def test_get_meta_refresh(self):
r1 = HtmlResponse("http://www.example.com", body="""
<html>
<head><title>Dummy</title><meta http-equiv="refresh" content="5;url=http://example.org/newpage" /></head>
<body>blahablsdfsal&</body>
</html>""")
r2 = HtmlResponse("http://www.example.com", body="""
<html>
<head><title>Dummy</title><noScript>
<meta http-equiv="refresh" content="5;url=http://example.org/newpage" /></head>
</noSCRIPT>
<body>blahablsdfsal&</body>
</html>""")
r3 = HtmlResponse("http://www.example.com", body="""
<noscript><meta http-equiv="REFRESH" content="0;url=http://www.example.com/newpage</noscript>
<script type="text/javascript">
if(!checkCookies()){
document.write('<meta http-equiv="REFRESH" content="0;url=http://www.example.com/newpage">');
}
</script>
""")
self.assertEqual(
get_meta_refresh(r1), (5.0, 'http://example.org/newpage'))
self.assertEqual(get_meta_refresh(r2), (None, None))
self.assertEqual(get_meta_refresh(r3), (None, None))
def test_get_meta_refresh(self):
r1 = HtmlResponse("http://www.example.com",
body=b"""
<html>
<head><title>Dummy</title><meta http-equiv="refresh" content="5;url=http://example.org/newpage" /></head>
<body>blahablsdfsal&</body>
</html>""")
r2 = HtmlResponse("http://www.example.com",
body=b"""
<html>
<head><title>Dummy</title><noScript>
<meta http-equiv="refresh" content="5;url=http://example.org/newpage" /></head>
</noSCRIPT>
<body>blahablsdfsal&</body>
</html>""")
r3 = HtmlResponse("http://www.example.com",
body=b"""
<noscript><meta http-equiv="REFRESH" content="0;url=http://www.example.com/newpage</noscript>
<script type="text/javascript">
if(!checkCookies()){
document.write('<meta http-equiv="REFRESH" content="0;url=http://www.example.com/newpage">');
}
</script>
""")
self.assertEqual(get_meta_refresh(r1),
(5.0, 'http://example.org/newpage'))
self.assertEqual(get_meta_refresh(r2), (None, None))
self.assertEqual(get_meta_refresh(r3), (None, None))
def process_response(self, request, response, spider):
url = response.url
if response.status in [301, 307]:
log.msg("trying to redirect us: %s" % url, level=log.INFO)
reason = 'redirect %d' % response.status
return self._retry(request, reason, spider) or response
interval, redirect_url = get_meta_refresh(response)
# handle meta redirect
if redirect_url:
log.msg("trying to redirect us: %s" % url, level=log.INFO)
reason = 'meta'
return self._retry(request, reason, spider) or response
hxs = HtmlXPathSelector(response)
# test for captcha page
captcha = hxs.select(
".//input[contains(@id, 'captchacharacters')]").extract()
if captcha:
log.msg("captcha page %s" % url, level=log.INFO)
reason = 'capcha'
return self._retry(request, reason, spider) or response
return response
def process_response(self, request, response, spider):
if 'dont_redirect' in request.meta:
return response
if request.method.upper() == 'HEAD':
if response.status in [301, 302, 303, 307] and 'Location' in response.headers:
redirected_url = urljoin(request.url, response.headers['location'])
redirected = request.replace(url=redirected_url)
return self._redirect(redirected, request, spider, response.status)
else:
return response
if response.status in [302, 303] and 'Location' in response.headers:
redirected_url = urljoin(request.url, response.headers['location'])
redirected = self._redirect_request_using_get(request, redirected_url)
return self._redirect(redirected, request, spider, response.status)
if response.status in [301, 307] and 'Location' in response.headers:
redirected_url = urljoin(request.url, response.headers['location'])
redirected = request.replace(url=redirected_url)
return self._redirect(redirected, request, spider, response.status)
if isinstance(response, HtmlResponse):
interval, url = get_meta_refresh(response)
if url and interval < self.max_metarefresh_delay:
redirected = self._redirect_request_using_get(request, url)
return self._redirect(redirected, request, spider, 'meta refresh')
return response
def process_response(self, request, response, spider):
if 'dont_redirect' in request.meta:
return response
if request.method.upper() == 'HEAD':
if response.status in [301, 302, 303, 307
] and 'Location' in response.headers:
redirected_url = urljoin(request.url,
response.headers['location'])
redirected = request.replace(url=redirected_url)
return self._redirect(redirected, request, spider,
response.status)
else:
return response
if response.status in [302, 303] and 'Location' in response.headers:
redirected_url = urljoin(request.url, response.headers['location'])
redirected = self._redirect_request_using_get(
request, redirected_url)
return self._redirect(redirected, request, spider, response.status)
if response.status in [301, 307] and 'Location' in response.headers:
redirected_url = urljoin(request.url, response.headers['location'])
redirected = request.replace(url=redirected_url)
return self._redirect(redirected, request, spider, response.status)
if isinstance(response, HtmlResponse):
interval, url = get_meta_refresh(response)
if url and interval < self.max_metarefresh_delay:
redirected = self._redirect_request_using_get(request, url)
return self._redirect(redirected, request, spider,
'meta refresh')
return response
def _check_redirect(self, request, response):
if request.method.upper() == 'HEAD':
if response.status in [301, 302, 303, 307] and 'Location' in response.headers:
redirected_url = urljoin_rfc(request.url, response.headers['location'])
redirected = request.replace(url=redirected_url)
return redirected,response.status
else:
return None,None
if response.status in [302, 303] and 'Location' in response.headers:
redirected_url = urljoin_rfc(request.url, response.headers['location'])
redirected = self._redirect_request_using_get(request, redirected_url)
return redirected,response.status
if response.status in [301, 307] and 'Location' in response.headers:
redirected_url = urljoin_rfc(request.url, response.headers['location'])
redirected = request.replace(url=redirected_url)
return redirected,response.status
if request.meta.get('meta_refresh',None) and \
isinstance(response, HtmlResponse):
interval, url = get_meta_refresh(response)
if url and interval < self.max_metarefresh_delay:
redirected = self._redirect_request_using_get(request, url)
return redirected,'meta refresh'
return None,None
def process_response(self, request, response, spider):
get_list = {}
obj = DmozSpider()
redirect_filename = 'output/' + obj.redirect_filename
from_url = request.url
to_url = ''
if response.status in [301,302,303, 307] and "Location" in response.headers:
to_url = response.headers["Location"]
get_list = self.extractgetList(from_url)
redirect_dict = {"from_url":from_url,"params":get_list,"to_url":to_url}
f = open(redirect_filename,'a')
json.dump(redirect_dict,f,indent = 2)
f.write(",")
f.close()
log.msg("trying to redirect : %s -> %s" %(from_url,to_url), level=log.INFO)
reason = 'redirect %d' %response.status
return self._retry(request, reason, spider) or response
interval, redirect_url = get_meta_refresh(response)
# handle meta redirect
if redirect_url:
get_list = self.extractgetList(to_url)
redirect_dict = {"from_url":from_url,"params":get_list,"to_url":to_url}
f = open(redirect_filename,'a')
json.dump(redirect_dict,f,indent = 2)
f.write(",")
f.close()
log.msg("trying to redirect : %s -> %s" %(from_url,to_url), level=log.INFO)
reason = 'meta'
return self._retry(request, reason, spider) or response
return response
def process_response(self, request, response, spider):
if request.meta.get("meta_refresh"):
# logger.debug("local meta redirect middlewares: {}".format(response.url))
_, location_url = get_meta_refresh(response)
if not location_url:
raise IgnoreRequest
for off_key in off_keys:
if off_key in location_url:
# ignore the page
raise IgnoreRequest
if location_url.startswith("http"):
reason = "local pan middlewares, meta redirected!!!"
request.meta["meta_refresh"] = False
request.headers.pop('Content-Type', None)
request.headers.pop("Referer", None)
request.headers.pop('Content-Length', None)
request.priority += 100
redirected = request.replace(url=location_url)
return self._redirect(redirected, request, spider,
reason) or response
return response
def _check_redirect(self, request, response):
if request.method.upper() == 'HEAD':
if response.status in [301, 302, 303, 307
] and 'Location' in response.headers:
redirected_url = urljoin_rfc(request.url,
response.headers['location'])
redirected = request.replace(url=redirected_url)
return redirected, response.status
else:
return None, None
if response.status in [302, 303] and 'Location' in response.headers:
redirected_url = urljoin_rfc(request.url,
response.headers['location'])
redirected = self._redirect_request_using_get(
request, redirected_url)
return redirected, response.status
if response.status in [301, 307] and 'Location' in response.headers:
redirected_url = urljoin_rfc(request.url,
response.headers['location'])
redirected = request.replace(url=redirected_url)
return redirected, response.status
if request.meta.get('meta_refresh',None) and \
isinstance(response, HtmlResponse):
interval, url = get_meta_refresh(response)
if url and interval < self.max_metarefresh_delay:
redirected = self._redirect_request_using_get(request, url)
return redirected, 'meta refresh'
return None, None
def process_response(self, request, response, spider):
url = response.url
response
with open('redirects.txt', 'a+') as f:
if response.status in [301, 307]:
f.write("trying to redirect us: " + url + '\n')
f.write('redirect %d' + str(response.status) + '\n')
reason = 'redirect %d' %response.status
return self._retry(request, reason, spider) or response
interval, redirect_url = get_meta_refresh(response)
# handle meta redirect
if redirect_url:
f.write("trying to redirect us: " + url + '\n')
f.write('redirect meta' + '\n')
reason = 'meta'
return self._retry(request, reason, spider) or response
hxs = HtmlXPathSelector(response)
# test for captcha page
captcha = hxs.select(".//input[contains(@id, 'captchacharacters')]").extract()
if captcha:
f.write("trying to redirect us: " + url + '\n')
f.write('redirect capcha' + '\n')
reason = 'capcha'
return self._retry(request, reason, spider) or response
return response
def process_response(self, request, response, spider):
url = response.url
if response.status in [301, 307]:
log.msg("trying to redirect us: %s" %url, level=log.INFO)
reason = 'redirect %d' %response.status
return self._retry(request, reason, spider) or response
interval, redirect_url = get_meta_refresh(response)
if response.status in [502, 503]:
log.msg("Service Unavailable: %s" %url, level=log.INFO)
reason = 'Possible block with 5xx error'
return self._retry(request, reason, spider) or response
# handle meta redirect
if redirect_url:
log.msg("trying to redirect us: %s" %url, level=log.INFO)
reason = 'meta'
return self._retry(request, reason, spider) or response
hxs = HtmlXPathSelector(response)
# test for captcha page
captcha = hxs.select(".//input[contains(@id, 'captchacharacters')]").extract()
if captcha or "Dostęp zablokowany" in response.text:
log.msg("captcha page %s" %url, level=log.INFO)
reason = 'captcha'
return self._retry(request, reason, spider) or response
if response.status in [502, 503, 504]:
log.msg("Captcha with status: \n%s" %response.text, level=log.INFO)
reason = 'captcha'
return self._retry(request, reason, spider) or response
return response
def process_response(self, request, response, spider):
if request.meta.get('dont_redirect', False) or request.method == 'HEAD' or \
not isinstance(response, HtmlResponse):
return response
interval, url = get_meta_refresh(response)
if url and interval < self._maxdelay:
redirected = self._redirect_request_using_get(request, url)
return self._redirect(redirected, request, spider, 'meta refresh')
return response
def process_response(self, request, response, spider):
if request.meta.get('dont_redirect', False) or request.method == 'HEAD' or \
not isinstance(response, HtmlResponse):
return response
interval, url = get_meta_refresh(response)
if url and interval < self._maxdelay:
redirected = self._redirect_request_using_get(request, url)
return self._redirect(redirected, request, spider, 'meta refresh')
return response
def process_response(self, request, response, spider):
if "dont_redirect" in request.meta or request.method == "HEAD" or not isinstance(response, HtmlResponse):
return response
if isinstance(response, HtmlResponse):
interval, url = get_meta_refresh(response)
if url and interval < self._maxdelay:
redirected = self._redirect_request_using_get(request, url)
return self._redirect(redirected, request, spider, "meta refresh")
return response
def process_response(self, request, response, spider):
url = response.url
if response.status in [301, 307]:
log.msg("trying to redirect us: %s" %url, level=log.INFO)
reason = 'redirect %d' %response.status
return self._retry(request, reason, spider) or response
interval, redirect_url = get_meta_refresh(response)
# handle meta redirect
if redirect_url:
log.msg("trying to redirect us: %s" %url, level=log.INFO)
reason = 'meta'
return self._retry(request, reason, spider) or response
def process_response(self, request, response, spider):
url = response.url
if response.status in [301, 307]:
log.msg("trying to redirect us: %s" % url, level=log.INFO)
reason = 'redirect %d' % response.status
return self._retry(request, reason, spider) or response
interval, redirect_url = get_meta_refresh(response)
# handle meta redirect
if redirect_url:
log.msg("trying to redirect us: %s" % url, level=log.INFO)
reason = 'meta'
return self._retry(request, reason, spider) or response
def process_response(self, request, response, spider):
if (request.meta.get("dont_redirect", False)
or request.method == "HEAD"
or not isinstance(response, HtmlResponse)):
return response
interval, url = get_meta_refresh(response,
ignore_tags=self._ignore_tags)
if url and interval < self._maxdelay:
redirected = self._redirect_request_using_get(request, url)
return self._redirect(redirected, request, spider, "meta refresh")
return response
def process_response(self, request, response, spider):
if 'dont_redirect' in request.meta or request.method == 'HEAD' or \
not isinstance(response, HtmlResponse):
return response
if isinstance(response, HtmlResponse):
interval, url = get_meta_refresh(response)
if url and interval < self._maxdelay:
redirected = self._redirect_request_using_get(request, url)
# print response.body
if (response.url.find("view") > 0):
self.print_conversation(response)
return self._redirect(redirected, request, spider, 'meta refresh')
return response
def process_response(self, request, response, spider):
if request.meta.get('dont_retry', False):
return response
if response.status in self.retry_http_codes:
reason = response_status_message(response.status)
return self._retry(request, reason, spider) or response
interval, redirect_url= get_meta_refresh(response)
if redirect_url:
print('redirect_url',redirect_url,'*******','response.url',response.url)
# this is your check
if response.status == 403 and response.url:
print('*********************response.url',response.url)
return self._retry(request, 'response got xpath "{}"'.format(response.url), spider) or response
return response
def process_response(self, request, response, spider):
request.meta['dont_filter'] = True
if 'dont_redirect' in request.meta or request.method == 'HEAD' or \
not isinstance(response, HtmlResponse) or request.meta.get('redirect_times') >= 1:
request.meta['dont_redirect'] = True
return response
if isinstance(response, HtmlResponse):
interval, url = get_meta_refresh(response)
if url and interval < self._maxdelay:
redirected = self._redirect_request_using_get(request, url)
redirected.dont_filter = True
return self._redirect(redirected, request, spider,
'meta refresh')
return response
def process_response(self, request, response, spider):
if response.status in [302, 303] and 'Location' in response.headers:
redirected_url = urljoin_rfc(request.url, response.headers['location'])
redirected = self._redirect_request_using_get(request, redirected_url)
return self._redirect(redirected, request, spider, response.status)
if response.status in [301, 307] and 'Location' in response.headers:
redirected_url = urljoin_rfc(request.url, response.headers['location'])
redirected = request.replace(url=redirected_url)
return self._redirect(redirected, request, spider, response.status)
interval, url = get_meta_refresh(response)
if url and interval < self.max_metarefresh_delay:
redirected = self._redirect_request_using_get(request, url)
return self._redirect(redirected, request, spider, 'meta refresh')
return response
def process_response(self, request, response, spider):
get_list = {}
obj = DmozSpider()
redirect_filename = 'output/' + obj.redirect_filename
from_url = request.url
to_url = ''
if response.status in [301, 302, 303, 307
] and "Location" in response.headers:
to_url = response.headers["Location"]
get_list = self.extractgetList(from_url)
redirect_dict = {
"from_url": from_url,
"params": get_list,
"to_url": to_url
}
f = open(redirect_filename, 'a')
json.dump(redirect_dict, f, indent=2)
f.write(",")
f.close()
log.msg("trying to redirect : %s -> %s" % (from_url, to_url),
level=log.INFO)
reason = 'redirect %d' % response.status
return self._retry(request, reason, spider) or response
interval, redirect_url = get_meta_refresh(response)
# handle meta redirect
if redirect_url:
get_list = self.extractgetList(to_url)
redirect_dict = {
"from_url": from_url,
"params": get_list,
"to_url": to_url
}
f = open(redirect_filename, 'a')
json.dump(redirect_dict, f, indent=2)
f.write(",")
f.close()
log.msg("trying to redirect : %s -> %s" % (from_url, to_url),
level=log.INFO)
reason = 'meta'
return self._retry(request, reason, spider) or response
return response
def process_response(self, request, response, spider):
url = response.url
if response.status in [301,302, 307]:
log.msg("trying to redirect us: %s" %url, level=log.INFO)
reason = 'redirect %d' %response.status
return self._retry(request, reason, spider) or response
interval, redirect_url = get_meta_refresh(response)
# handle meta redirect
if redirect_url:
log.msg("trying to redirect us: %s" %url, level=log.INFO)
reason = 'meta'
return self._retry(request, reason, spider) or response
print(response.url)
userblocked = "userblocked" in response.url
print(userblocked)
# test for captcha page
if userblocked:
log.msg("blocked page %s" %url, level=log.INFO)
reason = 'blocked'
return self._retry(request, reason, spider) or response
return response
def process_response(self, request, response, spider):
url = response.url
logging.debug( 'WangJun I am OK111' )
logging.debug( 'WangJun I am OK111 %d' %response.status )
print('Cookie',response)
if response.status in [301, 302]:
logging.info("WangJun trying to redirect us: %s" %url)
reason = 'redirect %d' %response.status
return self._retry(request, reason, spider) or response
interval, redirect_url = get_meta_refresh(response)
# handle meta redirect
if redirect_url:
logging.info("trying to redirect us: %s" %url)
reason = 'meta'
return self._retry(request, reason, spider) or response
hxs = Selector(response) #HtmlXPathSelector(response)
# test for captcha page
captcha = hxs.xpath(".//input[contains(@id, 'captchacharacters')]").extract()
if captcha:
logging.info("captcha page %s" %url)
reason = 'capcha'
return self._retry(request, reason, spider) or response
return response
def process_response(self, request, response, spider):
# 跳过成功抓取的页面
if response.status == 200:
return response
url = response.url
if response.status in [301, 307]:
# req = urllib2.Request(url='http://imgs.co/u/16/10/06/JmQo.jpg')
# opener = urllib2.build_opener()
# reponse = opener.open(req)
# return reponse
# interval, redirect_url = get_meta_refresh(response)
# log.msg('redirect response.body:%s' %
# response.body.extract(), level=log.INFO)
# url = request.meta['redirect_urls']
# url = 'https:' + url[5:]
# log.msg("response redirect_url: %s" % redirect_url, level=log.INFO)
# log.msg("request.headers: %s" % repr(request.headers))
# log.msg("request.body: %s" % repr(request.body))
# log.msg("response.headers: %s" % repr(response.headers))
# log.msg("response.request type: %s" %
# type(response.request), level=log.INFO)
# log.msg("response type: %s" %
# type(response), level=log.INFO)
# request.headers['Accept-Encoding'] = 'identity'
# request.headers['Host'] = 'imgs.co'
# request.headers['Connection'] = 'close'
# del request.headers['Accept-Language']
# del request.headers['Accept']
# # del request.headers['Cookie']
# request.meta['dont_merge_cookies'] = True
# """
#
# 'Accept-Language': ['en'],
# 'Accept-Encoding': ['identity'],
# 'Host': ['imgs.co'],
# 'Accept': ['text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'],
# 'User-Agent': ['Mozilla/5.0 (Windows NT 10.0; WOW64; rv:49.0) Gecko/20100101 Firefox/49.0'], 'Connection': ['close'], 'Referer': ['http://c2.1024mx.org/pw/htm_data/3/1611/470074.html'],
# 'Cookie': ['__cfduid=dc80e726a73461e3823f2a312eb2b34cd1478357543']
# """
# log.msg("trying to redirect us: %s" % url, level=log.INFO)
url = response.headers['Location']
logger.info("trying to redirect us: %s" % url)
reason = 'redirect %d' % response.status
# return response.request
return self._retry(request, reason, spider) or response
# else:
# return response
# get_meta_refresh方法导致 'Response' object has no attribute 'text'
# 下段暂时通过try进行包装处理
try:
# handle meta redirect
interval, redirect_url = get_meta_refresh(response)
if redirect_url:
# log.msg("trying to redirect us: %s" % url, level=log.INFO)
logger.info("trying to redirect us: %s" % url)
reason = 'meta'
return self._retry(request, reason, spider) or response
except Exception, e:
print 'str(Exception):\t', str(Exception)
print 'str(e):\t\t', str(e)
print 'repr(e):\t', repr(e)
print 'e.message:\t', e.message
print 'traceback.print_exc():'
traceback.print_exc()
print 'traceback.format_exc():\n%s' % traceback.format_exc()
def test_get_meta_refresh(self):
body = """
<html>
<head><title>Dummy</title><meta http-equiv="refresh" content="5;url=http://example.org/newpage" /></head>
<body>blahablsdfsal&</body>
</html>"""
response = TextResponse(url='http://example.org', body=body)
self.assertEqual(get_meta_refresh(response),
(5, 'http://example.org/newpage'))
# refresh without url should return (None, None)
body = """<meta http-equiv="refresh" content="5" />"""
response = TextResponse(url='http://example.org', body=body)
self.assertEqual(get_meta_refresh(response), (None, None))
body = """<meta http-equiv="refresh" content="5;
url=http://example.org/newpage" /></head>"""
response = TextResponse(url='http://example.org', body=body)
self.assertEqual(get_meta_refresh(response),
(5, 'http://example.org/newpage'))
# meta refresh in multiple lines
body = """<html><head>
<META
HTTP-EQUIV="Refresh"
CONTENT="1; URL=http://example.org/newpage">"""
response = TextResponse(url='http://example.org', body=body)
self.assertEqual(get_meta_refresh(response),
(1, 'http://example.org/newpage'))
# entities in the redirect url
body = """<meta http-equiv="refresh" content="3; url='http://www.example.com/other'">"""
response = TextResponse(url='http://example.com', body=body)
self.assertEqual(get_meta_refresh(response),
(3, 'http://www.example.com/other'))
# relative redirects
body = """<meta http-equiv="refresh" content="3; url=other.html">"""
response = TextResponse(url='http://example.com/page/this.html',
body=body)
self.assertEqual(get_meta_refresh(response),
(3, 'http://example.com/page/other.html'))
# non-standard encodings (utf-16)
body = """<meta http-equiv="refresh" content="3; url=http://example.com/redirect">"""
body = body.decode('ascii').encode('utf-16')
response = TextResponse(url='http://example.com',
body=body,
encoding='utf-16')
self.assertEqual(get_meta_refresh(response),
(3, 'http://example.com/redirect'))
# non-ascii chars in the url (utf8)
body = """<meta http-equiv="refresh" content="3; url=http://example.com/to\xc2\xa3">"""
response = TextResponse(url='http://example.com',
body=body,
encoding='utf-8')
self.assertEqual(get_meta_refresh(response),
(3, 'http://example.com/to%C2%A3'))
# non-ascii chars in the url (latin1)
body = """<meta http-equiv="refresh" content="3; url=http://example.com/to\xa3">"""
response = TextResponse(url='http://example.com',
body=body,
encoding='latin1')
self.assertEqual(get_meta_refresh(response),
(3, 'http://example.com/to%C2%A3'))
# responses without refresh tag should return None None
response = TextResponse(url='http://example.org')
self.assertEqual(get_meta_refresh(response), (None, None))
response = TextResponse(url='http://example.org')
self.assertEqual(get_meta_refresh(response), (None, None))
# html commented meta refresh header must not directed
body = """<!--<meta http-equiv="refresh" content="3; url=http://example.com/">-->"""
response = TextResponse(url='http://example.com', body=body)
self.assertEqual(get_meta_refresh(response), (None, None))
# html comments must not interfere with uncommented meta refresh header
body = """<!-- commented --><meta http-equiv="refresh" content="3; url=http://example.com/">-->"""
response = TextResponse(url='http://example.com', body=body)
self.assertEqual(get_meta_refresh(response),
(3, 'http://example.com/'))
# float refresh intervals
body = """<meta http-equiv="refresh" content=".1;URL=index.html" />"""
response = TextResponse(url='http://example.com', body=body)
self.assertEqual(get_meta_refresh(response),
(0.1, 'http://example.com/index.html'))
body = """<meta http-equiv="refresh" content="3.1;URL=index.html" />"""
response = TextResponse(url='http://example.com', body=body)
self.assertEqual(get_meta_refresh(response),
(3.1, 'http://example.com/index.html'))
def test_get_meta_refresh(self):
body = """
<html>
<head><title>Dummy</title><meta http-equiv="refresh" content="5;url=http://example.org/newpage" /></head>
<body>blahablsdfsal&</body>
</html>"""
response = TextResponse(url='http://example.org', body=body)
self.assertEqual(get_meta_refresh(response), (5, 'http://example.org/newpage'))
# refresh without url should return (None, None)
body = """<meta http-equiv="refresh" content="5" />"""
response = TextResponse(url='http://example.org', body=body)
self.assertEqual(get_meta_refresh(response), (None, None))
body = """<meta http-equiv="refresh" content="5;
url=http://example.org/newpage" /></head>"""
response = TextResponse(url='http://example.org', body=body)
self.assertEqual(get_meta_refresh(response), (5, 'http://example.org/newpage'))
# meta refresh in multiple lines
body = """<html><head>
<META
HTTP-EQUIV="Refresh"
CONTENT="1; URL=http://example.org/newpage">"""
response = TextResponse(url='http://example.org', body=body)
self.assertEqual(get_meta_refresh(response), (1, 'http://example.org/newpage'))
# entities in the redirect url
body = """<meta http-equiv="refresh" content="3; url='http://www.example.com/other'">"""
response = TextResponse(url='http://example.com', body=body)
self.assertEqual(get_meta_refresh(response), (3, 'http://www.example.com/other'))
# relative redirects
body = """<meta http-equiv="refresh" content="3; url=other.html">"""
response = TextResponse(url='http://example.com/page/this.html', body=body)
self.assertEqual(get_meta_refresh(response), (3, 'http://example.com/page/other.html'))
# non-standard encodings (utf-16)
body = """<meta http-equiv="refresh" content="3; url=http://example.com/redirect">"""
body = body.decode('ascii').encode('utf-16')
response = TextResponse(url='http://example.com', body=body, encoding='utf-16')
self.assertEqual(get_meta_refresh(response), (3, 'http://example.com/redirect'))
# non-ascii chars in the url (default encoding - utf8)
body = """<meta http-equiv="refresh" content="3; url=http://example.com/to\xc2\xa3">"""
response = TextResponse(url='http://example.com', body=body)
self.assertEqual(get_meta_refresh(response), (3, 'http://example.com/to%C2%A3'))
# non-ascii chars in the url (custom encoding - latin1)
body = """<meta http-equiv="refresh" content="3; url=http://example.com/to\xa3">"""
response = TextResponse(url='http://example.com', body=body, encoding='latin1')
self.assertEqual(get_meta_refresh(response), (3, 'http://example.com/to%C2%A3'))
# responses without refresh tag should return None None
response = TextResponse(url='http://example.org')
self.assertEqual(get_meta_refresh(response), (None, None))
response = TextResponse(url='http://example.org')
self.assertEqual(get_meta_refresh(response), (None, None))