def _preview(self, code, affiliate_url):
response = self.fetch_url("https://tinyurl.com/preview.php?num=" +
code,
method='get')
if response.status_code != 200:
raise UnexpectedNoResult(
"Unexpected HTTP status %i on preview page %s" %
(response.status_code, response.url))
match = re.search(
"<a id=\"redirecturl\" href=\"(.*?)\">Proceed to this site.</a>",
response.text, re.DOTALL)
if not match:
raise UnexpectedNoResult("No redirect on preview page {0}".format(
response.url))
url = match.group(1)
if url == "":
return self._scrub_url(code, affiliate_url)
return (URLStatus.ok, html_parser.HTMLParser().unescape(url),
response.encoding)
def _parse_spam_blocklist(self, response):
match = re.search("<p>This TinyURL went to: (.*?)</p>", response.text,
re.DOTALL)
if not match:
raise UnexpectedNoResult(
"No redirect on \"spam redirect\" page on HTTP status 200 for {0}"
.format(response.url))
url = match.group(1)
return (URLStatus.ok, html_parser.HTMLParser().unescape(url),
response.encoding)
def parse_preview(self, response):
response.encoding = 'utf-8'
match = re.search(
"<b>Click the link</b> if you'd like to proceed to the destination shown: -<br /><a href=\"(.*)\" class=\"biglink\">",
response.text)
if not match:
raise errors.UnexpectedNoResult(
"Could not find target URL in 'Preview' page")
url = match.group(1)
return (URLStatus.ok, html_parser.HTMLParser().unescape(url),
response.encoding)
def _parse_tinyurl_redirect(self, response):
match = re.search(
"<p class=\"intro\">The URL you followed redirects back to a TinyURL and therefore we can't directly send you to the site\\. The URL it redirects to is (?:<script>.*?</script>)?<a href=\"(.*?)\">",
response.text, re.DOTALL)
if not match:
raise UnexpectedNoResult(
"No redirect on \"tinyurl redirect\" page on HTTP status 200 for {0}"
.format(response.url))
url = match.group(1)
return (URLStatus.ok, html_parser.HTMLParser().unescape(url),
response.encoding)
def parse_blocked(self, response):
response.encoding = 'utf-8'
match = re.search(
"<p>For reference and to help those fighting spam the original destination of this URL is given below \(we strongly recommend you don't visit it since it may damage your PC\): -<br />(.*)</p><h2>is\.gd</h2><p>is\.gd is a free service used to shorten long URLs\.",
response.text)
if not match:
raise errors.UnexpectedNoResult(
"Could not find target URL in 'Link Disabled' page")
url = match.group(1)
url = html_parser.HTMLParser().unescape(url)
if url == "":
return (URLStatus.unavailable, None, None)
return (URLStatus.ok, url, response.encoding)
)
def process_connection_error(self, exception):
ex_args = repr(exception.args)
if 'ProtocolError' in ex_args or 'Invalid IPv6 URL' in ex_args:
raise MalformedResponse(
'Malformed response: {0}'.format(ex_args))
else:
raise PleaseRetry('Connection error: {0}'.format(ex_args))
def check_anti_regex(self, response, result_url, encoding):
if not result_url or self.matches_anti_regex(result_url):
return self.process_no_redirect(response)
else:
return (URLStatus.ok, result_url, encoding)
def matches_anti_regex(self, result_url):
anti_regex = self.params.get('location_anti_regex')
return (anti_regex and re.search(anti_regex, result_url))
class DefaultService(BaseService):
pass
_html_parser_unescaper = html_parser.HTMLParser()
def html_unescape(text):
return _html_parser_unescaper.unescape(text)