How to use the extruct.rdflibxml.extras.httpheader.content_type function in extruct

To help you get started, we’ve selected a few extruct examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github scrapinghub / extruct / extruct / rdflibxml / extras / httpheader.py View on Github external
always be processed, but be at a lower priority than a complete
    matching type.

    See also: RFC 2616 section 14.1, and
    

    """
    if _is_string(accept_header):
        accept_list = parse_accept_header(accept_header)
    else:
        accept_list = accept_header

    if _is_string(content_types):
        content_types = [content_types]

    server_ctlist = [content_type(ct) for ct in content_types]
    del ct

    #print 'AC', repr(accept_list)
    #print 'SV', repr(server_ctlist)

    best = None   # (content_type, qvalue, accept_parms, matchlen)

    for server_ct in server_ctlist:
        best_for_this = None
        for client_ct, qvalue, aargs in accept_list:
            if ignore_wildcard and client_ct.is_universal_wildcard():
                continue  # */* being ignored

            matchlen = 0 # how specifically this one matches (0 is a non-match)
            if client_ct.is_universal_wildcard():
                matchlen = 1   # */* is a 1
github scrapinghub / extruct / extruct / rdflibxml / extras / httpheader.py View on Github external
def parse_mt_only(s, start):
        mt, k = parse_media_type(s, start, with_parameters=False)
        ct = content_type()
        ct.major = mt[0]
        ct.minor = mt[1]
        return ct, k
github scrapinghub / extruct / extruct / rdflibxml / extras / httpheader.py View on Github external
"""
        return self.major == 'multipart' or self.major == 'message'

    def is_xml(self):
        """Returns True if this media type is XML-based.

        Note this does not consider text/html to be XML, but
        application/xhtml+xml is.
        """
        return self.minor == 'xml' or self.minor.endswith('+xml')

# Some common media types
content_formdata = content_type('multipart/form-data')
content_urlencoded = content_type('application/x-www-form-urlencoded')
content_byteranges = content_type('multipart/byteranges') # RFC 2616 sect 14.16
content_opaque = content_type('application/octet-stream')
content_html = content_type('text/html')
content_xhtml = content_type('application/xhtml+xml')


def acceptable_content_type( accept_header, content_types, ignore_wildcard=True ):
    """Determines if the given content type is acceptable to the user agent.

    The accept_header should be the value present in the HTTP
    "Accept:" header.  In mod_python this is typically obtained from
    the req.http_headers_in table; in WSGI it is environ["Accept"];
    other web frameworks may provide other methods of obtaining it.

    Optionally the accept_header parameter can be pre-parsed, as
    returned from the parse_accept_header() function in this module.

    The content_types argument should either be a single MIME media
github scrapinghub / extruct / extruct / rdflibxml / extras / httpheader.py View on Github external
def is_composite(self):
        """Is this media type composed of multiple parts.
        """
        return self.major == 'multipart' or self.major == 'message'

    def is_xml(self):
        """Returns True if this media type is XML-based.

        Note this does not consider text/html to be XML, but
        application/xhtml+xml is.
        """
        return self.minor == 'xml' or self.minor.endswith('+xml')

# Some common media types
content_formdata = content_type('multipart/form-data')
content_urlencoded = content_type('application/x-www-form-urlencoded')
content_byteranges = content_type('multipart/byteranges') # RFC 2616 sect 14.16
content_opaque = content_type('application/octet-stream')
content_html = content_type('text/html')
content_xhtml = content_type('application/xhtml+xml')


def acceptable_content_type( accept_header, content_types, ignore_wildcard=True ):
    """Determines if the given content type is acceptable to the user agent.

    The accept_header should be the value present in the HTTP
    "Accept:" header.  In mod_python this is typically obtained from
    the req.http_headers_in table; in WSGI it is environ["Accept"];
    other web frameworks may provide other methods of obtaining it.

    Optionally the accept_header parameter can be pre-parsed, as
    returned from the parse_accept_header() function in this module.
github scrapinghub / extruct / extruct / rdflibxml / extras / httpheader.py View on Github external
def is_composite(self):
        """Is this media type composed of multiple parts.
        """
        return self.major == 'multipart' or self.major == 'message'

    def is_xml(self):
        """Returns True if this media type is XML-based.

        Note this does not consider text/html to be XML, but
        application/xhtml+xml is.
        """
        return self.minor == 'xml' or self.minor.endswith('+xml')

# Some common media types
content_formdata = content_type('multipart/form-data')
content_urlencoded = content_type('application/x-www-form-urlencoded')
content_byteranges = content_type('multipart/byteranges') # RFC 2616 sect 14.16
content_opaque = content_type('application/octet-stream')
content_html = content_type('text/html')
content_xhtml = content_type('application/xhtml+xml')


def acceptable_content_type( accept_header, content_types, ignore_wildcard=True ):
    """Determines if the given content type is acceptable to the user agent.

    The accept_header should be the value present in the HTTP
    "Accept:" header.  In mod_python this is typically obtained from
    the req.http_headers_in table; in WSGI it is environ["Accept"];
    other web frameworks may provide other methods of obtaining it.

    Optionally the accept_header parameter can be pre-parsed, as
github scrapinghub / extruct / extruct / rdflibxml / extras / httpheader.py View on Github external
def is_xml(self):
        """Returns True if this media type is XML-based.

        Note this does not consider text/html to be XML, but
        application/xhtml+xml is.
        """
        return self.minor == 'xml' or self.minor.endswith('+xml')

# Some common media types
content_formdata = content_type('multipart/form-data')
content_urlencoded = content_type('application/x-www-form-urlencoded')
content_byteranges = content_type('multipart/byteranges') # RFC 2616 sect 14.16
content_opaque = content_type('application/octet-stream')
content_html = content_type('text/html')
content_xhtml = content_type('application/xhtml+xml')


def acceptable_content_type( accept_header, content_types, ignore_wildcard=True ):
    """Determines if the given content type is acceptable to the user agent.

    The accept_header should be the value present in the HTTP
    "Accept:" header.  In mod_python this is typically obtained from
    the req.http_headers_in table; in WSGI it is environ["Accept"];
    other web frameworks may provide other methods of obtaining it.

    Optionally the accept_header parameter can be pre-parsed, as
    returned from the parse_accept_header() function in this module.

    The content_types argument should either be a single MIME media
    type string, or a sequence of them.  It represents the set of
    content types that the caller (server) is willing to send.
github scrapinghub / extruct / extruct / rdflibxml / extras / httpheader.py View on Github external
return self.major == 'multipart' or self.major == 'message'

    def is_xml(self):
        """Returns True if this media type is XML-based.

        Note this does not consider text/html to be XML, but
        application/xhtml+xml is.
        """
        return self.minor == 'xml' or self.minor.endswith('+xml')

# Some common media types
content_formdata = content_type('multipart/form-data')
content_urlencoded = content_type('application/x-www-form-urlencoded')
content_byteranges = content_type('multipart/byteranges') # RFC 2616 sect 14.16
content_opaque = content_type('application/octet-stream')
content_html = content_type('text/html')
content_xhtml = content_type('application/xhtml+xml')


def acceptable_content_type( accept_header, content_types, ignore_wildcard=True ):
    """Determines if the given content type is acceptable to the user agent.

    The accept_header should be the value present in the HTTP
    "Accept:" header.  In mod_python this is typically obtained from
    the req.http_headers_in table; in WSGI it is environ["Accept"];
    other web frameworks may provide other methods of obtaining it.

    Optionally the accept_header parameter can be pre-parsed, as
    returned from the parse_accept_header() function in this module.

    The content_types argument should either be a single MIME media
    type string, or a sequence of them.  It represents the set of