def __init__(self, *args, **kwargs):
BaseService.__init__(self, *args, **kwargs)
self.user_agent = (
'Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/39.0.2171.95 Safari/537.36 '
'Nintendu/64 (URLTeam {0})'
).format(VERSION)
def process_redirect(self, response):
status, link, encoding = BaseService.process_redirect(self, response)
if link.startswith('/') and link.endswith('/'):
url = self.params['url_template'].format(shortcode=self.current_shortcode) + '/'
response = self.fetch_url(url, 'head')
status, link, encoding = BaseService.process_redirect(self, response)
if link in ('https://myspace.com/404', 'http://myspace.com/404'):
return URLStatus.not_found, None, None
else:
return status, link, encoding
def process_unknown_code(self, response):
if response.status_code != 200:
return BaseService.process_unknown_code(self, response)
url = self.params['url_template'].format(shortcode=self.current_shortcode)
response = self.fetch_url(url, 'get')
if response.status_code != 200:
raise UnexpectedNoResult(
"Didn't get OK on second try. Got {0} for {1}"
.format(response.status_code, self.current_shortcode)
)
# Copied form tinyback. I don't think code will reach here anymore
match = re.search(
"<a class=\"btn ignore\" href=\"(.*?)\" title=",
html_unescape(response.text)
)
if not match:
raise UnexpectedNoResult(
"Didn't get match on second try for {0}"
.format(self.current_shortcode)
)
return (URLStatus.ok, match.group(1), response.encoding)
def process_unknown_code(self, response):
first_status_code = response.status_code
if first_status_code not in (200, 500):
return BaseService.process_unknown_code(self, response)
url = self.params["url_template"].format(shortcode=self.current_shortcode)
response = self.fetch_url(url, "get")
second_status_code = response.status_code
if second_status_code not in (200, 500):
raise UnhandledStatusCode(
"HTTP status changed from %s to %i on second request for %s"
% (first_status_code, second_status_code, self.current_shortcode)
)
pattern = '<p>You clicked on a snipped URL, which will take you to the following looong URL: </p> <div class="quote"><span class="quotet"></span><br/>(.*?)</div> <br />'
match = re.search(pattern, response.text)
if not match:
text = response.text.replace("<br />\n", "")
match = re.search(pattern, text)
if not match:
pattern = '<p>You clicked on a snipped URL, which will take you to the following looong URL: </p> <div class="quote"><span class="quotet"></span><br/>(.*?)</div> <br />'
match = re.search(pattern, response.text, re.DOTALL)
if not match:
raise UnexpectedNoResult("Could not find target URL on preview page for {0}".format(self.current_shortcode))
url = html_unescape(match.group(1))
url = url.replace("\n", "").replace("\r", "")
return URLStatus.ok, url, response.encoding
def process_redirect(self, response):
status, url, encoding = BaseService.process_redirect(self, response)
if url == 'http://yatuc.com':
return URLStatus.not_found, None, None
else:
return status, url, encoding
def process_redirect(self, response):
if response.status_code == 302:
if 'location' not in response.headers:
raise UnexpectedNoResult()
url = urlparse.urlparse(response.headers['location'])
if url.scheme != "http" or url.netloc != "bit.ly" or url.path != "/a/warning":
raise UnexpectedNoResult("Unexpected Location header after HTTP status 302")
if sys.version_info[0] == 2:
query = urlparse.parse_qs(url.query.encode('latin-1'))
else:
query = urlparse.parse_qs(url.query)
if not ("url" in query and len(query["url"]) == 1) or not ("hash" in query and len(query["hash"]) == 1):
raise UnexpectedNoResult("Unexpected Location header after HTTP status 302")
if query["hash"][0] != self.current_shortcode:
raise UnexpectedNoResult("Hash mismatch for HTTP status 302")
if sys.version_info[0] == 2:
unshortened_url = query["url"][0].decode('latin-1')
else:
unshortened_url = query["url"][0]
return (URLStatus.ok, unshortened_url, None)
else:
return BaseService.process_redirect(self, response)
def process_redirect_body(self, response):
try:
return BaseService.process_redirect_body(self, response)
except UnexpectedNoResult:
if b'Sajn\xc3\xa1lom, de a be\xc3\xadrt URL hib\xc3\xa1s!'.decode('utf8') in response.text:
return (URLStatus.not_found, None, None)
else:
raise
def process_redirect(self, response):
status, url, encoding = BaseService.process_redirect(self, response)
if url.startswith('http://totally.awe.sm/') and \
url.endswith(self.current_shortcode):
return URLStatus.not_found, None, None
else:
return status, url, encoding
def process_redirect(self, response):
status, url, encoding = BaseService.process_redirect(self, response)
if status == URLStatus.ok:
if url == 'http://www.godaddy.com/default.aspx?isc=xcowebgd':
return URLStatus.not_found, None, None
return status, url, encoding
def process_redirect_body(self, response):
try:
return BaseService.process_redirect_body(self, response)
except UnexpectedNoResult:
if b'Sajn\xc3\xa1lom, de a be\xc3\xadrt URL hib\xc3\xa1s!'.decode(
'utf8') in response.text:
return (URLStatus.not_found, None, None)
else:
raise
def process_redirect(self, response):
try:
url_status, link, encoding = BaseService.process_redirect(self, response)
except UnexpectedNoResult:
if "Location" not in response.headers:
return URLStatus.not_found, None, None
else:
raise
if link == "/site/getprivate?snip=" + self.current_shortcode:
return URLStatus.unavailable, None, None
else:
return url_status, link, encoding
def process_redirect(self, response):
try:
url_status, link, encoding = BaseService.process_redirect(
self, response)
except UnexpectedNoResult:
if 'Location' not in response.headers:
return URLStatus.not_found, None, None
else:
raise
if link == "/site/getprivate?snip=" + self.current_shortcode:
return URLStatus.unavailable, None, None
else:
return url_status, link, encoding
def process_redirect(self, response):
if response.status_code == 200:
return self._fetch_200(response)
else:
if 'Location' in response.headers and response.status_code == 301:
tiny = response.headers.get("X-tiny")
if tiny and tiny[:3] == "aff":
return self._preview(self.current_shortcode,
response.headers['Location'])
try:
return BaseService.process_redirect(self, response)
except UnexpectedNoResult:
return (URLStatus.unavailable, None, None)
def process_redirect(self, response):
if response.status_code == 200:
return self._fetch_200(response)
else:
if 'Location' in response.headers and response.status_code == 301:
tiny = response.headers.get("X-tiny")
if tiny and tiny[:3] == "aff":
return self._preview(
self.current_shortcode, response.headers['Location']
)
try:
return BaseService.process_redirect(self, response)
except UnexpectedNoResult:
return (URLStatus.unavailable, None, None)
def process_redirect_body(self, response):
try:
return BaseService.process_redirect_body(self, response)
except UnexpectedNoResult:
if 'cakeErr1-context' not in response.text:
raise
match = re.search(r'"Location: (.*)"</pre>', response.text,
re.DOTALL)
if not match:
raise
link = match.group(1)
# Python's urllib escapes too much. We'll escape the bare minimum
link = link.replace('\n', '%0A')
link = link.replace('\r', '%0D')
return (URLStatus.ok, link, response.encoding)
def process_redirect_body(self, response):
try:
return BaseService.process_redirect_body(self, response)
except UnexpectedNoResult:
if 'cakeErr1-context' not in response.text:
raise
match = re.search(
r'"Location: (.*)"</pre>', response.text, re.DOTALL
)
if not match:
raise
link = match.group(1)
# Python's urllib escapes too much. We'll escape the bare minimum
link = link.replace('\n', '%0A')
link = link.replace('\r', '%0D')
return (URLStatus.ok, link, response.encoding)
def process_unavailable(self, response):
if response.status_code != 410:
return BaseService.process_unavailable(self, response)
match = re.search(r'was forwarding to: <BR> <font color=red>(.*)</font>', response.text)
if not match:
if re.search(r'This shortURL address was REMOVED for SPAMMING', response.text):
return URLStatus.unavailable, None, None
if not match and 'REMOVED FOR SPAMMING' in response.text:
return URLStatus.unavailable, None, None
if not match:
raise UnexpectedNoResult(
"Could not find target URL on blocked page for {0}"
.format(self.current_shortcode))
url = html_unescape(match.group(1))
return URLStatus.ok, url, response.encoding
def process_unknown_code(self, response):
first_status_code = response.status_code
if first_status_code not in (200, 500):
return BaseService.process_unknown_code(self, response)
url = self.params['url_template'].format(
shortcode=self.current_shortcode)
response = self.fetch_url(url, 'get')
second_status_code = response.status_code
if second_status_code not in (200, 500):
raise UnhandledStatusCode(
"HTTP status changed from %s to %i on second request for %s" %
(first_status_code, second_status_code,
self.current_shortcode))
pattern = "<p>You clicked on a snipped URL, which will take you to the following looong URL: </p> <div class=\"quote\"><span class=\"quotet\"></span><br/>(.*?)</div> <br />"
match = re.search(pattern, response.text)
if not match:
text = response.text.replace("<br />\n", "")
match = re.search(pattern, text)
if not match:
pattern = "<p>You clicked on a snipped URL, which will take you to the following looong URL: </p> <div class=\"quote\"><span class=\"quotet\"></span><br/>(.*?)</div> <br />"
match = re.search(pattern, response.text, re.DOTALL)
if not match:
raise UnexpectedNoResult(
"Could not find target URL on preview page for {0}".format(
self.current_shortcode))
url = html_unescape(match.group(1))
url = url.replace('\n', '').replace('\r', '')
return URLStatus.ok, url, response.encoding
def scrape_one(self, sequence_number):
self._processing_phishing_page = False
return BaseService.scrape_one(self, sequence_number)
def scrape_one(self, sequence_number):
self._processing_phishing_page = False
return BaseService.scrape_one(self, sequence_number)
def __init__(self, *args, **kwargs):
BaseService.__init__(self, *args, **kwargs)
self._processing_phishing_page = False
def fetch_url(self, url):
return BaseService.fetch_url(self, url + '?passthru=1')
def __init__(self, *args, **kwargs):
BaseService.__init__(self, *args, **kwargs)
self.user_agent = ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/39.0.2171.95 Safari/537.36 '
'Nintendu/64 (URLTeam {0})').format(VERSION)
def __init__(self, *args, **kwargs):
BaseService.__init__(self, *args, **kwargs)
self._processing_phishing_page = False
def process_redirect_body(self, response):
if response.status_code == 301 and 'Location' not in response.headers:
return (URLStatus.not_found, None, None)
return BaseService.process_redirect_body(self, response)
def __init__(self, *args, **kwargs):
self.shortcode_width = kwargs.pop('shortcode_width', 4)
BaseService.__init__(self, *args, **kwargs)
def process_redirect(self, response):
try:
return BaseService.process_redirect(self, response)
except UnexpectedNoResult:
return (URLStatus.not_found, None, None)
