def test_encoding(self):
import mechanize
from StringIO import StringIO
import urllib
# always take first encoding, since that's the one from the real HTTP
# headers, rather than from HTTP-EQUIV
b = mechanize.Browser()
for s, ct in [
("", mechanize._html.DEFAULT_ENCODING),
("Foo: Bar\r\n\r\n", mechanize._html.DEFAULT_ENCODING),
("Content-Type: text/html; charset=UTF-8\r\n\r\n", "UTF-8"),
("Content-Type: text/html; charset=UTF-8\r\n"
"Content-Type: text/html; charset=KOI8-R\r\n\r\n", "UTF-8"),
]:
msg = mimetools.Message(StringIO(s))
r = urllib.addinfourl(StringIO(""), msg, "http://www.example.com/")
b.set_response(r)
self.assertEqual(b.encoding(), ct)
python类addinfourl()的实例源码
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(":", 1)
mediatype, data = data.split(",", 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(";base64"):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = "text/plain;charset=US-ASCII"
headers = email.message_from_string(
"Content-type: %s\nContent-length: %d\n" % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
def wsopen(self, url, post, **params):
noparam = params.pop('noparam',False)
if noparam:
params = {}
else:
if self.user is not None:
params['user'] = self.user
if self.password is not None:
params.pop('hmac', None)
HMAC=hmac.new(self.password)
for k,v in sorted(params.items()):
HMAC.update("%s=%s" % (k,v))
params.update({'hmac':HMAC.hexdigest()})
query = urllib.urlencode(params)
if post:
body = query
elif query:
url = "{}?{}".format(url, query)
if self.debug:
if post:
print("POST:\n{}\n{!r}\n".format(url, body), file=sys.stderr)
else:
print("GET:\n{}\n".format(url), file=sys.stderr)
class URLopener(urllib.FancyURLopener):
def http_error_default(self, url, fp, errcode, errmsg, headers):
return urllib.addinfourl(fp, headers, "http:" + url, errcode)
try:
urllib._urlopener = URLopener()
if post:
resp = urllib.urlopen(url, body)
else:
resp = urllib.urlopen(url)
except IOError as e:
raise WSError(url, msg=e)
if self.debug:
print("RESPONSE:\n{}\n{}".format(resp.getcode(), resp.info()), file=sys.stderr)
if resp.getcode() != 200:
raise WSError(url, resp.getcode(), resp.read())
return resp
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(':', 1)
mediatype, data = data.split(',', 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(';base64'):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = 'text/plain;charset=US-ASCII'
headers = email.message_from_string(
'Content-type: %s\nContent-length: %d\n' % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
def http_error_302(self, req, fp, code, msg, headers):
x = addinfourl(fp, headers, (req.get_full_url)())
(x.status) = code
(x.code) = code
return x
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(':', 1)
mediatype, data = data.split(',', 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(';base64'):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = 'text/plain;charset=US-ASCII'
headers = email.message_from_string(
'Content-type: %s\nContent-length: %d\n' % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(':', 1)
mediatype, data = data.split(',', 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(';base64'):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = 'text/plain;charset=US-ASCII'
headers = email.message_from_string(
'Content-type: %s\nContent-length: %d\n' % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
def http_error_206(self, req, fp, code, msg, hdrs):
# 206 Partial Content Response
r = urllib.addinfourl(fp, hdrs, req.get_full_url())
r.code = code
r.msg = msg
return r
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(':', 1)
mediatype, data = data.split(',', 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(';base64'):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = 'text/plain;charset=US-ASCII'
headers = email.message_from_string(
'Content-type: %s\nContent-length: %d\n' % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
def get_response(self):
"""Returns a copy of the current response."""
return urllib.addinfourl(StringIO(self.data), self._response.info(), self._response.geturl())
def _make_response(self, result, url):
data = "\r\n".join(["%s: %s" % (k, v) for k, v in result.header_items])
headers = httplib.HTTPMessage(StringIO(data))
response = urllib.addinfourl(StringIO(result.data), headers, url)
code, msg = result.status.split(None, 1)
response.code, response.msg = int(code), msg
return response
def http_error_default(self, req, fp, code, msg, headers):
if ((code / 100) == 3) and (code != 304):
return self.http_error_302(req, fp, code, msg, headers)
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
return infourl
def http_error_302(self, req, fp, code, msg, headers):
if headers.dict.has_key('location'):
infourl = urllib2.HTTPRedirectHandler.http_error_302(self, req, fp, code, msg, headers)
else:
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
if not hasattr(infourl, 'status'):
infourl.status = code
return infourl
def http_error_301(self, req, fp, code, msg, headers):
if headers.dict.has_key('location'):
infourl = urllib2.HTTPRedirectHandler.http_error_301(self, req, fp, code, msg, headers)
else:
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
if not hasattr(infourl, 'status'):
infourl.status = code
return infourl
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(':', 1)
mediatype, data = data.split(',', 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(';base64'):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = 'text/plain;charset=US-ASCII'
headers = email.message_from_string(
'Content-type: %s\nContent-length: %d\n' % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
plugintools.py 文件源码
项目：plugin.video.streamondemand-pureita
作者: orione7
项目源码
文件源码
阅读 29
收藏 0
点赞 0
评论 0
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
scrapertools_old.py 文件源码
项目：plugin.video.streamondemand-pureita
作者: orione7
项目源码
文件源码
阅读 24
收藏 0
点赞 0
评论 0
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
def http_error_302(self, req, fp, code, msg, headers):
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
infourl.code = code
return infourl
def http_error_302(self, req, fp, code, msg, headers):
print "Ignoring redirect"
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = status
infourl.code = code
return infourl
def http_error_default(self, req, fp, code, msg, headers):
if ((code / 100) == 3) and (code != 304):
return self.http_error_302(req, fp, code, msg, headers)
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
infourl.status = code
return infourl
def http_error_302(self, req, fp, code, msg, headers):
if headers.dict.has_key('location'):
infourl = urllib2.HTTPRedirectHandler.http_error_302(self, req, fp, code, msg, headers)
else:
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
if not hasattr(infourl, 'status'):
infourl.status = code
return infourl
def http_error_301(self, req, fp, code, msg, headers):
if headers.dict.has_key('location'):
infourl = urllib2.HTTPRedirectHandler.http_error_301(self, req, fp, code, msg, headers)
else:
infourl = urllib.addinfourl(fp, headers, req.get_full_url())
if not hasattr(infourl, 'status'):
infourl.status = code
return infourl
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(':', 1)
mediatype, data = data.split(',', 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(';base64'):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = 'text/plain;charset=US-ASCII'
headers = email.message_from_string(
'Content-type: %s\nContent-length: %d\n' % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
