diff options
author | Jeremy Hylton <jeremy@alum.mit.edu> | 2009-03-31 14:35:53 (GMT) |
---|---|---|
committer | Jeremy Hylton <jeremy@alum.mit.edu> | 2009-03-31 14:35:53 (GMT) |
commit | 6c5e28c383bf587f80d01e52f887801be200200d (patch) | |
tree | 6f8485b2ea4820facd7049320142e40028658494 /Lib/urllib/request.py | |
parent | 16caab00a259c1a01f8e47abdd321c42b1b6e554 (diff) | |
download | cpython-6c5e28c383bf587f80d01e52f887801be200200d.zip cpython-6c5e28c383bf587f80d01e52f887801be200200d.tar.gz cpython-6c5e28c383bf587f80d01e52f887801be200200d.tar.bz2 |
Simplify the Request class. The basic components of the parsed
Request are now available as public attributes, e.g. full_url and
host. The accessor methods are deprecated. The implementation
replace the complicated __getattr__ machinery with a _parse() method.
The response from an HTTP request is now an HTTPResponse instance
instead of an addinfourl() wrapper instance. The wrapper provided
minimal extract functionality and was undocumented. The API of
addinfourl() was preserved, except for close hooks, by adding a few
methods and public attributes to the HTTPResponse class.
Diffstat (limited to 'Lib/urllib/request.py')
-rw-r--r-- | Lib/urllib/request.py | 165 |
1 files changed, 73 insertions, 92 deletions
diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py index c789ffc..3776536 100644 --- a/Lib/urllib/request.py +++ b/Lib/urllib/request.py @@ -1,6 +1,3 @@ -# Issues in merging urllib and urllib2: -# 1. They both define a function named urlopen() - """An extensible library for opening URLs using a variety of protocols The simplest way to use this module is to call the urlopen function, @@ -83,6 +80,7 @@ f = urllib.request.urlopen('http://www.python.org/') # abstract factory for opener import base64 +import bisect import email import hashlib import http.client @@ -94,7 +92,6 @@ import re import socket import sys import time -import bisect from urllib.error import URLError, HTTPError, ContentTooShortError from urllib.parse import ( @@ -149,7 +146,7 @@ def request_host(request): comparison. """ - url = request.get_full_url() + url = request.full_url host = urlparse(url)[1] if host == "": host = request.get_header("Host", "") @@ -163,11 +160,7 @@ class Request: def __init__(self, url, data=None, headers={}, origin_req_host=None, unverifiable=False): # unwrap('<URL:type://host/path>') --> 'type://host/path' - self.__original = unwrap(url) - self.type = None - # self.__r_type is what's left after doing the splittype - self.host = None - self.port = None + self.full_url = unwrap(url) self.data = data self.headers = {} for key, value in headers.items(): @@ -177,26 +170,23 @@ class Request: origin_req_host = request_host(self) self.origin_req_host = origin_req_host self.unverifiable = unverifiable + self._parse() - def __getattr__(self, attr): - # XXX this is a fallback mechanism to guard against these - # methods getting called in a non-standard order. this may be - # too complicated and/or unnecessary. - # XXX should the __r_XXX attributes be public? - if attr[:12] == '_Request__r_': - name = attr[12:] - if hasattr(Request, 'get_' + name): - getattr(self, 'get_' + name)() - return getattr(self, attr) - raise AttributeError(attr) + def _parse(self): + self.type, rest = splittype(self.full_url) + if self.type is None: + raise ValueError("unknown url type: %s" % self.full_url) + self.host, self.selector = splithost(rest) + if self.host: + self.host = unquote(self.host) def get_method(self): - if self.has_data(): + if self.data is not None: return "POST" else: return "GET" - # XXX these helper methods are lame + # Begin deprecated methods def add_data(self, data): self.data = data @@ -208,37 +198,31 @@ class Request: return self.data def get_full_url(self): - return self.__original + return self.full_url def get_type(self): - if self.type is None: - self.type, self.__r_type = splittype(self.__original) - if self.type is None: - raise ValueError("unknown url type: %s" % self.__original) return self.type def get_host(self): - if self.host is None: - self.host, self.__r_host = splithost(self.__r_type) - if self.host: - self.host = unquote(self.host) return self.host def get_selector(self): - return self.__r_host + return self.selector - def set_proxy(self, host, type): - self.host, self.type = host, type - self.__r_host = self.__original - - def has_proxy(self): - return self.__r_host == self.__original + def is_unverifiable(self): + return self.unverifiable def get_origin_req_host(self): return self.origin_req_host - def is_unverifiable(self): - return self.unverifiable + # End deprecated methods + + def set_proxy(self, host, type): + self.host, self.type = host, type + self.selector = self.full_url + + def has_proxy(self): + return self.selector == self.full_url def add_header(self, key, val): # useful for something like authentication @@ -344,10 +328,10 @@ class OpenerDirector: else: req = fullurl if data is not None: - req.add_data(data) + req.data = data req.timeout = timeout - protocol = req.get_type() + protocol = req.type # pre-process request meth_name = protocol+"_request" @@ -371,7 +355,7 @@ class OpenerDirector: if result: return result - protocol = req.get_type() + protocol = req.type result = self._call_chain(self.handle_open, protocol, protocol + '_open', req) if result: @@ -481,7 +465,7 @@ class HTTPErrorProcessor(BaseHandler): class HTTPDefaultErrorHandler(BaseHandler): def http_error_default(self, req, fp, code, msg, hdrs): - raise HTTPError(req.get_full_url(), code, msg, hdrs, fp) + raise HTTPError(req.full_url, code, msg, hdrs, fp) class HTTPRedirectHandler(BaseHandler): # maximum number of redirections to any single URL @@ -504,7 +488,7 @@ class HTTPRedirectHandler(BaseHandler): m = req.get_method() if (not (code in (301, 302, 303, 307) and m in ("GET", "HEAD") or code in (301, 302, 303) and m == "POST")): - raise HTTPError(req.get_full_url(), code, msg, headers, fp) + raise HTTPError(req.full_url, code, msg, headers, fp) # Strictly (according to RFC 2616), 301 or 302 in response to # a POST MUST NOT cause a redirection without confirmation @@ -518,7 +502,7 @@ class HTTPRedirectHandler(BaseHandler): if k.lower() not in CONTENT_HEADERS) return Request(newurl, headers=newheaders, - origin_req_host=req.get_origin_req_host(), + origin_req_host=req.origin_req_host, unverifiable=True) # Implementation note: To avoid the server sending us into an @@ -542,7 +526,7 @@ class HTTPRedirectHandler(BaseHandler): urlparts[2] = "/" newurl = urlunparse(urlparts) - newurl = urljoin(req.get_full_url(), newurl) + newurl = urljoin(req.full_url, newurl) # XXX Probably want to forget about the state of the current # request, although that might interact poorly with other @@ -557,7 +541,7 @@ class HTTPRedirectHandler(BaseHandler): 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, + raise HTTPError(req.full_url, code, self.inf_msg + msg, headers, fp) else: visited = new.redirect_dict = req.redirect_dict = {} @@ -664,7 +648,7 @@ class ProxyHandler(BaseHandler): meth(r, proxy, type)) def proxy_open(self, req, proxy, type): - orig_type = req.get_type() + orig_type = req.type proxy_type, user, password, hostport = _parse_proxy(proxy) if proxy_type is None: proxy_type = orig_type @@ -811,7 +795,7 @@ class HTTPBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler): auth_header = 'Authorization' def http_error_401(self, req, fp, code, msg, headers): - url = req.get_full_url() + url = req.full_url return self.http_error_auth_reqed('www-authenticate', url, req, headers) @@ -825,7 +809,7 @@ class ProxyBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler): # authority. Assume there isn't one, since urllib.request does not (and # should not, RFC 3986 s. 3.2.1) support requests for URLs containing # userinfo. - authority = req.get_host() + authority = req.host return self.http_error_auth_reqed('proxy-authenticate', authority, req, headers) @@ -864,7 +848,7 @@ class AbstractDigestAuthHandler: # prompting for the information. Crap. This isn't great # but it's better than the current 'repeat until recursion # depth exceeded' approach <wink> - raise HTTPError(req.get_full_url(), 401, "digest auth failed", + raise HTTPError(req.full_url, 401, "digest auth failed", headers, None) else: self.retried += 1 @@ -912,20 +896,20 @@ class AbstractDigestAuthHandler: if H is None: return None - user, pw = self.passwd.find_user_password(realm, req.get_full_url()) + user, pw = self.passwd.find_user_password(realm, req.full_url) if user is None: return None # XXX not implemented yet - if req.has_data(): - entdig = self.get_entity_digest(req.get_data(), chal) + if req.data is not None: + entdig = self.get_entity_digest(req.data, chal) else: entdig = None A1 = "%s:%s:%s" % (user, realm, pw) A2 = "%s:%s" % (req.get_method(), # XXX selector: what about proxies and full urls - req.get_selector()) + req.selector) if qop == 'auth': self.nonce_count += 1 ncvalue = '%08x' % self.nonce_count @@ -941,7 +925,7 @@ class AbstractDigestAuthHandler: # XXX should the partial digests be encoded too? base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \ - 'response="%s"' % (user, realm, nonce, req.get_selector(), + 'response="%s"' % (user, realm, nonce, req.selector, respdig) if opaque: base += ', opaque="%s"' % opaque @@ -978,7 +962,7 @@ class HTTPDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler): handler_order = 490 # before Basic auth def http_error_401(self, req, fp, code, msg, headers): - host = urlparse(req.get_full_url())[1] + host = urlparse(req.full_url)[1] retry = self.http_error_auth_reqed('www-authenticate', host, req, headers) self.reset_retry_count() @@ -991,7 +975,7 @@ class ProxyDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler): handler_order = 490 # before Basic auth def http_error_407(self, req, fp, code, msg, headers): - host = req.get_host() + host = req.host retry = self.http_error_auth_reqed('proxy-authenticate', host, req, headers) self.reset_retry_count() @@ -1006,12 +990,12 @@ class AbstractHTTPHandler(BaseHandler): self._debuglevel = level def do_request_(self, request): - host = request.get_host() + host = request.host if not host: raise URLError('no host given') - if request.has_data(): # POST - data = request.get_data() + if request.data is not None: # POST + data = request.data if not request.has_header('Content-type'): request.add_unredirected_header( 'Content-type', @@ -1022,7 +1006,7 @@ class AbstractHTTPHandler(BaseHandler): sel_host = host if request.has_proxy(): - scheme, sel = splittype(request.get_selector()) + scheme, sel = splittype(request.selector) sel_host, sel_path = splithost(sel) if not request.has_header('Host'): request.add_unredirected_header('Host', sel_host) @@ -1034,16 +1018,11 @@ class AbstractHTTPHandler(BaseHandler): return request def do_open(self, http_class, req): - """Return an addinfourl object for the request, using http_class. + """Return an HTTPResponse object for the request, using http_class. http_class must implement the HTTPConnection API from http.client. - The addinfourl return value is a file-like object. It also - has methods and attributes including: - - info(): return a email Message object for the headers - - geturl(): return the original request URL - - code: HTTP status code """ - host = req.get_host() + host = req.host if not host: raise URLError('no host given') @@ -1061,19 +1040,21 @@ class AbstractHTTPHandler(BaseHandler): # So make sure the connection gets closed after the (only) # request. headers["Connection"] = "close" - headers = dict( - (name.title(), val) for name, val in headers.items()) + headers = dict((name.title(), val) for name, val in headers.items()) try: - h.request(req.get_method(), req.get_selector(), req.data, headers) - r = h.getresponse() - except socket.error as err: # XXX what error? + h.request(req.get_method(), req.selector, req.data, headers) + r = h.getresponse() # an HTTPResponse instance + except socket.error as err: raise URLError(err) -## resp = addinfourl(r.fp, r.msg, req.get_full_url()) - resp = addinfourl(r, r.msg, req.get_full_url()) - resp.code = r.status - resp.msg = r.reason - return resp + r.url = req.full_url + # This line replaces the .msg attribute of the HTTPResponse + # with .headers, because urllib clients expect the response to + # have the reason in .msg. It would be good to mark this + # attribute is deprecated and get then to use info() or + # .headers. + r.msg = r.reason + return r class HTTPHandler(AbstractHTTPHandler): @@ -1111,7 +1092,7 @@ class HTTPCookieProcessor(BaseHandler): class UnknownHandler(BaseHandler): def unknown_open(self, req): - type = req.get_type() + type = req.type raise URLError('unknown url type: %s' % type) def parse_keqv_list(l): @@ -1170,7 +1151,7 @@ def parse_http_list(s): class FileHandler(BaseHandler): # Use local file or FTP depending on form of URL def file_open(self, req): - url = req.get_selector() + url = req.selector if url[:2] == '//' and url[2:3] != '/': req.type = 'ftp' return self.parent.open(req) @@ -1192,8 +1173,8 @@ class FileHandler(BaseHandler): def open_local_file(self, req): import email.utils import mimetypes - host = req.get_host() - file = req.get_selector() + host = req.host + file = req.selector localfile = url2pathname(file) try: stats = os.stat(localfile) @@ -1223,7 +1204,7 @@ class FTPHandler(BaseHandler): def ftp_open(self, req): import ftplib import mimetypes - host = req.get_host() + host = req.host if not host: raise URLError('ftp error: no host given') host, port = splitport(host) @@ -1246,7 +1227,7 @@ class FTPHandler(BaseHandler): host = socket.gethostbyname(host) except socket.error as msg: raise URLError(msg) - path, attrs = splitattr(req.get_selector()) + path, attrs = splitattr(req.selector) dirs = path.split('/') dirs = list(map(unquote, dirs)) dirs, file = dirs[:-1], dirs[-1] @@ -1262,13 +1243,13 @@ class FTPHandler(BaseHandler): type = value.upper() fp, retrlen = fw.retrfile(file, type) headers = "" - mtype = mimetypes.guess_type(req.get_full_url())[0] + mtype = mimetypes.guess_type(req.full_url)[0] if mtype: headers += "Content-type: %s\n" % mtype if retrlen is not None and retrlen >= 0: headers += "Content-length: %d\n" % retrlen headers = email.message_from_string(headers) - return addinfourl(fp, headers, req.get_full_url()) + return addinfourl(fp, headers, req.full_url) except ftplib.all_errors as msg: exc = URLError('ftp error: %s' % msg) raise exc.with_traceback(sys.exc_info()[2]) @@ -1581,9 +1562,9 @@ class URLopener: else: auth = None http_conn = connection_factory(host) - # XXX We should fix urllib so that it works with HTTP/1.1. - http_conn._http_vsn = 10 - http_conn._http_vsn_str = "HTTP/1.0" +## # XXX We should fix urllib so that it works with HTTP/1.1. +## http_conn._http_vsn = 10 +## http_conn._http_vsn_str = "HTTP/1.0" headers = {} if proxy_auth: |