class Crawler(object):
"""
This class defines methods used to perform crawling (command
line option '--crawl'
"""
def getTargetUrls(self):
try:
threadData = getCurrentThreadData()
threadData.shared.outputs = oset()
def crawlThread():
threadData = getCurrentThreadData()
while kb.threadContinue:
with kb.locks.limits:
if threadData.shared.unprocessed:
current = threadData.shared.unprocessed.pop()
else:
break
content = None
try:
if current:
content = Request.getPage(url=current,
crawling=True,
raise404=False)[0]
except SqlmapConnectionException, e:
errMsg = "connection exception detected (%s). skipping " % e
errMsg += "url '%s'" % current
logger.critical(errMsg)
except httplib.InvalidURL, e:
errMsg = "invalid url detected (%s). skipping " % e
errMsg += "url '%s'" % current
logger.critical(errMsg)
if not kb.threadContinue:
break
if isinstance(content, unicode):
try:
soup = BeautifulSoup(content)
for tag in soup('a'):
if tag.get("href"):
url = urlparse.urljoin(
conf.url, tag.get("href"))
# flag to know if we are dealing with the same target host
_ = reduce(
lambda x, y: x == y,
map(
lambda x: urlparse.urlparse(
x).netloc.split(':')[0],
(url, conf.url)))
if conf.scope:
if not re.search(
conf.scope, url, re.I):
continue
elif not _:
continue
if url.split('.')[-1].lower(
) not in CRAWL_EXCLUDE_EXTENSIONS:
with kb.locks.outputs:
threadData.shared.deeper.add(url)
if re.search(r"(.*?)\?(.+)", url):
threadData.shared.outputs.add(
url)
except UnicodeEncodeError: # for non-HTML files
pass
finally:
if conf.forms:
findPageForms(content, current, False, True)
if conf.verbose in (1, 2):
threadData.shared.count += 1
status = '%d/%d links visited (%d%s)' % (
threadData.shared.count, threadData.shared.length,
round(100.0 * threadData.shared.count /
threadData.shared.length), '%')
dataToStdout(
"\r[%s] [INFO] %s" % (time.strftime("%X"), status),
True)
if conf.scope:
if not re.search(conf.scope, url, re.I):
continue
elif not _:
continue
if url.split('.')[-1].lower() not in CRAWL_EXCLUDE_EXTENSIONS:
with kb.locks.value:
threadData.shared.deeper.add(url)
if re.search(r"(.*?)\?(.+)", url):
threadData.shared.value.add(url)
except UnicodeEncodeError: # for non-HTML files
pass
finally:
if conf.forms:
findPageForms(content, current, False, True)
if conf.verbose in (1, 2):
threadData.shared.count += 1
status = '%d/%d links visited (%d%%)' % (threadData.shared.count, threadData.shared.length, round(100.0 * threadData.shared.count / threadData.shared.length))
dataToStdout("\r[%s] [INFO] %s" % (time.strftime("%X"), status), True)
threadData.shared.deeper = set()
threadData.shared.unprocessed = set([target])
logger.info("starting crawler")
for i in xrange(conf.crawlDepth):
if i > 0 and conf.threads == 1:
singleTimeWarnMessage("running in a single-thread mode. This could take a while.")
threadData.shared.count = 0
def crawlThread():
threadData = getCurrentThreadData()
while kb.threadContinue:
with kb.locks.limit:
if threadData.shared.unprocessed:
current = threadData.shared.unprocessed.pop()
if current in visited:
continue
elif conf.crawlExclude and re.search(conf.crawlExclude, current):
dbgMsg = "skipping '%s'" % current
logger.debug(dbgMsg)
continue
else:
visited.add(current)
else:
break
content = None
try:
if current:
content = Request.getPage(url=current, crawling=True, raise404=False)[0]
except SqlmapConnectionException as ex:
errMsg = "connection exception detected ('%s'). skipping " % getSafeExString(ex)
errMsg += "URL '%s'" % current
logger.critical(errMsg)
except SqlmapSyntaxException:
errMsg = "invalid URL detected. skipping '%s'" % current
logger.critical(errMsg)
except _http_client.InvalidURL as ex:
errMsg = "invalid URL detected ('%s'). skipping " % getSafeExString(ex)
errMsg += "URL '%s'" % current
logger.critical(errMsg)
if not kb.threadContinue:
break
if isinstance(content, six.text_type):
try:
match = re.search(r"(?si)<html[^>]*>(.+)</html>", content)
if match:
content = "<html>%s</html>" % match.group(1)
soup = BeautifulSoup(content)
tags = soup('a')
tags += re.finditer(r'(?i)\s(href|src)=["\'](?P<href>[^>"\']+)', content)
tags += re.finditer(r'(?i)window\.open\(["\'](?P<href>[^)"\']+)["\']', content)
for tag in tags:
href = tag.get("href") if hasattr(tag, "get") else tag.group("href")
if href:
if threadData.lastRedirectURL and threadData.lastRedirectURL[0] == threadData.lastRequestUID:
current = threadData.lastRedirectURL[1]
url = _urllib.parse.urljoin(current, htmlUnescape(href))
# flag to know if we are dealing with the same target host
_ = checkSameHost(url, target)
if conf.scope:
if not re.search(conf.scope, url, re.I):
continue
elif not _:
continue
if (extractRegexResult(r"\A[^?]+\.(?P<result>\w+)(\?|\Z)", url) or "").lower() not in CRAWL_EXCLUDE_EXTENSIONS:
with kb.locks.value:
threadData.shared.deeper.add(url)
if re.search(r"(.*?)\?(.+)", url) and not re.search(r"\?(v=)?\d+\Z", url) and not re.search(r"(?i)\.(js|css)(\?|\Z)", url):
threadData.shared.value.add(url)
except UnicodeEncodeError: # for non-HTML files
pass
except ValueError: # for non-valid links
pass
finally:
if conf.forms:
threadData.shared.formsFound |= len(findPageForms(content, current, False, True)) > 0
if conf.verbose in (1, 2):
threadData.shared.count += 1
status = '%d/%d links visited (%d%%)' % (threadData.shared.count, threadData.shared.length, round(100.0 * threadData.shared.count / threadData.shared.length))
dataToStdout("\r[%s] [INFO] %s" % (time.strftime("%X"), status), True)
continue
elif not _:
continue
if url.split('.')[-1].lower() not in CRAWL_EXCLUDE_EXTENSIONS:
with kb.locks.value:
threadData.shared.deeper.add(url)
if re.search(r"(.*?)\?(.+)", url):
threadData.shared.value.add(url)
except UnicodeEncodeError: # 用于非HTML文件
pass
except ValueError: # 用于非有效链接
pass
finally:
if conf.forms:
findPageForms(content, current, False, True)
if conf.verbose in (1, 2):
threadData.shared.count += 1
status = u'访问了%d/%d个链接(%d%%)' % (threadData.shared.count, threadData.shared.length, round(100.0 * threadData.shared.count / threadData.shared.length))
dataToStdout("\r[%s] [INFO] %s" % (time.strftime("%X"), status), True)
threadData.shared.deeper = set()
threadData.shared.unprocessed = set([target])
if not conf.sitemapUrl:
message = u"你想检查网站是否存在站点地图sitemap(.xml)文件吗? [y/N] "
if readInput(message, default='N', boolean=True):
found = True
items = None
# print traceback.print_exc()
return
if isinstance(content, unicode):
try:
match = re.search(r"(?si)<html[^>]*>(.+)</html>", content)
if match:
content = "<html>%s</html>" % match.group(1)
soup = BeautifulSoup(content, 'lxml')
tags = soup('a')
if not tags:
tags = re.finditer(r'(?si)<a[^>]+href="(?P<href>[^>"]+)"', content)
for tag in tags:
href = tag.get("href") if hasattr(tag, "get") else tag.group("href")
if href and 'javascript:' not in href:
href = urlparse.urljoin(conf.CRAWL_SITE, href)
if conf.CRAWL_SITE in href:
redisCon.lpush('tmpVisit', href)
# logger.log(CUSTOM_LOGGING.ERROR, href)
except Exception, ex: # for non-HTML files
logger.log(CUSTOM_LOGGING.ERROR, ex)
finally:
forms = findPageForms(content, url, False)
for form in forms:
formMsg = '%s has form, url: %s method: %s data: %s' % (url, form[0], form[1], form[2])
logger.log(CUSTOM_LOGGING.WARNING, formMsg)
