)
setup_logging(
log_folder_path=LOG_PATH,
log_level=LOG_LEVEL,
external_lib_log_level="WARNING",
rotate_logger_configuration=ROTATE_CONFIG,
extra_handlers=[buffer_handler])
logger = logging.getLogger('Max')
logger.debug("Deb")
logger.info('inf')
logger.warning('warn')
logger.error('errrrr')
logger.fatal('fat!')
print("buffer returned: ", list(map(str, buffer_handler.flush())))
exit()
import crawler
crawler.run()
print("%"*50)
logging.getLogger().handlers[2].flush()
setup_logging(log_folder_path=LOG_PATH, log_level=LOG_LEVEL, external_lib_log_level="WARNING",
rotate_logger_configuration=ROTATE_CONFIG)
import crawler
def analysis():
logger.info("I'm working..." + time.ctime())
run()
dft = False
bft = False
if formData.getvalue('startingSite'):
startingSite = formData.getvalue('startingSite')
else:
startingSite = None
if formData.getvalue('crawlLimit'):
crawlLimit = int(formData.getvalue('crawlLimit'))
else:
crawlLimit = 0
if formData.getvalue('kWord'):
kWord = formData.getvalue('kWord')
else:
kWord = None
return dft, bft, startingSite, crawlLimit, kWord
###############################################################################
# Main Function
###############################################################################
# Get the data from the user-submitted form and set the global variable values
formData = cgi.FieldStorage()
dft, bft, startingSite, crawlLimit, kWord = getFormData(formData)
# Testing code
print "Content-Type: text/html;charset=utf-8\n"
print crawler.run("https://www.talkingpointsmemo.com", dft, 5, None)
def runcrawler():
connect = psycopg2.connect(db_config)
crawler.run(connect)
connect.close()
def analysis():
logger.info("I'm working..." + time.ctime())
run()
import argparse
import crawler
import phones_parser
parser = argparse.ArgumentParser()
parser.add_argument('--tasks',
help='path to file with tasks list (one url per line)',
required=True)
parser.add_argument('-n',
help='number of simultaneously performed requests',
default=100)
args = parser.parse_args()
with open(args.tasks) as f:
urls = [url.strip() for url in f.readlines() if url.strip()]
pages = crawler.run(urls, limit=args.n)
phones = {phone for phone in phones_parser.parse(page for page in pages)}
for phone in phones:
print(phone)
