mirror of
https://github.com/sqlmapproject/sqlmap.git
synced 2025-12-07 05:01:30 +00:00
Patch for an Issue #169
This commit is contained in:
Miroslav Stampar
@@ -25,116 +25,110 @@ from lib.request.connect import Connect as Request
|
||||
from thirdparty.beautifulsoup.beautifulsoup import BeautifulSoup
|
||||
from thirdparty.oset.pyoset import oset
|
||||
|
||||
class Crawler(object):
|
||||
"""
|
||||
This class defines methods used to perform crawling (command
|
||||
line option '--crawl'
|
||||
"""
|
||||
def crawl(target):
|
||||
try:
|
||||
threadData = getCurrentThreadData()
|
||||
threadData.shared.value = oset()
|
||||
|
||||
def getTargetUrls(self):
|
||||
try:
|
||||
def crawlThread():
|
||||
threadData = getCurrentThreadData()
|
||||
threadData.shared.value = oset()
|
||||
|
||||
def crawlThread():
|
||||
threadData = getCurrentThreadData()
|
||||
|
||||
while kb.threadContinue:
|
||||
with kb.locks.limit:
|
||||
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:
|
||||
while kb.threadContinue:
|
||||
with kb.locks.limit:
|
||||
if threadData.shared.unprocessed:
|
||||
current = threadData.shared.unprocessed.pop()
|
||||
else:
|
||||
break
|
||||
|
||||
if isinstance(content, unicode):
|
||||
try:
|
||||
match = re.search(r"(?si)<html[^>]*>(.+)</html>", content)
|
||||
if match:
|
||||
content = "<html>%s</html>" % match.group(1)
|
||||
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)
|
||||
|
||||
soup = BeautifulSoup(content)
|
||||
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:
|
||||
url = urlparse.urljoin(conf.url, 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.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%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)
|
||||
|
||||
threadData.shared.deeper = set()
|
||||
threadData.shared.unprocessed = set([conf.url])
|
||||
|
||||
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
|
||||
threadData.shared.length = len(threadData.shared.unprocessed)
|
||||
numThreads = min(conf.threads, len(threadData.shared.unprocessed))
|
||||
logger.info("searching for links with depth %d" % (i + 1))
|
||||
runThreads(numThreads, crawlThread)
|
||||
clearConsoleLine(True)
|
||||
if threadData.shared.deeper:
|
||||
threadData.shared.unprocessed = set(threadData.shared.deeper)
|
||||
else:
|
||||
if not kb.threadContinue:
|
||||
break
|
||||
|
||||
except KeyboardInterrupt:
|
||||
warnMsg = "user aborted during crawling. sqlmap "
|
||||
warnMsg += "will use partial list"
|
||||
logger.warn(warnMsg)
|
||||
if isinstance(content, unicode):
|
||||
try:
|
||||
match = re.search(r"(?si)<html[^>]*>(.+)</html>", content)
|
||||
if match:
|
||||
content = "<html>%s</html>" % match.group(1)
|
||||
|
||||
finally:
|
||||
soup = BeautifulSoup(content)
|
||||
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:
|
||||
url = urlparse.urljoin(target, 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, target)))
|
||||
|
||||
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%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)
|
||||
|
||||
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
|
||||
threadData.shared.length = len(threadData.shared.unprocessed)
|
||||
numThreads = min(conf.threads, len(threadData.shared.unprocessed))
|
||||
logger.info("searching for links with depth %d" % (i + 1))
|
||||
runThreads(numThreads, crawlThread)
|
||||
clearConsoleLine(True)
|
||||
|
||||
if not threadData.shared.value:
|
||||
warnMsg = "no usable links found (with GET parameters)"
|
||||
logger.warn(warnMsg)
|
||||
if threadData.shared.deeper:
|
||||
threadData.shared.unprocessed = set(threadData.shared.deeper)
|
||||
else:
|
||||
for url in threadData.shared.value:
|
||||
kb.targets.add(( url, None, None, None ))
|
||||
break
|
||||
|
||||
except KeyboardInterrupt:
|
||||
warnMsg = "user aborted during crawling. sqlmap "
|
||||
warnMsg += "will use partial list"
|
||||
logger.warn(warnMsg)
|
||||
|
||||
finally:
|
||||
clearConsoleLine(True)
|
||||
|
||||
if not threadData.shared.value:
|
||||
warnMsg = "no usable links found (with GET parameters)"
|
||||
logger.warn(warnMsg)
|
||||
else:
|
||||
for url in threadData.shared.value:
|
||||
kb.targets.add((url, None, None, None))
|
||||
|
||||
Reference in New Issue
Block a user