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
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)
# 通过标记来判断我们是否在处理同一个目标主机
_ = 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: # 用于非HTML文件
pass
except ValueError: # 用于非有效链接
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)
