From f90b002e31f245286e34209a96e13d1d5e281c76 Mon Sep 17 00:00:00 2001 From: Jeremy Hylton Date: Thu, 25 Feb 1999 16:12:12 +0000 Subject: change indentation from 8 spaces to 4 spaces --- Lib/urllib.py | 1737 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 859 insertions(+), 878 deletions(-) diff --git a/Lib/urllib.py b/Lib/urllib.py index 2b0f2a7..3c8bc0f 100644 --- a/Lib/urllib.py +++ b/Lib/urllib.py @@ -29,25 +29,25 @@ import sys __version__ = '1.10' -MAXFTPCACHE = 10 # Trim the ftp cache beyond this size +MAXFTPCACHE = 10 # Trim the ftp cache beyond this size # Helper for non-unix systems if os.name == 'mac': - from macurl2path import url2pathname, pathname2url + from macurl2path import url2pathname, pathname2url elif os.name == 'nt': - from nturl2path import url2pathname, pathname2url + from nturl2path import url2pathname, pathname2url else: - def url2pathname(pathname): - return pathname - def pathname2url(pathname): - return pathname + def url2pathname(pathname): + return pathname + def pathname2url(pathname): + return pathname _url2pathname = url2pathname def url2pathname(url): - return _url2pathname(unquote(url)) + return _url2pathname(unquote(url)) _pathname2url = pathname2url def pathname2url(p): - return quote(_pathname2url(p)) + return quote(_pathname2url(p)) # This really consists of two pieces: # (1) a class which handles opening of all sorts of URLs @@ -59,21 +59,21 @@ def pathname2url(p): # Shortcut for basic usage _urlopener = None def urlopen(url, data=None): - global _urlopener - if not _urlopener: - _urlopener = FancyURLopener() - if data is None: - return _urlopener.open(url) - else: - return _urlopener.open(url, data) + global _urlopener + if not _urlopener: + _urlopener = FancyURLopener() + if data is None: + return _urlopener.open(url) + else: + return _urlopener.open(url, data) def urlretrieve(url, filename=None, reporthook=None): - global _urlopener - if not _urlopener: - _urlopener = FancyURLopener() - return _urlopener.retrieve(url, filename, reporthook) + global _urlopener + if not _urlopener: + _urlopener = FancyURLopener() + return _urlopener.retrieve(url, filename, reporthook) def urlcleanup(): - if _urlopener: - _urlopener.cleanup() + if _urlopener: + _urlopener.cleanup() # Class to open URLs. @@ -85,451 +85,433 @@ def urlcleanup(): ftpcache = {} class URLopener: - __tempfiles = None - - # Constructor - def __init__(self, proxies=None): - if proxies is None: - proxies = getproxies() - assert hasattr(proxies, 'has_key'), "proxies must be a mapping" - self.proxies = proxies - server_version = "Python-urllib/%s" % __version__ - self.addheaders = [('User-agent', server_version)] - self.__tempfiles = [] - self.__unlink = os.unlink # See cleanup() - self.tempcache = None - # Undocumented feature: if you assign {} to tempcache, - # it is used to cache files retrieved with - # self.retrieve(). This is not enabled by default - # since it does not work for changing documents (and I - # haven't got the logic to check expiration headers - # yet). - self.ftpcache = ftpcache - # Undocumented feature: you can use a different - # ftp cache by assigning to the .ftpcache member; - # in case you want logically independent URL openers - # XXX This is not threadsafe. Bah. - - def __del__(self): - self.close() - - def close(self): - self.cleanup() - - def cleanup(self): - # This code sometimes runs when the rest of this module - # has already been deleted, so it can't use any globals - # or import anything. - if self.__tempfiles: - for file in self.__tempfiles: - try: - self.__unlink(file) - except: - pass - del self.__tempfiles[:] - if self.tempcache: - self.tempcache.clear() - - # Add a header to be used by the HTTP interface only - # e.g. u.addheader('Accept', 'sound/basic') - def addheader(self, *args): - self.addheaders.append(args) - - # External interface - # Use URLopener().open(file) instead of open(file, 'r') - def open(self, fullurl, data=None): - fullurl = unwrap(fullurl) - if self.tempcache and self.tempcache.has_key(fullurl): - filename, headers = self.tempcache[fullurl] - fp = open(filename, 'rb') - return addinfourl(fp, headers, fullurl) - type, url = splittype(fullurl) - if not type: type = 'file' - if self.proxies.has_key(type): - proxy = self.proxies[type] - type, proxy = splittype(proxy) - host, selector = splithost(proxy) - url = (host, fullurl) # Signal special case to open_*() - name = 'open_' + type - if '-' in name: - # replace - with _ - name = string.join(string.split(name, '-'), '_') - if not hasattr(self, name): - if data is None: - return self.open_unknown(fullurl) - else: - return self.open_unknown(fullurl, data) - try: - if data is None: - return getattr(self, name)(url) - else: - return getattr(self, name)(url, data) - except socket.error, msg: - raise IOError, ('socket error', msg), sys.exc_info()[2] - - # Overridable interface to open unknown URL type - def open_unknown(self, fullurl, data=None): - type, url = splittype(fullurl) - raise IOError, ('url error', 'unknown url type', type) - - # External interface - # retrieve(url) returns (filename, None) for a local object - # or (tempfilename, headers) for a remote object - def retrieve(self, url, filename=None, reporthook=None): - url = unwrap(url) - if self.tempcache and self.tempcache.has_key(url): - return self.tempcache[url] - type, url1 = splittype(url) - if not filename and (not type or type == 'file'): - try: - fp = self.open_local_file(url1) - hdrs = fp.info() - del fp - return url2pathname(splithost(url1)[1]), hdrs - except IOError, msg: - pass - fp = self.open(url) - headers = fp.info() - if not filename: - import tempfile - garbage, path = splittype(url) - garbage, path = splithost(path or "") - path, garbage = splitquery(path or "") - path, garbage = splitattr(path or "") - suffix = os.path.splitext(path)[1] - filename = tempfile.mktemp(suffix) - self.__tempfiles.append(filename) - result = filename, headers - if self.tempcache is not None: - self.tempcache[url] = result - tfp = open(filename, 'wb') - bs = 1024*8 - size = -1 - blocknum = 1 - if reporthook: - if headers.has_key("content-length"): - size = int(headers["Content-Length"]) - reporthook(0, bs, size) - block = fp.read(bs) - if reporthook: - reporthook(1, bs, size) - while block: - tfp.write(block) - block = fp.read(bs) - blocknum = blocknum + 1 - if reporthook: - reporthook(blocknum, bs, size) - fp.close() - tfp.close() - del fp - del tfp - return result - - # Each method named open_ knows how to open that type of URL - - # Use HTTP protocol - def open_http(self, url, data=None): - import httplib - user_passwd = None - if type(url) is type(""): - host, selector = splithost(url) - if host: - user_passwd, host = splituser(host) - host = unquote(host) - realhost = host - else: - host, selector = url - urltype, rest = splittype(selector) - url = rest - user_passwd = None - if string.lower(urltype) != 'http': - realhost = None - else: - realhost, rest = splithost(rest) - if realhost: - user_passwd, realhost = \ - splituser(realhost) - if user_passwd: - selector = "%s://%s%s" % (urltype, - realhost, - rest) - #print "proxy via http:", host, selector - if not host: raise IOError, ('http error', 'no host given') - if user_passwd: - import base64 - auth = string.strip(base64.encodestring(user_passwd)) - else: - auth = None - h = httplib.HTTP(host) - if data is not None: - h.putrequest('POST', selector) - h.putheader('Content-type', - 'application/x-www-form-urlencoded') - h.putheader('Content-length', '%d' % len(data)) - else: - h.putrequest('GET', selector) - if auth: h.putheader('Authorization', 'Basic %s' % auth) - if realhost: h.putheader('Host', realhost) - for args in self.addheaders: apply(h.putheader, args) - h.endheaders() - if data is not None: - h.send(data + '\r\n') - errcode, errmsg, headers = h.getreply() - fp = h.getfile() - if errcode == 200: - return addinfourl(fp, headers, "http:" + url) - else: - if data is None: - return self.http_error(url, - fp, errcode, - errmsg, - headers, - data) - else: - return self.http_error(url, - fp, errcode, - errmsg, - headers) - - # Handle http errors. - # Derived class can override this, or provide specific handlers - # named http_error_DDD where DDD is the 3-digit error code - def http_error(self, url, fp, errcode, errmsg, headers, data=None): - # First check if there's a specific handler for this error - name = 'http_error_%d' % errcode - if hasattr(self, name): - method = getattr(self, name) - if data is None: - result = method(url, fp, errcode, errmsg, - headers, data) - else: - result = method(url, fp, errcode, errmsg, - headers) - if result: return result - return self.http_error_default( - url, fp, errcode, errmsg, headers) - - # Default http error handler: close the connection and raises IOError - def http_error_default(self, url, fp, errcode, errmsg, headers): - void = fp.read() - fp.close() - raise IOError, ('http error', errcode, errmsg, headers) - - # Use Gopher protocol - def open_gopher(self, url): - import gopherlib - host, selector = splithost(url) - if not host: raise IOError, ('gopher error', 'no host given') - host = unquote(host) - type, selector = splitgophertype(selector) - selector, query = splitquery(selector) - selector = unquote(selector) - if query: - query = unquote(query) - fp = gopherlib.send_query(selector, query, host) - else: - fp = gopherlib.send_selector(selector, host) - return addinfourl(fp, noheaders(), "gopher:" + url) - - # Use local file or FTP depending on form of URL - def open_file(self, url): - if url[:2] == '//' and url[2:3] != '/': - return self.open_ftp(url) - else: - return self.open_local_file(url) - - # Use local file - def open_local_file(self, url): - import mimetypes, mimetools, StringIO - mtype = mimetypes.guess_type(url)[0] - headers = mimetools.Message(StringIO.StringIO( - 'Content-Type: %s\n' % (mtype or 'text/plain'))) - host, file = splithost(url) - if not host: - return addinfourl( - open(url2pathname(file), 'rb'), - headers, 'file:'+pathname2url(file)) - host, port = splitport(host) - if not port and socket.gethostbyname(host) in ( - localhost(), thishost()): - return addinfourl( - open(url2pathname(file), 'rb'), - headers, 'file:'+pathname2url(file)) - raise IOError, ('local file error', 'not on local host') - - # Use FTP protocol - def open_ftp(self, url): - host, path = splithost(url) - if not host: raise IOError, ('ftp error', 'no host given') - host, port = splitport(host) - user, host = splituser(host) - if user: user, passwd = splitpasswd(user) - else: passwd = None - host = unquote(host) - user = unquote(user or '') - passwd = unquote(passwd or '') - host = socket.gethostbyname(host) - if not port: - import ftplib - port = ftplib.FTP_PORT - else: - port = int(port) - path, attrs = splitattr(path) - path = unquote(path) - dirs = string.splitfields(path, '/') - dirs, file = dirs[:-1], dirs[-1] - if dirs and not dirs[0]: dirs = dirs[1:] - key = (user, host, port, string.joinfields(dirs, '/')) - # XXX thread unsafe! - if len(self.ftpcache) > MAXFTPCACHE: - # Prune the cache, rather arbitrarily - for k in self.ftpcache.keys(): - if k != key: - v = self.ftpcache[k] - del self.ftpcache[k] - v.close() - try: - if not self.ftpcache.has_key(key): - self.ftpcache[key] = \ - ftpwrapper(user, passwd, - host, port, dirs) - if not file: type = 'D' - else: type = 'I' - for attr in attrs: - attr, value = splitvalue(attr) - if string.lower(attr) == 'type' and \ - value in ('a', 'A', 'i', 'I', 'd', 'D'): - type = string.upper(value) - (fp, retrlen) = self.ftpcache[key].retrfile(file, type) - if retrlen is not None and retrlen >= 0: - import mimetools, StringIO - headers = mimetools.Message(StringIO.StringIO( - 'Content-Length: %d\n' % retrlen)) - else: - headers = noheaders() - return addinfourl(fp, headers, "ftp:" + url) - except ftperrors(), msg: - raise IOError, ('ftp error', msg), sys.exc_info()[2] - - # Use "data" URL - def open_data(self, url, data=None): - # ignore POSTed data - # - # syntax of data URLs: - # dataurl := "data:" [ mediatype ] [ ";base64" ] "," data - # mediatype := [ type "/" subtype ] *( ";" parameter ) - # data := *urlchar - # parameter := attribute "=" value - import StringIO, mimetools, time - try: - [type, data] = string.split(url, ',', 1) - except ValueError: - raise IOError, ('data error', 'bad data URL') - if not type: - type = 'text/plain;charset=US-ASCII' - semi = string.rfind(type, ';') - if semi >= 0 and '=' not in type[semi:]: - encoding = type[semi+1:] - type = type[:semi] - else: - encoding = '' - msg = [] - msg.append('Date: %s'%time.strftime('%a, %d %b %Y %T GMT', - time.gmtime(time.time()))) - msg.append('Content-type: %s' % type) - if encoding == 'base64': - import base64 - data = base64.decodestring(data) - else: - data = unquote(data) - msg.append('Content-length: %d' % len(data)) - msg.append('') - msg.append(data) - msg = string.join(msg, '\n') - f = StringIO.StringIO(msg) - headers = mimetools.Message(f, 0) - f.fileno = None # needed for addinfourl - return addinfourl(f, headers, url) + __tempfiles = None + + # Constructor + def __init__(self, proxies=None): + if proxies is None: + proxies = getproxies() + assert hasattr(proxies, 'has_key'), "proxies must be a mapping" + self.proxies = proxies + server_version = "Python-urllib/%s" % __version__ + self.addheaders = [('User-agent', server_version)] + self.__tempfiles = [] + self.__unlink = os.unlink # See cleanup() + self.tempcache = None + # Undocumented feature: if you assign {} to tempcache, + # it is used to cache files retrieved with + # self.retrieve(). This is not enabled by default + # since it does not work for changing documents (and I + # haven't got the logic to check expiration headers + # yet). + self.ftpcache = ftpcache + # Undocumented feature: you can use a different + # ftp cache by assigning to the .ftpcache member; + # in case you want logically independent URL openers + # XXX This is not threadsafe. Bah. + + def __del__(self): + self.close() + + def close(self): + self.cleanup() + + def cleanup(self): + # This code sometimes runs when the rest of this module + # has already been deleted, so it can't use any globals + # or import anything. + if self.__tempfiles: + for file in self.__tempfiles: + try: + self.__unlink(file) + except: + pass + del self.__tempfiles[:] + if self.tempcache: + self.tempcache.clear() + + # Add a header to be used by the HTTP interface only + # e.g. u.addheader('Accept', 'sound/basic') + def addheader(self, *args): + self.addheaders.append(args) + + # External interface + # Use URLopener().open(file) instead of open(file, 'r') + def open(self, fullurl, data=None): + fullurl = unwrap(fullurl) + if self.tempcache and self.tempcache.has_key(fullurl): + filename, headers = self.tempcache[fullurl] + fp = open(filename, 'rb') + return addinfourl(fp, headers, fullurl) + type, url = splittype(fullurl) + if not type: type = 'file' + if self.proxies.has_key(type): + proxy = self.proxies[type] + type, proxy = splittype(proxy) + host, selector = splithost(proxy) + url = (host, fullurl) # Signal special case to open_*() + name = 'open_' + type + if '-' in name: + # replace - with _ + name = string.join(string.split(name, '-'), '_') + if not hasattr(self, name): + if data is None: + return self.open_unknown(fullurl) + else: + return self.open_unknown(fullurl, data) + try: + if data is None: + return getattr(self, name)(url) + else: + return getattr(self, name)(url, data) + except socket.error, msg: + raise IOError, ('socket error', msg), sys.exc_info()[2] + + # Overridable interface to open unknown URL type + def open_unknown(self, fullurl, data=None): + type, url = splittype(fullurl) + raise IOError, ('url error', 'unknown url type', type) + + # External interface + # retrieve(url) returns (filename, None) for a local object + # or (tempfilename, headers) for a remote object + def retrieve(self, url, filename=None, reporthook=None): + url = unwrap(url) + if self.tempcache and self.tempcache.has_key(url): + return self.tempcache[url] + type, url1 = splittype(url) + if not filename and (not type or type == 'file'): + try: + fp = self.open_local_file(url1) + hdrs = fp.info() + del fp + return url2pathname(splithost(url1)[1]), hdrs + except IOError, msg: + pass + fp = self.open(url) + headers = fp.info() + if not filename: + import tempfile + garbage, path = splittype(url) + garbage, path = splithost(path or "") + path, garbage = splitquery(path or "") + path, garbage = splitattr(path or "") + suffix = os.path.splitext(path)[1] + filename = tempfile.mktemp(suffix) + self.__tempfiles.append(filename) + result = filename, headers + if self.tempcache is not None: + self.tempcache[url] = result + tfp = open(filename, 'wb') + bs = 1024*8 + size = -1 + blocknum = 1 + if reporthook: + if headers.has_key("content-length"): + size = int(headers["Content-Length"]) + reporthook(0, bs, size) + block = fp.read(bs) + if reporthook: + reporthook(1, bs, size) + while block: + tfp.write(block) + block = fp.read(bs) + blocknum = blocknum + 1 + if reporthook: + reporthook(blocknum, bs, size) + fp.close() + tfp.close() + del fp + del tfp + return result + + # Each method named open_ knows how to open that type of URL + + # Use HTTP protocol + def open_http(self, url, data=None): + import httplib + user_passwd = None + if type(url) is type(""): + host, selector = splithost(url) + if host: + user_passwd, host = splituser(host) + host = unquote(host) + realhost = host + else: + host, selector = url + urltype, rest = splittype(selector) + url = rest + user_passwd = None + if string.lower(urltype) != 'http': + realhost = None + else: + realhost, rest = splithost(rest) + if realhost: + user_passwd, realhost = splituser(realhost) + if user_passwd: + selector = "%s://%s%s" % (urltype, realhost, rest) + #print "proxy via http:", host, selector + if not host: raise IOError, ('http error', 'no host given') + if user_passwd: + import base64 + auth = string.strip(base64.encodestring(user_passwd)) + else: + auth = None + h = httplib.HTTP(host) + if data is not None: + h.putrequest('POST', selector) + h.putheader('Content-type', 'application/x-www-form-urlencoded') + h.putheader('Content-length', '%d' % len(data)) + else: + h.putrequest('GET', selector) + if auth: h.putheader('Authorization', 'Basic %s' % auth) + if realhost: h.putheader('Host', realhost) + for args in self.addheaders: apply(h.putheader, args) + h.endheaders() + if data is not None: + h.send(data + '\r\n') + errcode, errmsg, headers = h.getreply() + fp = h.getfile() + if errcode == 200: + return addinfourl(fp, headers, "http:" + url) + else: + if data is None: + return self.http_error(url, fp, errcode, errmsg, + headers, data) + else: + return self.http_error(url, fp, errcode, errmsg, headers) + + # Handle http errors. + # Derived class can override this, or provide specific handlers + # named http_error_DDD where DDD is the 3-digit error code + def http_error(self, url, fp, errcode, errmsg, headers, data=None): + # First check if there's a specific handler for this error + name = 'http_error_%d' % errcode + if hasattr(self, name): + method = getattr(self, name) + if data is None: + result = method(url, fp, errcode, errmsg, headers, data) + else: + result = method(url, fp, errcode, errmsg, headers) + if result: return result + return self.http_error_default( + url, fp, errcode, errmsg, headers) + + # Default http error handler: close the connection and raises IOError + def http_error_default(self, url, fp, errcode, errmsg, headers): + void = fp.read() + fp.close() + raise IOError, ('http error', errcode, errmsg, headers) + + # Use Gopher protocol + def open_gopher(self, url): + import gopherlib + host, selector = splithost(url) + if not host: raise IOError, ('gopher error', 'no host given') + host = unquote(host) + type, selector = splitgophertype(selector) + selector, query = splitquery(selector) + selector = unquote(selector) + if query: + query = unquote(query) + fp = gopherlib.send_query(selector, query, host) + else: + fp = gopherlib.send_selector(selector, host) + return addinfourl(fp, noheaders(), "gopher:" + url) + + # Use local file or FTP depending on form of URL + def open_file(self, url): + if url[:2] == '//' and url[2:3] != '/': + return self.open_ftp(url) + else: + return self.open_local_file(url) + + # Use local file + def open_local_file(self, url): + import mimetypes, mimetools, StringIO + mtype = mimetypes.guess_type(url)[0] + headers = mimetools.Message(StringIO.StringIO( + 'Content-Type: %s\n' % (mtype or 'text/plain'))) + host, file = splithost(url) + if not host: + return addinfourl(open(url2pathname(file), 'rb'), + headers, 'file:'+pathname2url(file)) + host, port = splitport(host) + if not port \ + and socket.gethostbyname(host) in (localhost(), thishost()): + return addinfourl(open(url2pathname(file), 'rb'), + headers, 'file:'+pathname2url(file)) + raise IOError, ('local file error', 'not on local host') + + # Use FTP protocol + def open_ftp(self, url): + host, path = splithost(url) + if not host: raise IOError, ('ftp error', 'no host given') + host, port = splitport(host) + user, host = splituser(host) + if user: user, passwd = splitpasswd(user) + else: passwd = None + host = unquote(host) + user = unquote(user or '') + passwd = unquote(passwd or '') + host = socket.gethostbyname(host) + if not port: + import ftplib + port = ftplib.FTP_PORT + else: + port = int(port) + path, attrs = splitattr(path) + path = unquote(path) + dirs = string.splitfields(path, '/') + dirs, file = dirs[:-1], dirs[-1] + if dirs and not dirs[0]: dirs = dirs[1:] + key = (user, host, port, string.joinfields(dirs, '/')) + # XXX thread unsafe! + if len(self.ftpcache) > MAXFTPCACHE: + # Prune the cache, rather arbitrarily + for k in self.ftpcache.keys(): + if k != key: + v = self.ftpcache[k] + del self.ftpcache[k] + v.close() + try: + if not self.ftpcache.has_key(key): + self.ftpcache[key] = \ + ftpwrapper(user, passwd, host, port, dirs) + if not file: type = 'D' + else: type = 'I' + for attr in attrs: + attr, value = splitvalue(attr) + if string.lower(attr) == 'type' and \ + value in ('a', 'A', 'i', 'I', 'd', 'D'): + type = string.upper(value) + (fp, retrlen) = self.ftpcache[key].retrfile(file, type) + if retrlen is not None and retrlen >= 0: + import mimetools, StringIO + headers = mimetools.Message(StringIO.StringIO( + 'Content-Length: %d\n' % retrlen)) + else: + headers = noheaders() + return addinfourl(fp, headers, "ftp:" + url) + except ftperrors(), msg: + raise IOError, ('ftp error', msg), sys.exc_info()[2] + + # Use "data" URL + def open_data(self, url, data=None): + # ignore POSTed data + # + # syntax of data URLs: + # dataurl := "data:" [ mediatype ] [ ";base64" ] "," data + # mediatype := [ type "/" subtype ] *( ";" parameter ) + # data := *urlchar + # parameter := attribute "=" value + import StringIO, mimetools, time + try: + [type, data] = string.split(url, ',', 1) + except ValueError: + raise IOError, ('data error', 'bad data URL') + if not type: + type = 'text/plain;charset=US-ASCII' + semi = string.rfind(type, ';') + if semi >= 0 and '=' not in type[semi:]: + encoding = type[semi+1:] + type = type[:semi] + else: + encoding = '' + msg = [] + msg.append('Date: %s'%time.strftime('%a, %d %b %Y %T GMT', + time.gmtime(time.time()))) + msg.append('Content-type: %s' % type) + if encoding == 'base64': + import base64 + data = base64.decodestring(data) + else: + data = unquote(data) + msg.append('Content-length: %d' % len(data)) + msg.append('') + msg.append(data) + msg = string.join(msg, '\n') + f = StringIO.StringIO(msg) + headers = mimetools.Message(f, 0) + f.fileno = None # needed for addinfourl + return addinfourl(f, headers, url) # Derived class with handlers for errors we can handle (perhaps) class FancyURLopener(URLopener): - def __init__(self, *args): - apply(URLopener.__init__, (self,) + args) - self.auth_cache = {} - - # Default error handling -- don't raise an exception - def http_error_default(self, url, fp, errcode, errmsg, headers): - return addinfourl(fp, headers, "http:" + url) - - # Error 302 -- relocated (temporarily) - def http_error_302(self, url, fp, errcode, errmsg, headers, - data=None): - # XXX The server can force infinite recursion here! - if headers.has_key('location'): - newurl = headers['location'] - elif headers.has_key('uri'): - newurl = headers['uri'] - else: - return - void = fp.read() - fp.close() - return self.open(newurl, data) - - # Error 301 -- also relocated (permanently) - http_error_301 = http_error_302 - - # Error 401 -- authentication required - # See this URL for a description of the basic authentication scheme: - # http://www.ics.uci.edu/pub/ietf/http/draft-ietf-http-v10-spec-00.txt - def http_error_401(self, url, fp, errcode, errmsg, headers, - data=None): - if headers.has_key('www-authenticate'): - stuff = headers['www-authenticate'] - import re - match = re.match( - '[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff) - if match: - scheme, realm = match.groups() - if string.lower(scheme) == 'basic': - return self.retry_http_basic_auth( - url, realm, data) - - def retry_http_basic_auth(self, url, realm, data): - host, selector = splithost(url) - i = string.find(host, '@') + 1 - host = host[i:] - user, passwd = self.get_user_passwd(host, realm, i) - if not (user or passwd): return None - host = user + ':' + passwd + '@' + host - newurl = 'http://' + host + selector - return self.open(newurl, data) - - def get_user_passwd(self, host, realm, clear_cache = 0): - key = realm + '@' + string.lower(host) - if self.auth_cache.has_key(key): - if clear_cache: - del self.auth_cache[key] - else: - return self.auth_cache[key] - user, passwd = self.prompt_user_passwd(host, realm) - if user or passwd: self.auth_cache[key] = (user, passwd) - return user, passwd - - def prompt_user_passwd(self, host, realm): - # Override this in a GUI environment! - import getpass - try: - user = raw_input("Enter username for %s at %s: " % - (realm, host)) - passwd = getpass.getpass( - "Enter password for %s in %s at %s: " % - (user, realm, host)) - return user, passwd - except KeyboardInterrupt: - print - return None, None + def __init__(self, *args): + apply(URLopener.__init__, (self,) + args) + self.auth_cache = {} + + # Default error handling -- don't raise an exception + def http_error_default(self, url, fp, errcode, errmsg, headers): + return addinfourl(fp, headers, "http:" + url) + + # Error 302 -- relocated (temporarily) + def http_error_302(self, url, fp, errcode, errmsg, headers, + data=None): + # XXX The server can force infinite recursion here! + if headers.has_key('location'): + newurl = headers['location'] + elif headers.has_key('uri'): + newurl = headers['uri'] + else: + return + void = fp.read() + fp.close() + return self.open(newurl, data) + + # Error 301 -- also relocated (permanently) + http_error_301 = http_error_302 + + # Error 401 -- authentication required + # See this URL for a description of the basic authentication scheme: + # http://www.ics.uci.edu/pub/ietf/http/draft-ietf-http-v10-spec-00.txt + def http_error_401(self, url, fp, errcode, errmsg, headers, + data=None): + if headers.has_key('www-authenticate'): + stuff = headers['www-authenticate'] + import re + match = re.match('[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff) + if match: + scheme, realm = match.groups() + if string.lower(scheme) == 'basic': + return self.retry_http_basic_auth(url, realm, data) + + def retry_http_basic_auth(self, url, realm, data): + host, selector = splithost(url) + i = string.find(host, '@') + 1 + host = host[i:] + user, passwd = self.get_user_passwd(host, realm, i) + if not (user or passwd): return None + host = user + ':' + passwd + '@' + host + newurl = 'http://' + host + selector + return self.open(newurl, data) + + def get_user_passwd(self, host, realm, clear_cache = 0): + key = realm + '@' + string.lower(host) + if self.auth_cache.has_key(key): + if clear_cache: + del self.auth_cache[key] + else: + return self.auth_cache[key] + user, passwd = self.prompt_user_passwd(host, realm) + if user or passwd: self.auth_cache[key] = (user, passwd) + return user, passwd + + def prompt_user_passwd(self, host, realm): + # Override this in a GUI environment! + import getpass + try: + user = raw_input("Enter username for %s at %s: " % (realm, + host)) + passwd = getpass.getpass("Enter password for %s in %s at %s: " % + (user, realm, host)) + return user, passwd + except KeyboardInterrupt: + print + return None, None # Utility functions @@ -537,219 +519,218 @@ class FancyURLopener(URLopener): # Return the IP address of the magic hostname 'localhost' _localhost = None def localhost(): - global _localhost - if not _localhost: - _localhost = socket.gethostbyname('localhost') - return _localhost + global _localhost + if not _localhost: + _localhost = socket.gethostbyname('localhost') + return _localhost # Return the IP address of the current host _thishost = None def thishost(): - global _thishost - if not _thishost: - _thishost = socket.gethostbyname(socket.gethostname()) - return _thishost + global _thishost + if not _thishost: + _thishost = socket.gethostbyname(socket.gethostname()) + return _thishost # Return the set of errors raised by the FTP class _ftperrors = None def ftperrors(): - global _ftperrors - if not _ftperrors: - import ftplib - _ftperrors = ftplib.all_errors - return _ftperrors + global _ftperrors + if not _ftperrors: + import ftplib + _ftperrors = ftplib.all_errors + return _ftperrors # Return an empty mimetools.Message object _noheaders = None def noheaders(): - global _noheaders - if not _noheaders: - import mimetools - import StringIO - _noheaders = mimetools.Message(StringIO.StringIO(), 0) - _noheaders.fp.close() # Recycle file descriptor - return _noheaders + global _noheaders + if not _noheaders: + import mimetools + import StringIO + _noheaders = mimetools.Message(StringIO.StringIO(), 0) + _noheaders.fp.close() # Recycle file descriptor + return _noheaders # Utility classes # Class used by open_ftp() for cache of open FTP connections class ftpwrapper: - def __init__(self, user, passwd, host, port, dirs): - self.user = user - self.passwd = passwd - self.host = host - self.port = port - self.dirs = dirs - self.init() - def init(self): - import ftplib - self.busy = 0 - self.ftp = ftplib.FTP() - self.ftp.connect(self.host, self.port) - self.ftp.login(self.user, self.passwd) - for dir in self.dirs: - self.ftp.cwd(dir) - def retrfile(self, file, type): - import ftplib - self.endtransfer() - if type in ('d', 'D'): cmd = 'TYPE A'; isdir = 1 - else: cmd = 'TYPE ' + type; isdir = 0 - try: - self.ftp.voidcmd(cmd) - except ftplib.all_errors: - self.init() - self.ftp.voidcmd(cmd) - conn = None - if file and not isdir: - # Use nlst to see if the file exists at all - try: - self.ftp.nlst(file) - except ftplib.error_perm, reason: - raise IOError, ('ftp error', reason), \ - sys.exc_info()[2] - # Restore the transfer mode! - self.ftp.voidcmd(cmd) - # Try to retrieve as a file - try: - cmd = 'RETR ' + file - conn = self.ftp.ntransfercmd(cmd) - except ftplib.error_perm, reason: - if reason[:3] != '550': - raise IOError, ('ftp error', reason), \ - sys.exc_info()[2] - if not conn: - # Set transfer mode to ASCII! - self.ftp.voidcmd('TYPE A') - # Try a directory listing - if file: cmd = 'LIST ' + file - else: cmd = 'LIST' - conn = self.ftp.ntransfercmd(cmd) - self.busy = 1 - # Pass back both a suitably decorated object and a retrieval length - return (addclosehook(conn[0].makefile('rb'), self.endtransfer), conn[1]) - def endtransfer(self): - if not self.busy: - return - self.busy = 0 - try: - self.ftp.voidresp() - except ftperrors(): - pass - def close(self): - self.endtransfer() - try: - self.ftp.close() - except ftperrors(): - pass + def __init__(self, user, passwd, host, port, dirs): + self.user = user + self.passwd = passwd + self.host = host + self.port = port + self.dirs = dirs + self.init() + def init(self): + import ftplib + self.busy = 0 + self.ftp = ftplib.FTP() + self.ftp.connect(self.host, self.port) + self.ftp.login(self.user, self.passwd) + for dir in self.dirs: + self.ftp.cwd(dir) + def retrfile(self, file, type): + import ftplib + self.endtransfer() + if type in ('d', 'D'): cmd = 'TYPE A'; isdir = 1 + else: cmd = 'TYPE ' + type; isdir = 0 + try: + self.ftp.voidcmd(cmd) + except ftplib.all_errors: + self.init() + self.ftp.voidcmd(cmd) + conn = None + if file and not isdir: + # Use nlst to see if the file exists at all + try: + self.ftp.nlst(file) + except ftplib.error_perm, reason: + raise IOError, ('ftp error', reason), sys.exc_info()[2] + # Restore the transfer mode! + self.ftp.voidcmd(cmd) + # Try to retrieve as a file + try: + cmd = 'RETR ' + file + conn = self.ftp.ntransfercmd(cmd) + except ftplib.error_perm, reason: + if reason[:3] != '550': + raise IOError, ('ftp error', reason), sys.exc_info()[2] + if not conn: + # Set transfer mode to ASCII! + self.ftp.voidcmd('TYPE A') + # Try a directory listing + if file: cmd = 'LIST ' + file + else: cmd = 'LIST' + conn = self.ftp.ntransfercmd(cmd) + self.busy = 1 + # Pass back both a suitably decorated object and a retrieval length + return (addclosehook(conn[0].makefile('rb'), + self.endtransfer), conn[1]) + def endtransfer(self): + if not self.busy: + return + self.busy = 0 + try: + self.ftp.voidresp() + except ftperrors(): + pass + def close(self): + self.endtransfer() + try: + self.ftp.close() + except ftperrors(): + pass # Base class for addinfo and addclosehook class addbase: - def __init__(self, fp): - self.fp = fp - self.read = self.fp.read - self.readline = self.fp.readline - self.readlines = self.fp.readlines - self.fileno = self.fp.fileno - def __repr__(self): - return '<%s at %s whose fp = %s>' % ( - self.__class__.__name__, `id(self)`, `self.fp`) - def close(self): - self.read = None - self.readline = None - self.readlines = None - self.fileno = None - if self.fp: self.fp.close() - self.fp = None + def __init__(self, fp): + self.fp = fp + self.read = self.fp.read + self.readline = self.fp.readline + self.readlines = self.fp.readlines + self.fileno = self.fp.fileno + def __repr__(self): + return '<%s at %s whose fp = %s>' % (self.__class__.__name__, + `id(self)`, `self.fp`) + def close(self): + self.read = None + self.readline = None + self.readlines = None + self.fileno = None + if self.fp: self.fp.close() + self.fp = None # Class to add a close hook to an open file class addclosehook(addbase): - def __init__(self, fp, closehook, *hookargs): - addbase.__init__(self, fp) - self.closehook = closehook - self.hookargs = hookargs - def close(self): - if self.closehook: - apply(self.closehook, self.hookargs) - self.closehook = None - self.hookargs = None - addbase.close(self) + def __init__(self, fp, closehook, *hookargs): + addbase.__init__(self, fp) + self.closehook = closehook + self.hookargs = hookargs + def close(self): + if self.closehook: + apply(self.closehook, self.hookargs) + self.closehook = None + self.hookargs = None + addbase.close(self) # class to add an info() method to an open file class addinfo(addbase): - def __init__(self, fp, headers): - addbase.__init__(self, fp) - self.headers = headers - def info(self): - return self.headers + def __init__(self, fp, headers): + addbase.__init__(self, fp) + self.headers = headers + def info(self): + return self.headers # class to add info() and geturl() methods to an open file class addinfourl(addbase): - def __init__(self, fp, headers, url): - addbase.__init__(self, fp) - self.headers = headers - self.url = url - def info(self): - return self.headers - def geturl(self): - return self.url + def __init__(self, fp, headers, url): + addbase.__init__(self, fp) + self.headers = headers + self.url = url + def info(self): + return self.headers + def geturl(self): + return self.url # Utility to combine a URL with a base URL to form a new URL def basejoin(base, url): - type, path = splittype(url) - if type: - # if url is complete (i.e., it contains a type), return it - return url - host, path = splithost(path) - type, basepath = splittype(base) # inherit type from base - if host: - # if url contains host, just inherit type - if type: return type + '://' + host + path - else: - # no type inherited, so url must have started with // - # just return it - return url - host, basepath = splithost(basepath) # inherit host - basepath, basetag = splittag(basepath) # remove extraneuous cruft - basepath, basequery = splitquery(basepath) # idem - if path[:1] != '/': - # non-absolute path name - if path[:1] in ('#', '?'): - # path is just a tag or query, attach to basepath - i = len(basepath) - else: - # else replace last component - i = string.rfind(basepath, '/') - if i < 0: - # basepath not absolute - if host: - # host present, make absolute - basepath = '/' - else: - # else keep non-absolute - basepath = '' - else: - # remove last file component - basepath = basepath[:i+1] - # Interpret ../ (important because of symlinks) - while basepath and path[:3] == '../': - path = path[3:] - i = string.rfind(basepath[:-1], '/') - if i > 0: - basepath = basepath[:i+1] - elif i == 0: - basepath = '/' - break - else: - basepath = '' - - path = basepath + path - if type and host: return type + '://' + host + path - elif type: return type + ':' + path - elif host: return '//' + host + path # don't know what this means - else: return path + type, path = splittype(url) + if type: + # if url is complete (i.e., it contains a type), return it + return url + host, path = splithost(path) + type, basepath = splittype(base) # inherit type from base + if host: + # if url contains host, just inherit type + if type: return type + '://' + host + path + else: + # no type inherited, so url must have started with // + # just return it + return url + host, basepath = splithost(basepath) # inherit host + basepath, basetag = splittag(basepath) # remove extraneuous cruft + basepath, basequery = splitquery(basepath) # idem + if path[:1] != '/': + # non-absolute path name + if path[:1] in ('#', '?'): + # path is just a tag or query, attach to basepath + i = len(basepath) + else: + # else replace last component + i = string.rfind(basepath, '/') + if i < 0: + # basepath not absolute + if host: + # host present, make absolute + basepath = '/' + else: + # else keep non-absolute + basepath = '' + else: + # remove last file component + basepath = basepath[:i+1] + # Interpret ../ (important because of symlinks) + while basepath and path[:3] == '../': + path = path[3:] + i = string.rfind(basepath[:-1], '/') + if i > 0: + basepath = basepath[:i+1] + elif i == 0: + basepath = '/' + break + else: + basepath = '' + + path = basepath + path + if type and host: return type + '://' + host + path + elif type: return type + ':' + path + elif host: return '//' + host + path # don't know what this means + else: return path # Utilities to parse URLs (most of these return None for missing parts): @@ -769,68 +750,68 @@ def basejoin(base, url): # quote('abc def') -> 'abc%20def') def unwrap(url): - url = string.strip(url) - if url[:1] == '<' and url[-1:] == '>': - url = string.strip(url[1:-1]) - if url[:4] == 'URL:': url = string.strip(url[4:]) - return url + url = string.strip(url) + if url[:1] == '<' and url[-1:] == '>': + url = string.strip(url[1:-1]) + if url[:4] == 'URL:': url = string.strip(url[4:]) + return url _typeprog = None def splittype(url): - global _typeprog - if _typeprog is None: - import re - _typeprog = re.compile('^([^/:]+):') + global _typeprog + if _typeprog is None: + import re + _typeprog = re.compile('^([^/:]+):') - match = _typeprog.match(url) - if match: - scheme = match.group(1) - return scheme, url[len(scheme) + 1:] - return None, url + match = _typeprog.match(url) + if match: + scheme = match.group(1) + return scheme, url[len(scheme) + 1:] + return None, url _hostprog = None def splithost(url): - global _hostprog - if _hostprog is None: - import re - _hostprog = re.compile('^//([^/]+)(.*)$') + global _hostprog + if _hostprog is None: + import re + _hostprog = re.compile('^//([^/]+)(.*)$') - match = _hostprog.match(url) - if match: return match.group(1, 2) - return None, url + match = _hostprog.match(url) + if match: return match.group(1, 2) + return None, url _userprog = None def splituser(host): - global _userprog - if _userprog is None: - import re - _userprog = re.compile('^([^@]*)@(.*)$') + global _userprog + if _userprog is None: + import re + _userprog = re.compile('^([^@]*)@(.*)$') - match = _userprog.match(host) - if match: return match.group(1, 2) - return None, host + match = _userprog.match(host) + if match: return match.group(1, 2) + return None, host _passwdprog = None def splitpasswd(user): - global _passwdprog - if _passwdprog is None: - import re - _passwdprog = re.compile('^([^:]*):(.*)$') + global _passwdprog + if _passwdprog is None: + import re + _passwdprog = re.compile('^([^:]*):(.*)$') - match = _passwdprog.match(user) - if match: return match.group(1, 2) - return user, None + match = _passwdprog.match(user) + if match: return match.group(1, 2) + return user, None _portprog = None def splitport(host): - global _portprog - if _portprog is None: - import re - _portprog = re.compile('^(.*):([0-9]+)$') + global _portprog + if _portprog is None: + import re + _portprog = re.compile('^(.*):([0-9]+)$') - match = _portprog.match(host) - if match: return match.group(1, 2) - return host, None + match = _portprog.match(host) + if match: return match.group(1, 2) + return host, None # Split host and port, returning numeric port. # Return given default port if no ':' found; defaults to -1. @@ -838,183 +819,183 @@ def splitport(host): # Return None if ':' but not a valid number. _nportprog = None def splitnport(host, defport=-1): - global _nportprog - if _nportprog is None: - import re - _nportprog = re.compile('^(.*):(.*)$') - - match = _nportprog.match(host) - if match: - host, port = match.group(1, 2) - try: - if not port: raise string.atoi_error, "no digits" - nport = string.atoi(port) - except string.atoi_error: - nport = None - return host, nport - return host, defport + global _nportprog + if _nportprog is None: + import re + _nportprog = re.compile('^(.*):(.*)$') + + match = _nportprog.match(host) + if match: + host, port = match.group(1, 2) + try: + if not port: raise string.atoi_error, "no digits" + nport = string.atoi(port) + except string.atoi_error: + nport = None + return host, nport + return host, defport _queryprog = None def splitquery(url): - global _queryprog - if _queryprog is None: - import re - _queryprog = re.compile('^(.*)\?([^?]*)$') + global _queryprog + if _queryprog is None: + import re + _queryprog = re.compile('^(.*)\?([^?]*)$') - match = _queryprog.match(url) - if match: return match.group(1, 2) - return url, None + match = _queryprog.match(url) + if match: return match.group(1, 2) + return url, None _tagprog = None def splittag(url): - global _tagprog - if _tagprog is None: - import re - _tagprog = re.compile('^(.*)#([^#]*)$') + global _tagprog + if _tagprog is None: + import re + _tagprog = re.compile('^(.*)#([^#]*)$') - match = _tagprog.match(url) - if match: return match.group(1, 2) - return url, None + match = _tagprog.match(url) + if match: return match.group(1, 2) + return url, None def splitattr(url): - words = string.splitfields(url, ';') - return words[0], words[1:] + words = string.splitfields(url, ';') + return words[0], words[1:] _valueprog = None def splitvalue(attr): - global _valueprog - if _valueprog is None: - import re - _valueprog = re.compile('^([^=]*)=(.*)$') + global _valueprog + if _valueprog is None: + import re + _valueprog = re.compile('^([^=]*)=(.*)$') - match = _valueprog.match(attr) - if match: return match.group(1, 2) - return attr, None + match = _valueprog.match(attr) + if match: return match.group(1, 2) + return attr, None def splitgophertype(selector): - if selector[:1] == '/' and selector[1:2]: - return selector[1], selector[2:] - return None, selector + if selector[:1] == '/' and selector[1:2]: + return selector[1], selector[2:] + return None, selector def unquote(s): - mychr = chr - myatoi = string.atoi - list = string.split(s, '%') - res = [list[0]] - myappend = res.append - del list[0] - for item in list: - if item[1:2]: - try: - myappend(mychr(myatoi(item[:2], 16)) - + item[2:]) - except: - myappend('%' + item) - else: - myappend('%' + item) - return string.join(res, "") + mychr = chr + myatoi = string.atoi + list = string.split(s, '%') + res = [list[0]] + myappend = res.append + del list[0] + for item in list: + if item[1:2]: + try: + myappend(mychr(myatoi(item[:2], 16)) + + item[2:]) + except: + myappend('%' + item) + else: + myappend('%' + item) + return string.join(res, "") def unquote_plus(s): - if '+' in s: - # replace '+' with ' ' - s = string.join(string.split(s, '+'), ' ') - return unquote(s) + if '+' in s: + # replace '+' with ' ' + s = string.join(string.split(s, '+'), ' ') + return unquote(s) always_safe = string.letters + string.digits + '_,.-' def quote(s, safe = '/'): - safe = always_safe + safe - res = list(s) - for i in range(len(res)): - c = res[i] - if c not in safe: - res[i] = '%%%02x' % ord(c) - return string.joinfields(res, '') + safe = always_safe + safe + res = list(s) + for i in range(len(res)): + c = res[i] + if c not in safe: + res[i] = '%%%02x' % ord(c) + return string.joinfields(res, '') def quote_plus(s, safe = '/'): - if ' ' in s: - # replace ' ' with '+' - l = string.split(s, ' ') - for i in range(len(l)): - l[i] = quote(l[i], safe) - return string.join(l, '+') - else: - return quote(s, safe) + if ' ' in s: + # replace ' ' with '+' + l = string.split(s, ' ') + for i in range(len(l)): + l[i] = quote(l[i], safe) + return string.join(l, '+') + else: + return quote(s, safe) def urlencode(dict): - l = [] - for k, v in dict.items(): - k = quote_plus(str(k)) - v = quote_plus(str(v)) - l.append(k + '=' + v) - return string.join(l, '&') + l = [] + for k, v in dict.items(): + k = quote_plus(str(k)) + v = quote_plus(str(v)) + l.append(k + '=' + v) + return string.join(l, '&') # Proxy handling if os.name == 'mac': - def getproxies(): - """Return a dictionary of scheme -> proxy server URL mappings. - - By convention the mac uses Internet Config to store - proxies. An HTTP proxy, for instance, is stored under - the HttpProxy key. - - """ - try: - import ic - except ImportError: - return {} - - try: - config = ic.IC() - except ic.error: - return {} - proxies = {} - # HTTP: - if config.has_key('UseHTTPProxy') and config['UseHTTPProxy']: - try: - value = config['HTTPProxyHost'] - except ic.error: - pass - else: - proxies['http'] = 'http://%s' % value - # FTP: XXXX To be done. - # Gopher: XXXX To be done. - return proxies - + def getproxies(): + """Return a dictionary of scheme -> proxy server URL mappings. + + By convention the mac uses Internet Config to store + proxies. An HTTP proxy, for instance, is stored under + the HttpProxy key. + + """ + try: + import ic + except ImportError: + return {} + + try: + config = ic.IC() + except ic.error: + return {} + proxies = {} + # HTTP: + if config.has_key('UseHTTPProxy') and config['UseHTTPProxy']: + try: + value = config['HTTPProxyHost'] + except ic.error: + pass + else: + proxies['http'] = 'http://%s' % value + # FTP: XXXX To be done. + # Gopher: XXXX To be done. + return proxies + else: - def getproxies(): - """Return a dictionary of scheme -> proxy server URL mappings. - - Scan the environment for variables named _proxy; - this seems to be the standard convention. If you need a - different way, you can pass a proxies dictionary to the - [Fancy]URLopener constructor. - - """ - proxies = {} - for name, value in os.environ.items(): - name = string.lower(name) - if value and name[-6:] == '_proxy': - proxies[name[:-6]] = value - return proxies + def getproxies(): + """Return a dictionary of scheme -> proxy server URL mappings. + + Scan the environment for variables named _proxy; + this seems to be the standard convention. If you need a + different way, you can pass a proxies dictionary to the + [Fancy]URLopener constructor. + + """ + proxies = {} + for name, value in os.environ.items(): + name = string.lower(name) + if value and name[-6:] == '_proxy': + proxies[name[:-6]] = value + return proxies # Test and time quote() and unquote() def test1(): - import time - s = '' - for i in range(256): s = s + chr(i) - s = s*4 - t0 = time.time() - qs = quote(s) - uqs = unquote(qs) - t1 = time.time() - if uqs != s: - print 'Wrong!' - print `s` - print `qs` - print `uqs` - print round(t1 - t0, 3), 'sec' + import time + s = '' + for i in range(256): s = s + chr(i) + s = s*4 + t0 = time.time() + qs = quote(s) + uqs = unquote(qs) + t1 = time.time() + if uqs != s: + print 'Wrong!' + print `s` + print `qs` + print `uqs` + print round(t1 - t0, 3), 'sec' def reporthook(blocknum, blocksize, totalsize): @@ -1023,63 +1004,63 @@ def reporthook(blocknum, blocksize, totalsize): # Test program def test(args=[]): - if not args: - args = [ - '/etc/passwd', - 'file:/etc/passwd', - 'file://localhost/etc/passwd', - 'ftp://ftp.python.org/etc/passwd', -## 'gopher://gopher.micro.umn.edu/1/', - 'http://www.python.org/index.html', - ] - try: - for url in args: - print '-'*10, url, '-'*10 - fn, h = urlretrieve(url, None, reporthook) - print fn, h - if h: - print '======' - for k in h.keys(): print k + ':', h[k] - print '======' - fp = open(fn, 'rb') - data = fp.read() - del fp - if '\r' in data: - table = string.maketrans("", "") - data = string.translate(data, table, "\r") - print data - fn, h = None, None - print '-'*40 - finally: - urlcleanup() + if not args: + args = [ + '/etc/passwd', + 'file:/etc/passwd', + 'file://localhost/etc/passwd', + 'ftp://ftp.python.org/etc/passwd', +## 'gopher://gopher.micro.umn.edu/1/', + 'http://www.python.org/index.html', + ] + try: + for url in args: + print '-'*10, url, '-'*10 + fn, h = urlretrieve(url, None, reporthook) + print fn, h + if h: + print '======' + for k in h.keys(): print k + ':', h[k] + print '======' + fp = open(fn, 'rb') + data = fp.read() + del fp + if '\r' in data: + table = string.maketrans("", "") + data = string.translate(data, table, "\r") + print data + fn, h = None, None + print '-'*40 + finally: + urlcleanup() def main(): - import getopt, sys - try: - opts, args = getopt.getopt(sys.argv[1:], "th") - except getopt.error, msg: - print msg - print "Use -h for help" - return - t = 0 - for o, a in opts: - if o == '-t': - t = t + 1 - if o == '-h': - print "Usage: python urllib.py [-t] [url ...]" - print "-t runs self-test;", - print "otherwise, contents of urls are printed" - return - if t: - if t > 1: - test1() - test(args) - else: - if not args: - print "Use -h for help" - for url in args: - print urlopen(url).read(), + import getopt, sys + try: + opts, args = getopt.getopt(sys.argv[1:], "th") + except getopt.error, msg: + print msg + print "Use -h for help" + return + t = 0 + for o, a in opts: + if o == '-t': + t = t + 1 + if o == '-h': + print "Usage: python urllib.py [-t] [url ...]" + print "-t runs self-test;", + print "otherwise, contents of urls are printed" + return + if t: + if t > 1: + test1() + test(args) + else: + if not args: + print "Use -h for help" + for url in args: + print urlopen(url).read(), # Run test program when run as a script if __name__ == '__main__': - main() + main() -- cgit v0.12