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
url = urlparse.urljoin(target, "/sitemap.xml")
try:
items = parseSitemap(url)
except SqlmapConnectionException, ex:
if "page not found" in getSafeExString(ex):
found = False
logger.warn(u"'sitemap.xml'未找到")
except:
pass
finally:
if found:
if items:
for item in items:
if re.search(r"(.*?)\?(.+)", item):
threadData.shared.value.add(item)
if conf.crawlDepth > 1:
threadData.shared.unprocessed.update(items)
logger.info("%s links found" % ("no" if not items else len(items)))
def crawl(target):
try:
visited = set()
threadData = getCurrentThreadData()
threadData.shared.value = OrderedSet()
threadData.shared.formsFound = False
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)
threadData.shared.deeper = set()
threadData.shared.unprocessed = set([target])
if kb.checkSitemap is None:
message = "do you want to check for the existence of "
message += "site's sitemap(.xml) [y/N] "
kb.checkSitemap = readInput(message, default='N', boolean=True)
if kb.checkSitemap:
found = True
items = None
url = _urllib.parse.urljoin(target, "/sitemap.xml")
try:
items = parseSitemap(url)
except SqlmapConnectionException as ex:
if "page not found" in getSafeExString(ex):
found = False
logger.warn("'sitemap.xml' not found")
except:
pass
finally:
if found:
if items:
for item in items:
if re.search(r"(.*?)\?(.+)", item):
threadData.shared.value.add(item)
if conf.crawlDepth > 1:
threadData.shared.unprocessed.update(items)
logger.info("%s links found" % ("no" if not items else len(items)))
if not conf.bulkFile:
infoMsg = "starting crawler for target URL '%s'" % target
logger.info(infoMsg)
for i in xrange(conf.crawlDepth):
threadData.shared.count = 0
threadData.shared.length = len(threadData.shared.unprocessed)
numThreads = min(conf.threads, len(threadData.shared.unprocessed))
if not conf.bulkFile:
logger.info("searching for links with depth %d" % (i + 1))
runThreads(numThreads, crawlThread, threadChoice=(i > 0))
clearConsoleLine(True)
if threadData.shared.deeper:
threadData.shared.unprocessed = set(threadData.shared.deeper)
else:
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:
if not (conf.forms and threadData.shared.formsFound):
warnMsg = "no usable links found (with GET parameters)"
if conf.forms:
warnMsg += " or forms"
logger.warn(warnMsg)
else:
for url in threadData.shared.value:
kb.targets.add((urldecode(url, kb.pageEncoding), None, None, None, None))
if kb.targets:
if kb.normalizeCrawlingChoice is None:
message = "do you want to normalize "
message += "crawling results [Y/n] "
kb.normalizeCrawlingChoice = readInput(message, default='Y', boolean=True)
if kb.normalizeCrawlingChoice:
seen = set()
results = OrderedSet()
for target in kb.targets:
if target[1] in (HTTPMETHOD.GET, None):
match = re.search(r"/[^/?]*\?.*\Z", target[0])
if match:
key = re.sub(r"=[^=&]*", "=", match.group(0)).strip('&')
if key not in seen:
results.add(target)
seen.add(key)
else:
results.add(target)
kb.targets = results
storeResultsToFile(kb.targets)
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])
if not conf.sitemapUrl:
message = "do you want to check for the existence of "
message += "site's sitemap(.xml) [y/N] "
if readInput(message, default='N', boolean=True):
found = True
items = None
url = urlparse.urljoin(target, "/sitemap.xml")
try:
items = parseSitemap(url)
except SqlmapConnectionException, ex:
if "page not found" in getSafeExString(ex):
found = False
logger.warn("'sitemap.xml' not found")
except:
pass
finally:
if found:
if items:
for item in items:
if re.search(r"(.*?)\?(.+)", item):
threadData.shared.value.add(item)
if conf.crawlDepth > 1:
threadData.shared.unprocessed.update(items)
logger.info("%s links found" % ("no" if not items else len(items)))
def crawl(target):
try:
visited = set()
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()
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 httplib.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, unicode):
try:
match = re.search(r"(?si)<html[^>]*>(.+)</html>",
content)
if match:
content = "<html>%s</html>" % match.group(1)
soup = BeautifulSoup(content)
tags = soup('a')
if not tags:
tags = re.finditer(
r'(?i)<a[^>]+href="(?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 = urlparse.urljoin(current, 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 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
except ValueError: # for non-valid links
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])
if not conf.sitemapUrl:
message = "do you want to check for the existence of "
message += "site's sitemap(.xml) [y/N] "
if readInput(message, default='N', boolean=True):
found = True
items = None
url = urlparse.urljoin(target, "/sitemap.xml")
try:
items = parseSitemap(url)
except SqlmapConnectionException as ex:
if "page not found" in getSafeExString(ex):
found = False
logger.warn("'sitemap.xml' not found")
except:
pass
finally:
if found:
if items:
for item in items:
if re.search(r"(.*?)\?(.+)", item):
threadData.shared.value.add(item)
if conf.crawlDepth > 1:
threadData.shared.unprocessed.update(items)
logger.info("%s links found" %
("no" if not items else len(items)))
infoMsg = "starting crawler"
if conf.bulkFile:
infoMsg += " for target URL '%s'" % target
logger.info(infoMsg)
for i in xrange(conf.crawlDepth):
threadData.shared.count = 0
threadData.shared.length = len(threadData.shared.unprocessed)
numThreads = min(conf.threads, len(threadData.shared.unprocessed))
if not conf.bulkFile:
logger.info("searching for links with depth %d" % (i + 1))
runThreads(numThreads, crawlThread, threadChoice=(i > 0))
clearConsoleLine(True)
if threadData.shared.deeper:
threadData.shared.unprocessed = set(threadData.shared.deeper)
else:
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(
(urldecode(url, kb.pageEncoding), None, None, None, None))
storeResultsToFile(kb.targets)
