sqlmapproject/sqlmap
1
1
Fork 0
mirror of https://github.com/sqlmapproject/sqlmap.git synced 2025-06-19 04:23:12 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix for an Issue #324 (crawling when HTML is not well-formed)

Browse Source
This commit is contained in:
Miroslav Stampar 2012-12-27 20:55:37 +01:00
parent 127b880577
commit cb91729913
1 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
lib/utils/crawler.py
View File

@ -64,10 +64,21 @@ class Crawler(object):
if isinstance(content, unicode): if isinstance(content, unicode):
try: try:
match = re.search(r"(?si)<html[^>]*>(.+)</html>", content)
if match:
content = "<html>%s</html>" % match.group(1)
soup = BeautifulSoup(content) soup = BeautifulSoup(content)
for tag in soup('a'): tags = soup('a')
if tag.get("href"):
url = urlparse.urljoin(conf.url, tag.get("href")) 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 # 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))) _ = reduce(lambda x, y: x == y, map(lambda x: urlparse.urlparse(x).netloc.split(':')[0], (url, conf.url)))