def deepCrawl(crawled) :
tmp = []
for each in crawled :
crawl = Crawl(each['url'])
crawl.filter()
tmp.extend(crawl.get())
return tmp
def appCrawl(url):
crawl = Crawl(url)
crawl.filter()
crawled = []
crawled.extend(crawl.get())
crawled.extend(SubCrawl.deepCrawl(crawled))
crawled = SubCrawl.deleteOverlap(crawled)
crawled = SubCrawl.replaceAttack(crawled)
crawled = SubCrawl.getAttackable(crawled)
return crawled
def Run():
start_urls = Ctrip.StartURL()
my_crawl = Crawl(start_urls)
try:
my_crawl.Run()
price_pannel_list = my_crawl.price_pannel_list
for price_pannel in price_pannel_list:
SplunkLog.Save(price_pannel)
finally:
my_crawl.Finish()
def test(self):
session = Session()
crawl = Crawl()
crawl.begin()
session.add(crawl)
try:
session.commit()
except IntegrityError, e:
session.close()
Crawl.dropAndCreate(e.message)
self.fail(e.message)
def testGviz(self):
crawl = Crawl()
crawl.begin()
session = Session()
session.add(crawl)
session.commit()
record = Record()
record.setUrl("http://example.com/")
record.setCrawlId(crawl.crawlId)
record.setLastSeen(utcnow())
session = Session()
session.add(record)
try:
session.commit()
except IntegrityError, e:
session.close()
Record.dropAndCreateTable(e.message)
self.fail(e.message)
def start_simple(self):
# get the crawler
crawler = Crawl()
crawler.add_url(self.ask_for_link())
crawler.load_next_page()
links = crawler.crawl_next_page_for_links()
for link in links:
crawler.add_url(link)
pass
def main():
# start by asking for a link
toCrawl = []
crawled = []
toCrawl.append(getLinkToPage())
crawlercl = Crawl()
# print "got page " + pageLink
maxPagesSearched = 100
i = 0
# search this page for links
while len(toCrawl) > 0:
# get first entry of "toCrawl" list
crawl = toCrawl.pop()
# TODO
# ensure that this link is not contained in the "crawled" list
if crawl in crawled:
# continue with the next loop
continue
links = crawlercl.crawl_next_page_for_links(crawl)
# put into "crawled" list
crawled.append(crawl)
# add new found links to "toCrawl" list
for link in links:
# ensure that the link is not in the "crawled" list
if link not in crawled:
toCrawl.append(makeAbsoluteLink(link, crawl))
print makeAbsoluteLink(link, crawl)
# stop loop after .. iterations
i += 1
if i >= maxPagesSearched:
break
return 0
def testInsert2(self):
crawl = Crawl()
crawl.begin()
self.assertGreater(len(crawl.userName), 0, "no user name was given")
self.assertGreater(len(crawl.userDomain), 0, "no user domain was given")
crawl.end()
session = Session()
session.add(crawl)
session.commit()
debug("crawlId of inserted record is %s" % (crawl.crawlId))
session.close()
Crawl.dropTable()
def crawl(self):
self.url = input(">>> Enter url of website: ")
if not self.url:
self.url = "http://testphp.vulnweb.com"
if not self.url.startswith("http"):
self.url = "http://" + self.url
host = self.url.replace("http://", "").replace("https://", "").split("/")[0]
current_path = os.path.dirname(os.path.realpath(__file__))
self.output_dir = os.path.join(current_path, "output/" + host)
if os.path.exists(self.output_dir):
chose = input("Scan results are available at output/{}, continue? (Y/N | Default = Y)".format(host))
if chose.upper() == "N":
print("Stopping.....")
exit()
else:
shutil.rmtree(self.output_dir)
os.makedirs(self.output_dir)
crawl = Crawl(self.url)
return crawl
def dummy(cls, n_dummy):
n_before = cls.count()
session = Session()
record = None
for x in range(n_dummy):
crawl = Crawl.dummy()
from uuid import uuid1
record = Record()
record.crawlId = crawl.crawlId
record.uri = "http://example.com/"+uuid1().get_hex()
record.url = "http://exmaple.com/"+uuid1().get_hex()
from random import randint
record.size = randint()
record.lastSeen = utcnow()
record.lastModified = utcnow()
record.jsonString = {}
record.belongsTo = None
record.exhaustive = False
session.add(record)
session.commit()
n_after = cls.count()
assert n_before + n_dummy == n_after
assert isinstance(record, Record)
return record
sDB_User = _cf["StockAnalysis"]["DB_User"]
sDB_Pwd = _cf["StockAnalysis"]["DB_Pwd"]
sDB_Name = _cf["StockAnalysis"]["DB_Name"]
#endregion
log = Log.hyLog() #第一種函數宣告, 要用 instance (或是呼叫函數時第一個引數帶入物件)
start_date = datetime.date(2019, 11, 1) #.strftime("%Y%m%d")
end_date = datetime.date.today() #.strftime("%Y%m%d")
day = datetime.timedelta(days=1) #獲取昨天的日期
log.writeLog(apname=_APName,
text="要處理的時間 ({} ~ {})".format(start_date.strftime("%Y%m%d"),
end_date.strftime("%Y%m%d")))
# initial crawl object
craw = Crawl(sDownloadFilePath)
db = DB(_APName, sDB_Host, sDB_User, sDB_Pwd, sDB_Name)
sleep_sec = 5
lastprocmonth = 0
while start_date <= end_date:
try:
# 星期六,日不處理
if start_date.weekday() == 5 or start_date.weekday() == 6:
start_date = start_date + day
continue
#暫時的 code
procemonthdata = False
if start_date.month != lastprocmonth:
procemonthdata = True
lastprocmonth = start_date.month
def setUp(self):
try:
Crawl.dropTable()
except OperationalError,e:
debug(e.message)
