def check(self, page):
if self.is_status_expected(page.status):
return True, None
else:
GLog.warning("Status code[%s] not expected for url: %s",
page.status, page.url)
return False, "Unexpected status code %s" % page.status
def check_bak(self, url, port=None):
#extract protocol and address from the url
if len(url.split(":")) > 1:
protocol = url.split(":")[0]
addr = url.split(":")[1].strip("/")
else:
protocol = "http"
addr = url
#extract host and path from the address
host = addr.split("/", 1)[0]
path = addr.split("/", 1)[1] if len(
addr.split("/", 1)) > 1 else ""
#send http request and get response
#因为有些url访问的时候path必须以"/"开始才能访问，有些必须不以"/"开始
#才可以访问，因此需要测试两个路径（以"/"开始和不以"/"开始）
#如果全部fail才标志为fail
#print url, path
status = get_status_code(protocol, host, port, path)
if status is None or not self.is_status_expected(status):
status = get_status_code(protocol, host, port, "/" + path)
if status is None or not self.is_status_expected(status):
GLog.warning("Status code[%s] not expected for url: %s",
status, url)
return 1
return 0
def check(self, url):
status = utils.get_status_code(url)
if not self.is_status_expected(status):
GLog.warning("Status code[%s] not expected for url: %s",
status, url)
return 1
return 0
def read_list_from_file(file_name):
if os.path.isfile(file_name):
with open(file_name, "r") as in_fd:
return [line.strip() for line in in_fd]
else:
GLog.warning("file[%s] not existed!", file_name)
return []
def check(self, url):
if self.whitelist is None and self.blacklist is None:
GLog.fatal("You should input whitelist or blacklist at least")
return 0
v1 = 0
if self.whitelist is not None:
v1 = self.check_by_whitelist(url)
v2 = 0
if self.blacklist is not None:
v2 = self.check_by_blacklist(url)
if v1 + v2 == 0:
return (0, '')
else:
return (1, self.err_msg)
def check(self, url):
content = utils.read_content(url)
parser = HTMLTagParser()
parser.feed(content)
unmatch_tags = parser.close()
for t in unmatch_tags:
GLog.warning(
"Broken %s tag[%s] in pos[%s,%s] in url: %s",
"start" if t.start else "end",
t.name,
t.pos[0],
t.pos[1],
url,
)
if len(unmatch_tags) != 0:
return 1
else:
return 0
def check_by_blacklist(self, url):
links = self.get_url_list(url)
#count represent fail number
count = 0
for link in links:
#获取url当中的host
host = self.get_host_from_url(link)
for domain in self.blacklist:
if host.endswith(domain):
count += 1
self.err_msg += 'Domain in blacklist [%s]\n' % link
GLog.warning("Domain in blacklist [%s], parent url:%s",
link, url)
break
#count==0 represent no wrong
if count == 0:
return 0
else:
return 1
def check_by_whitelist(self, url):
links = self.get_url_list(url)
#count represent fail number
count = 0
for link in links:
#获取url当中的host
host = self.get_host_from_url(link)
#flag=True represent domain is ok
flag = False
for domain in self.whitelist:
if host.endswith(domain):
flag = True
break
if not flag:
count += 1
self.err_msg += 'Domain not in whitelist [%s]\n' % link
GLog.warning("Domain not in whitelist [%s], parent url: %s",
link, url)
#count==0 represent no wrong
if count == 0:
return 0
else:
return 1
def check_url(self, url):
#使用所有的checker检查某个url
parent = url.parent if isinstance(url, URL) else None
url = url.url if isinstance(url, URL) else url
GLog.debug("Checking url: %s", url)
failed_checker = 0
for checker in self.checkers:
failed_checker += checker.check(url)
#如果所有checker检查返回0（正常），直接返回0
if failed_checker == 0:
return 0
#有checker检查失败了
if not self.is_white_url(url):
GLog.fatal("URL check failed: %s, parent url: %s", url, parent)
return 1
else:
GLog.warning("URL check failed: %s, parent url: %s", url, parent)
return 0
def check(self, page):
GLog.debug("Checking url: %s", page.url)
for checker in self.checkers:
r, msg = checker.check(page)
if not r:
self.result.append(Result(page, msg))
def run_cmd(cmd):
ret, output = commands.getstatusoutput(cmd)
if ret != 0:
GLog.warning("Run cmd[%s] failed! Error msg: %s", cmd, output)
return ret, output
