def http_response(self, request, response):
code, msg, hdrs = response.code, response.msg, response.info()
if code == 200 and hdrs.has_key("refresh"):
refresh = getheaders(hdrs, "refresh")[0]
ii = string.find(refresh, ";")
if ii != -1:
pause, newurl_spec = float(refresh[:ii]), refresh[ii+1:]
jj = string.find(newurl_spec, "=")
if jj != -1:
key, newurl = newurl_spec[:jj], newurl_spec[jj+1:]
if key.strip().lower() != "url":
debug("bad Refresh header: %r" % refresh)
return response
else:
pause, newurl = float(refresh), response.geturl()
if (self.max_time is None) or (pause <= self.max_time):
if pause > 1E-3 and self.honor_time:
time.sleep(pause)
hdrs["location"] = newurl
# hardcoded http is NOT a bug
response = self.parent.error(
"http", request, response,
"refresh", msg, hdrs)
return response
def http_response(self, request, response):
code, msg, hdrs = response.code, response.msg, response.info()
if code == 200 and hdrs.has_key("refresh"):
refresh = getheaders(hdrs, "refresh")[0]
ii = string.find(refresh, ";")
if ii != -1:
pause, newurl_spec = float(refresh[:ii]), refresh[ii + 1:]
jj = string.find(newurl_spec, "=")
if jj != -1:
key, newurl = newurl_spec[:jj], newurl_spec[jj + 1:]
if key.strip().lower() != "url":
debug("bad Refresh header: %r" % refresh)
return response
else:
pause, newurl = float(refresh), response.geturl()
if (self.max_time is None) or (pause <= self.max_time):
if pause > 1E-3 and self.honor_time:
time.sleep(pause)
hdrs["location"] = newurl
# hardcoded http is NOT a bug
response = self.parent.error("http", request, response,
"refresh", msg, hdrs)
return response
def http_error_302(self, req, fp, code, msg, headers):
# Some servers (incorrectly) return multiple Location headers
# (so probably same goes for URI). Use first header.
if headers.has_key('location'):
newurl = getheaders(headers, 'location')[0]
elif headers.has_key('uri'):
newurl = getheaders(headers, 'uri')[0]
else:
return
newurl = urlparse.urljoin(req.get_full_url(), newurl)
# XXX Probably want to forget about the state of the current
# request, although that might interact poorly with other
# handlers that also use handler-specific request attributes
new = self.redirect_request(newurl, req, fp, code, msg, headers)
if new is None:
return
# loop detection
# .redirect_dict has a key url if url was previously visited.
if hasattr(req, 'redirect_dict'):
visited = new.redirect_dict = req.redirect_dict
if (visited.get(newurl, 0) >= self.max_repeats or
len(visited) >= self.max_redirections):
raise HTTPError(req.get_full_url(), code,
self.inf_msg + msg, headers, fp)
else:
visited = new.redirect_dict = req.redirect_dict = {}
visited[newurl] = visited.get(newurl, 0) + 1
# Don't close the fp until we are sure that we won't use it
# with HTTPError.
fp.read()
fp.close()
return self.parent.open(new)
def http_error_302(self, req, fp, code, msg, headers):
# Some servers (incorrectly) return multiple Location headers
# (so probably same goes for URI). Use first header.
if headers.has_key('location'):
newurl = getheaders(headers, 'location')[0]
elif headers.has_key('uri'):
newurl = getheaders(headers, 'uri')[0]
else:
return
newurl = urlparse.urljoin(req.get_full_url(), newurl)
# XXX Probably want to forget about the state of the current
# request, although that might interact poorly with other
# handlers that also use handler-specific request attributes
new = self.redirect_request(newurl, req, fp, code, msg, headers)
if new is None:
return
# loop detection
# .redirect_dict has a key url if url was previously visited.
if hasattr(req, 'redirect_dict'):
visited = new.redirect_dict = req.redirect_dict
if (visited.get(newurl, 0) >= self.max_repeats
or len(visited) >= self.max_redirections):
raise HTTPError(req.get_full_url(), code,
self.inf_msg + msg, headers, fp)
else:
visited = new.redirect_dict = req.redirect_dict = {}
visited[newurl] = visited.get(newurl, 0) + 1
# Don't close the fp until we are sure that we won't use it
# with HTTPError.
fp.read()
fp.close()
return self.parent.open(new)
def http_response(self, request, response):
if not hasattr(response, "seek"):
response = response_seek_wrapper(response)
headers = response.info()
url = response.geturl()
ct_hdrs = getheaders(response.info(), "content-type")
if is_html(ct_hdrs, url, self._allow_xhtml):
try:
try:
html_headers = parse_head(response, self.head_parser_class())
finally:
response.seek(0)
except (HTMLParser.HTMLParseError,
sgmllib.SGMLParseError):
pass
else:
for hdr, val in html_headers:
# rfc822.Message interprets this as appending, not clobbering
headers[hdr] = val
return response
def http_response(self, request, response):
if not hasattr(response, "seek"):
response = response_seek_wrapper(response)
headers = response.info()
url = response.geturl()
ct_hdrs = getheaders(response.info(), "content-type")
if is_html(ct_hdrs, url, self._allow_xhtml):
try:
try:
html_headers = parse_head(response,
self.head_parser_class())
finally:
response.seek(0)
except (HTMLParser.HTMLParseError, sgmllib.SGMLParseError):
pass
else:
for hdr, val in html_headers:
# rfc822.Message interprets this as appending, not clobbering
headers[hdr] = val
return response
def http_response(self, request, response):
code, msg, hdrs = response.code, response.msg, response.info()
if code == 200 and hdrs.has_key("refresh"):
refresh = getheaders(hdrs, "refresh")[0]
i = string.find(refresh, ";")
if i != -1:
pause, newurl_spec = refresh[:i], refresh[i+1:]
i = string.find(newurl_spec, "=")
if i != -1:
pause = int(pause)
if (self.max_time is None) or (pause <= self.max_time):
if pause != 0 and self.honor_time:
time.sleep(pause)
newurl = newurl_spec[i+1:]
hdrs["location"] = newurl
# hardcoded http is NOT a bug
response = self.parent.error(
"http", request, response,
"refresh", msg, hdrs)
return response
def http_response(self, request, response):
code, msg, hdrs = response.code, response.msg, response.info()
if code == 200 and hdrs.has_key("refresh"):
refresh = getheaders(hdrs, "refresh")[0]
i = string.find(refresh, ";")
if i != -1:
pause, newurl_spec = refresh[:i], refresh[i + 1:]
i = string.find(newurl_spec, "=")
if i != -1:
pause = int(pause)
if (self.max_time is None) or (pause <= self.max_time):
if pause != 0 and self.honor_time:
time.sleep(pause)
newurl = newurl_spec[i + 1:]
hdrs["location"] = newurl
# hardcoded http is NOT a bug
response = self.parent.error(
"http", request, response, "refresh", msg,
hdrs)
return response