| 1 | n/a | """Guess the MIME type of a file. |
|---|
| 2 | n/a | |
|---|
| 3 | n/a | This module defines two useful functions: |
|---|
| 4 | n/a | |
|---|
| 5 | n/a | guess_type(url, strict=True) -- guess the MIME type and encoding of a URL. |
|---|
| 6 | n/a | |
|---|
| 7 | n/a | guess_extension(type, strict=True) -- guess the extension for a given MIME type. |
|---|
| 8 | n/a | |
|---|
| 9 | n/a | It also contains the following, for tuning the behavior: |
|---|
| 10 | n/a | |
|---|
| 11 | n/a | Data: |
|---|
| 12 | n/a | |
|---|
| 13 | n/a | knownfiles -- list of files to parse |
|---|
| 14 | n/a | inited -- flag set when init() has been called |
|---|
| 15 | n/a | suffix_map -- dictionary mapping suffixes to suffixes |
|---|
| 16 | n/a | encodings_map -- dictionary mapping suffixes to encodings |
|---|
| 17 | n/a | types_map -- dictionary mapping suffixes to types |
|---|
| 18 | n/a | |
|---|
| 19 | n/a | Functions: |
|---|
| 20 | n/a | |
|---|
| 21 | n/a | init([files]) -- parse a list of files, default knownfiles (on Windows, the |
|---|
| 22 | n/a | default values are taken from the registry) |
|---|
| 23 | n/a | read_mime_types(file) -- parse one file, return a dictionary or None |
|---|
| 24 | n/a | """ |
|---|
| 25 | n/a | |
|---|
| 26 | n/a | import os |
|---|
| 27 | n/a | import sys |
|---|
| 28 | n/a | import posixpath |
|---|
| 29 | n/a | import urllib.parse |
|---|
| 30 | n/a | try: |
|---|
| 31 | n/a | import winreg as _winreg |
|---|
| 32 | n/a | except ImportError: |
|---|
| 33 | n/a | _winreg = None |
|---|
| 34 | n/a | |
|---|
| 35 | n/a | __all__ = [ |
|---|
| 36 | n/a | "knownfiles", "inited", "MimeTypes", |
|---|
| 37 | n/a | "guess_type", "guess_all_extensions", "guess_extension", |
|---|
| 38 | n/a | "add_type", "init", "read_mime_types", |
|---|
| 39 | n/a | "suffix_map", "encodings_map", "types_map", "common_types" |
|---|
| 40 | n/a | ] |
|---|
| 41 | n/a | |
|---|
| 42 | n/a | knownfiles = [ |
|---|
| 43 | n/a | "/etc/mime.types", |
|---|
| 44 | n/a | "/etc/httpd/mime.types", # Mac OS X |
|---|
| 45 | n/a | "/etc/httpd/conf/mime.types", # Apache |
|---|
| 46 | n/a | "/etc/apache/mime.types", # Apache 1 |
|---|
| 47 | n/a | "/etc/apache2/mime.types", # Apache 2 |
|---|
| 48 | n/a | "/usr/local/etc/httpd/conf/mime.types", |
|---|
| 49 | n/a | "/usr/local/lib/netscape/mime.types", |
|---|
| 50 | n/a | "/usr/local/etc/httpd/conf/mime.types", # Apache 1.2 |
|---|
| 51 | n/a | "/usr/local/etc/mime.types", # Apache 1.3 |
|---|
| 52 | n/a | ] |
|---|
| 53 | n/a | |
|---|
| 54 | n/a | inited = False |
|---|
| 55 | n/a | _db = None |
|---|
| 56 | n/a | |
|---|
| 57 | n/a | |
|---|
| 58 | n/a | class MimeTypes: |
|---|
| 59 | n/a | """MIME-types datastore. |
|---|
| 60 | n/a | |
|---|
| 61 | n/a | This datastore can handle information from mime.types-style files |
|---|
| 62 | n/a | and supports basic determination of MIME type from a filename or |
|---|
| 63 | n/a | URL, and can guess a reasonable extension given a MIME type. |
|---|
| 64 | n/a | """ |
|---|
| 65 | n/a | |
|---|
| 66 | n/a | def __init__(self, filenames=(), strict=True): |
|---|
| 67 | n/a | if not inited: |
|---|
| 68 | n/a | init() |
|---|
| 69 | n/a | self.encodings_map = encodings_map.copy() |
|---|
| 70 | n/a | self.suffix_map = suffix_map.copy() |
|---|
| 71 | n/a | self.types_map = ({}, {}) # dict for (non-strict, strict) |
|---|
| 72 | n/a | self.types_map_inv = ({}, {}) |
|---|
| 73 | n/a | for (ext, type) in types_map.items(): |
|---|
| 74 | n/a | self.add_type(type, ext, True) |
|---|
| 75 | n/a | for (ext, type) in common_types.items(): |
|---|
| 76 | n/a | self.add_type(type, ext, False) |
|---|
| 77 | n/a | for name in filenames: |
|---|
| 78 | n/a | self.read(name, strict) |
|---|
| 79 | n/a | |
|---|
| 80 | n/a | def add_type(self, type, ext, strict=True): |
|---|
| 81 | n/a | """Add a mapping between a type and an extension. |
|---|
| 82 | n/a | |
|---|
| 83 | n/a | When the extension is already known, the new |
|---|
| 84 | n/a | type will replace the old one. When the type |
|---|
| 85 | n/a | is already known the extension will be added |
|---|
| 86 | n/a | to the list of known extensions. |
|---|
| 87 | n/a | |
|---|
| 88 | n/a | If strict is true, information will be added to |
|---|
| 89 | n/a | list of standard types, else to the list of non-standard |
|---|
| 90 | n/a | types. |
|---|
| 91 | n/a | """ |
|---|
| 92 | n/a | self.types_map[strict][ext] = type |
|---|
| 93 | n/a | exts = self.types_map_inv[strict].setdefault(type, []) |
|---|
| 94 | n/a | if ext not in exts: |
|---|
| 95 | n/a | exts.append(ext) |
|---|
| 96 | n/a | |
|---|
| 97 | n/a | def guess_type(self, url, strict=True): |
|---|
| 98 | n/a | """Guess the type of a file based on its URL. |
|---|
| 99 | n/a | |
|---|
| 100 | n/a | Return value is a tuple (type, encoding) where type is None if |
|---|
| 101 | n/a | the type can't be guessed (no or unknown suffix) or a string |
|---|
| 102 | n/a | of the form type/subtype, usable for a MIME Content-type |
|---|
| 103 | n/a | header; and encoding is None for no encoding or the name of |
|---|
| 104 | n/a | the program used to encode (e.g. compress or gzip). The |
|---|
| 105 | n/a | mappings are table driven. Encoding suffixes are case |
|---|
| 106 | n/a | sensitive; type suffixes are first tried case sensitive, then |
|---|
| 107 | n/a | case insensitive. |
|---|
| 108 | n/a | |
|---|
| 109 | n/a | The suffixes .tgz, .taz and .tz (case sensitive!) are all |
|---|
| 110 | n/a | mapped to '.tar.gz'. (This is table-driven too, using the |
|---|
| 111 | n/a | dictionary suffix_map.) |
|---|
| 112 | n/a | |
|---|
| 113 | n/a | Optional `strict' argument when False adds a bunch of commonly found, |
|---|
| 114 | n/a | but non-standard types. |
|---|
| 115 | n/a | """ |
|---|
| 116 | n/a | scheme, url = urllib.parse.splittype(url) |
|---|
| 117 | n/a | if scheme == 'data': |
|---|
| 118 | n/a | # syntax of data URLs: |
|---|
| 119 | n/a | # dataurl := "data:" [ mediatype ] [ ";base64" ] "," data |
|---|
| 120 | n/a | # mediatype := [ type "/" subtype ] *( ";" parameter ) |
|---|
| 121 | n/a | # data := *urlchar |
|---|
| 122 | n/a | # parameter := attribute "=" value |
|---|
| 123 | n/a | # type/subtype defaults to "text/plain" |
|---|
| 124 | n/a | comma = url.find(',') |
|---|
| 125 | n/a | if comma < 0: |
|---|
| 126 | n/a | # bad data URL |
|---|
| 127 | n/a | return None, None |
|---|
| 128 | n/a | semi = url.find(';', 0, comma) |
|---|
| 129 | n/a | if semi >= 0: |
|---|
| 130 | n/a | type = url[:semi] |
|---|
| 131 | n/a | else: |
|---|
| 132 | n/a | type = url[:comma] |
|---|
| 133 | n/a | if '=' in type or '/' not in type: |
|---|
| 134 | n/a | type = 'text/plain' |
|---|
| 135 | n/a | return type, None # never compressed, so encoding is None |
|---|
| 136 | n/a | base, ext = posixpath.splitext(url) |
|---|
| 137 | n/a | while ext in self.suffix_map: |
|---|
| 138 | n/a | base, ext = posixpath.splitext(base + self.suffix_map[ext]) |
|---|
| 139 | n/a | if ext in self.encodings_map: |
|---|
| 140 | n/a | encoding = self.encodings_map[ext] |
|---|
| 141 | n/a | base, ext = posixpath.splitext(base) |
|---|
| 142 | n/a | else: |
|---|
| 143 | n/a | encoding = None |
|---|
| 144 | n/a | types_map = self.types_map[True] |
|---|
| 145 | n/a | if ext in types_map: |
|---|
| 146 | n/a | return types_map[ext], encoding |
|---|
| 147 | n/a | elif ext.lower() in types_map: |
|---|
| 148 | n/a | return types_map[ext.lower()], encoding |
|---|
| 149 | n/a | elif strict: |
|---|
| 150 | n/a | return None, encoding |
|---|
| 151 | n/a | types_map = self.types_map[False] |
|---|
| 152 | n/a | if ext in types_map: |
|---|
| 153 | n/a | return types_map[ext], encoding |
|---|
| 154 | n/a | elif ext.lower() in types_map: |
|---|
| 155 | n/a | return types_map[ext.lower()], encoding |
|---|
| 156 | n/a | else: |
|---|
| 157 | n/a | return None, encoding |
|---|
| 158 | n/a | |
|---|
| 159 | n/a | def guess_all_extensions(self, type, strict=True): |
|---|
| 160 | n/a | """Guess the extensions for a file based on its MIME type. |
|---|
| 161 | n/a | |
|---|
| 162 | n/a | Return value is a list of strings giving the possible filename |
|---|
| 163 | n/a | extensions, including the leading dot ('.'). The extension is not |
|---|
| 164 | n/a | guaranteed to have been associated with any particular data stream, |
|---|
| 165 | n/a | but would be mapped to the MIME type `type' by guess_type(). |
|---|
| 166 | n/a | |
|---|
| 167 | n/a | Optional `strict' argument when false adds a bunch of commonly found, |
|---|
| 168 | n/a | but non-standard types. |
|---|
| 169 | n/a | """ |
|---|
| 170 | n/a | type = type.lower() |
|---|
| 171 | n/a | extensions = self.types_map_inv[True].get(type, []) |
|---|
| 172 | n/a | if not strict: |
|---|
| 173 | n/a | for ext in self.types_map_inv[False].get(type, []): |
|---|
| 174 | n/a | if ext not in extensions: |
|---|
| 175 | n/a | extensions.append(ext) |
|---|
| 176 | n/a | return extensions |
|---|
| 177 | n/a | |
|---|
| 178 | n/a | def guess_extension(self, type, strict=True): |
|---|
| 179 | n/a | """Guess the extension for a file based on its MIME type. |
|---|
| 180 | n/a | |
|---|
| 181 | n/a | Return value is a string giving a filename extension, |
|---|
| 182 | n/a | including the leading dot ('.'). The extension is not |
|---|
| 183 | n/a | guaranteed to have been associated with any particular data |
|---|
| 184 | n/a | stream, but would be mapped to the MIME type `type' by |
|---|
| 185 | n/a | guess_type(). If no extension can be guessed for `type', None |
|---|
| 186 | n/a | is returned. |
|---|
| 187 | n/a | |
|---|
| 188 | n/a | Optional `strict' argument when false adds a bunch of commonly found, |
|---|
| 189 | n/a | but non-standard types. |
|---|
| 190 | n/a | """ |
|---|
| 191 | n/a | extensions = self.guess_all_extensions(type, strict) |
|---|
| 192 | n/a | if not extensions: |
|---|
| 193 | n/a | return None |
|---|
| 194 | n/a | return extensions[0] |
|---|
| 195 | n/a | |
|---|
| 196 | n/a | def read(self, filename, strict=True): |
|---|
| 197 | n/a | """ |
|---|
| 198 | n/a | Read a single mime.types-format file, specified by pathname. |
|---|
| 199 | n/a | |
|---|
| 200 | n/a | If strict is true, information will be added to |
|---|
| 201 | n/a | list of standard types, else to the list of non-standard |
|---|
| 202 | n/a | types. |
|---|
| 203 | n/a | """ |
|---|
| 204 | n/a | with open(filename, encoding='utf-8') as fp: |
|---|
| 205 | n/a | self.readfp(fp, strict) |
|---|
| 206 | n/a | |
|---|
| 207 | n/a | def readfp(self, fp, strict=True): |
|---|
| 208 | n/a | """ |
|---|
| 209 | n/a | Read a single mime.types-format file. |
|---|
| 210 | n/a | |
|---|
| 211 | n/a | If strict is true, information will be added to |
|---|
| 212 | n/a | list of standard types, else to the list of non-standard |
|---|
| 213 | n/a | types. |
|---|
| 214 | n/a | """ |
|---|
| 215 | n/a | while 1: |
|---|
| 216 | n/a | line = fp.readline() |
|---|
| 217 | n/a | if not line: |
|---|
| 218 | n/a | break |
|---|
| 219 | n/a | words = line.split() |
|---|
| 220 | n/a | for i in range(len(words)): |
|---|
| 221 | n/a | if words[i][0] == '#': |
|---|
| 222 | n/a | del words[i:] |
|---|
| 223 | n/a | break |
|---|
| 224 | n/a | if not words: |
|---|
| 225 | n/a | continue |
|---|
| 226 | n/a | type, suffixes = words[0], words[1:] |
|---|
| 227 | n/a | for suff in suffixes: |
|---|
| 228 | n/a | self.add_type(type, '.' + suff, strict) |
|---|
| 229 | n/a | |
|---|
| 230 | n/a | def read_windows_registry(self, strict=True): |
|---|
| 231 | n/a | """ |
|---|
| 232 | n/a | Load the MIME types database from Windows registry. |
|---|
| 233 | n/a | |
|---|
| 234 | n/a | If strict is true, information will be added to |
|---|
| 235 | n/a | list of standard types, else to the list of non-standard |
|---|
| 236 | n/a | types. |
|---|
| 237 | n/a | """ |
|---|
| 238 | n/a | |
|---|
| 239 | n/a | # Windows only |
|---|
| 240 | n/a | if not _winreg: |
|---|
| 241 | n/a | return |
|---|
| 242 | n/a | |
|---|
| 243 | n/a | def enum_types(mimedb): |
|---|
| 244 | n/a | i = 0 |
|---|
| 245 | n/a | while True: |
|---|
| 246 | n/a | try: |
|---|
| 247 | n/a | ctype = _winreg.EnumKey(mimedb, i) |
|---|
| 248 | n/a | except EnvironmentError: |
|---|
| 249 | n/a | break |
|---|
| 250 | n/a | else: |
|---|
| 251 | n/a | if '\0' not in ctype: |
|---|
| 252 | n/a | yield ctype |
|---|
| 253 | n/a | i += 1 |
|---|
| 254 | n/a | |
|---|
| 255 | n/a | with _winreg.OpenKey(_winreg.HKEY_CLASSES_ROOT, '') as hkcr: |
|---|
| 256 | n/a | for subkeyname in enum_types(hkcr): |
|---|
| 257 | n/a | try: |
|---|
| 258 | n/a | with _winreg.OpenKey(hkcr, subkeyname) as subkey: |
|---|
| 259 | n/a | # Only check file extensions |
|---|
| 260 | n/a | if not subkeyname.startswith("."): |
|---|
| 261 | n/a | continue |
|---|
| 262 | n/a | # raises EnvironmentError if no 'Content Type' value |
|---|
| 263 | n/a | mimetype, datatype = _winreg.QueryValueEx( |
|---|
| 264 | n/a | subkey, 'Content Type') |
|---|
| 265 | n/a | if datatype != _winreg.REG_SZ: |
|---|
| 266 | n/a | continue |
|---|
| 267 | n/a | self.add_type(mimetype, subkeyname, strict) |
|---|
| 268 | n/a | except EnvironmentError: |
|---|
| 269 | n/a | continue |
|---|
| 270 | n/a | |
|---|
| 271 | n/a | def guess_type(url, strict=True): |
|---|
| 272 | n/a | """Guess the type of a file based on its URL. |
|---|
| 273 | n/a | |
|---|
| 274 | n/a | Return value is a tuple (type, encoding) where type is None if the |
|---|
| 275 | n/a | type can't be guessed (no or unknown suffix) or a string of the |
|---|
| 276 | n/a | form type/subtype, usable for a MIME Content-type header; and |
|---|
| 277 | n/a | encoding is None for no encoding or the name of the program used |
|---|
| 278 | n/a | to encode (e.g. compress or gzip). The mappings are table |
|---|
| 279 | n/a | driven. Encoding suffixes are case sensitive; type suffixes are |
|---|
| 280 | n/a | first tried case sensitive, then case insensitive. |
|---|
| 281 | n/a | |
|---|
| 282 | n/a | The suffixes .tgz, .taz and .tz (case sensitive!) are all mapped |
|---|
| 283 | n/a | to ".tar.gz". (This is table-driven too, using the dictionary |
|---|
| 284 | n/a | suffix_map). |
|---|
| 285 | n/a | |
|---|
| 286 | n/a | Optional `strict' argument when false adds a bunch of commonly found, but |
|---|
| 287 | n/a | non-standard types. |
|---|
| 288 | n/a | """ |
|---|
| 289 | n/a | if _db is None: |
|---|
| 290 | n/a | init() |
|---|
| 291 | n/a | return _db.guess_type(url, strict) |
|---|
| 292 | n/a | |
|---|
| 293 | n/a | |
|---|
| 294 | n/a | def guess_all_extensions(type, strict=True): |
|---|
| 295 | n/a | """Guess the extensions for a file based on its MIME type. |
|---|
| 296 | n/a | |
|---|
| 297 | n/a | Return value is a list of strings giving the possible filename |
|---|
| 298 | n/a | extensions, including the leading dot ('.'). The extension is not |
|---|
| 299 | n/a | guaranteed to have been associated with any particular data |
|---|
| 300 | n/a | stream, but would be mapped to the MIME type `type' by |
|---|
| 301 | n/a | guess_type(). If no extension can be guessed for `type', None |
|---|
| 302 | n/a | is returned. |
|---|
| 303 | n/a | |
|---|
| 304 | n/a | Optional `strict' argument when false adds a bunch of commonly found, |
|---|
| 305 | n/a | but non-standard types. |
|---|
| 306 | n/a | """ |
|---|
| 307 | n/a | if _db is None: |
|---|
| 308 | n/a | init() |
|---|
| 309 | n/a | return _db.guess_all_extensions(type, strict) |
|---|
| 310 | n/a | |
|---|
| 311 | n/a | def guess_extension(type, strict=True): |
|---|
| 312 | n/a | """Guess the extension for a file based on its MIME type. |
|---|
| 313 | n/a | |
|---|
| 314 | n/a | Return value is a string giving a filename extension, including the |
|---|
| 315 | n/a | leading dot ('.'). The extension is not guaranteed to have been |
|---|
| 316 | n/a | associated with any particular data stream, but would be mapped to the |
|---|
| 317 | n/a | MIME type `type' by guess_type(). If no extension can be guessed for |
|---|
| 318 | n/a | `type', None is returned. |
|---|
| 319 | n/a | |
|---|
| 320 | n/a | Optional `strict' argument when false adds a bunch of commonly found, |
|---|
| 321 | n/a | but non-standard types. |
|---|
| 322 | n/a | """ |
|---|
| 323 | n/a | if _db is None: |
|---|
| 324 | n/a | init() |
|---|
| 325 | n/a | return _db.guess_extension(type, strict) |
|---|
| 326 | n/a | |
|---|
| 327 | n/a | def add_type(type, ext, strict=True): |
|---|
| 328 | n/a | """Add a mapping between a type and an extension. |
|---|
| 329 | n/a | |
|---|
| 330 | n/a | When the extension is already known, the new |
|---|
| 331 | n/a | type will replace the old one. When the type |
|---|
| 332 | n/a | is already known the extension will be added |
|---|
| 333 | n/a | to the list of known extensions. |
|---|
| 334 | n/a | |
|---|
| 335 | n/a | If strict is true, information will be added to |
|---|
| 336 | n/a | list of standard types, else to the list of non-standard |
|---|
| 337 | n/a | types. |
|---|
| 338 | n/a | """ |
|---|
| 339 | n/a | if _db is None: |
|---|
| 340 | n/a | init() |
|---|
| 341 | n/a | return _db.add_type(type, ext, strict) |
|---|
| 342 | n/a | |
|---|
| 343 | n/a | |
|---|
| 344 | n/a | def init(files=None): |
|---|
| 345 | n/a | global suffix_map, types_map, encodings_map, common_types |
|---|
| 346 | n/a | global inited, _db |
|---|
| 347 | n/a | inited = True # so that MimeTypes.__init__() doesn't call us again |
|---|
| 348 | n/a | db = MimeTypes() |
|---|
| 349 | n/a | if files is None: |
|---|
| 350 | n/a | if _winreg: |
|---|
| 351 | n/a | db.read_windows_registry() |
|---|
| 352 | n/a | files = knownfiles |
|---|
| 353 | n/a | for file in files: |
|---|
| 354 | n/a | if os.path.isfile(file): |
|---|
| 355 | n/a | db.read(file) |
|---|
| 356 | n/a | encodings_map = db.encodings_map |
|---|
| 357 | n/a | suffix_map = db.suffix_map |
|---|
| 358 | n/a | types_map = db.types_map[True] |
|---|
| 359 | n/a | common_types = db.types_map[False] |
|---|
| 360 | n/a | # Make the DB a global variable now that it is fully initialized |
|---|
| 361 | n/a | _db = db |
|---|
| 362 | n/a | |
|---|
| 363 | n/a | |
|---|
| 364 | n/a | def read_mime_types(file): |
|---|
| 365 | n/a | try: |
|---|
| 366 | n/a | f = open(file) |
|---|
| 367 | n/a | except OSError: |
|---|
| 368 | n/a | return None |
|---|
| 369 | n/a | with f: |
|---|
| 370 | n/a | db = MimeTypes() |
|---|
| 371 | n/a | db.readfp(f, True) |
|---|
| 372 | n/a | return db.types_map[True] |
|---|
| 373 | n/a | |
|---|
| 374 | n/a | |
|---|
| 375 | n/a | def _default_mime_types(): |
|---|
| 376 | n/a | global suffix_map |
|---|
| 377 | n/a | global encodings_map |
|---|
| 378 | n/a | global types_map |
|---|
| 379 | n/a | global common_types |
|---|
| 380 | n/a | |
|---|
| 381 | n/a | suffix_map = { |
|---|
| 382 | n/a | '.svgz': '.svg.gz', |
|---|
| 383 | n/a | '.tgz': '.tar.gz', |
|---|
| 384 | n/a | '.taz': '.tar.gz', |
|---|
| 385 | n/a | '.tz': '.tar.gz', |
|---|
| 386 | n/a | '.tbz2': '.tar.bz2', |
|---|
| 387 | n/a | '.txz': '.tar.xz', |
|---|
| 388 | n/a | } |
|---|
| 389 | n/a | |
|---|
| 390 | n/a | encodings_map = { |
|---|
| 391 | n/a | '.gz': 'gzip', |
|---|
| 392 | n/a | '.Z': 'compress', |
|---|
| 393 | n/a | '.bz2': 'bzip2', |
|---|
| 394 | n/a | '.xz': 'xz', |
|---|
| 395 | n/a | } |
|---|
| 396 | n/a | |
|---|
| 397 | n/a | # Before adding new types, make sure they are either registered with IANA, |
|---|
| 398 | n/a | # at http://www.iana.org/assignments/media-types |
|---|
| 399 | n/a | # or extensions, i.e. using the x- prefix |
|---|
| 400 | n/a | |
|---|
| 401 | n/a | # If you add to these, please keep them sorted! |
|---|
| 402 | n/a | types_map = { |
|---|
| 403 | n/a | '.a' : 'application/octet-stream', |
|---|
| 404 | n/a | '.ai' : 'application/postscript', |
|---|
| 405 | n/a | '.aif' : 'audio/x-aiff', |
|---|
| 406 | n/a | '.aifc' : 'audio/x-aiff', |
|---|
| 407 | n/a | '.aiff' : 'audio/x-aiff', |
|---|
| 408 | n/a | '.au' : 'audio/basic', |
|---|
| 409 | n/a | '.avi' : 'video/x-msvideo', |
|---|
| 410 | n/a | '.bat' : 'text/plain', |
|---|
| 411 | n/a | '.bcpio' : 'application/x-bcpio', |
|---|
| 412 | n/a | '.bin' : 'application/octet-stream', |
|---|
| 413 | n/a | '.bmp' : 'image/x-ms-bmp', |
|---|
| 414 | n/a | '.c' : 'text/plain', |
|---|
| 415 | n/a | # Duplicates :( |
|---|
| 416 | n/a | '.cdf' : 'application/x-cdf', |
|---|
| 417 | n/a | '.cdf' : 'application/x-netcdf', |
|---|
| 418 | n/a | '.cpio' : 'application/x-cpio', |
|---|
| 419 | n/a | '.csh' : 'application/x-csh', |
|---|
| 420 | n/a | '.css' : 'text/css', |
|---|
| 421 | n/a | '.csv' : 'text/csv', |
|---|
| 422 | n/a | '.dll' : 'application/octet-stream', |
|---|
| 423 | n/a | '.doc' : 'application/msword', |
|---|
| 424 | n/a | '.dot' : 'application/msword', |
|---|
| 425 | n/a | '.dvi' : 'application/x-dvi', |
|---|
| 426 | n/a | '.eml' : 'message/rfc822', |
|---|
| 427 | n/a | '.eps' : 'application/postscript', |
|---|
| 428 | n/a | '.etx' : 'text/x-setext', |
|---|
| 429 | n/a | '.exe' : 'application/octet-stream', |
|---|
| 430 | n/a | '.gif' : 'image/gif', |
|---|
| 431 | n/a | '.gtar' : 'application/x-gtar', |
|---|
| 432 | n/a | '.h' : 'text/plain', |
|---|
| 433 | n/a | '.hdf' : 'application/x-hdf', |
|---|
| 434 | n/a | '.htm' : 'text/html', |
|---|
| 435 | n/a | '.html' : 'text/html', |
|---|
| 436 | n/a | '.ico' : 'image/vnd.microsoft.icon', |
|---|
| 437 | n/a | '.ief' : 'image/ief', |
|---|
| 438 | n/a | '.jpe' : 'image/jpeg', |
|---|
| 439 | n/a | '.jpeg' : 'image/jpeg', |
|---|
| 440 | n/a | '.jpg' : 'image/jpeg', |
|---|
| 441 | n/a | '.js' : 'application/javascript', |
|---|
| 442 | n/a | '.ksh' : 'text/plain', |
|---|
| 443 | n/a | '.latex' : 'application/x-latex', |
|---|
| 444 | n/a | '.m1v' : 'video/mpeg', |
|---|
| 445 | n/a | '.m3u' : 'application/vnd.apple.mpegurl', |
|---|
| 446 | n/a | '.m3u8' : 'application/vnd.apple.mpegurl', |
|---|
| 447 | n/a | '.man' : 'application/x-troff-man', |
|---|
| 448 | n/a | '.me' : 'application/x-troff-me', |
|---|
| 449 | n/a | '.mht' : 'message/rfc822', |
|---|
| 450 | n/a | '.mhtml' : 'message/rfc822', |
|---|
| 451 | n/a | '.mif' : 'application/x-mif', |
|---|
| 452 | n/a | '.mov' : 'video/quicktime', |
|---|
| 453 | n/a | '.movie' : 'video/x-sgi-movie', |
|---|
| 454 | n/a | '.mp2' : 'audio/mpeg', |
|---|
| 455 | n/a | '.mp3' : 'audio/mpeg', |
|---|
| 456 | n/a | '.mp4' : 'video/mp4', |
|---|
| 457 | n/a | '.mpa' : 'video/mpeg', |
|---|
| 458 | n/a | '.mpe' : 'video/mpeg', |
|---|
| 459 | n/a | '.mpeg' : 'video/mpeg', |
|---|
| 460 | n/a | '.mpg' : 'video/mpeg', |
|---|
| 461 | n/a | '.ms' : 'application/x-troff-ms', |
|---|
| 462 | n/a | '.nc' : 'application/x-netcdf', |
|---|
| 463 | n/a | '.nws' : 'message/rfc822', |
|---|
| 464 | n/a | '.o' : 'application/octet-stream', |
|---|
| 465 | n/a | '.obj' : 'application/octet-stream', |
|---|
| 466 | n/a | '.oda' : 'application/oda', |
|---|
| 467 | n/a | '.p12' : 'application/x-pkcs12', |
|---|
| 468 | n/a | '.p7c' : 'application/pkcs7-mime', |
|---|
| 469 | n/a | '.pbm' : 'image/x-portable-bitmap', |
|---|
| 470 | n/a | '.pdf' : 'application/pdf', |
|---|
| 471 | n/a | '.pfx' : 'application/x-pkcs12', |
|---|
| 472 | n/a | '.pgm' : 'image/x-portable-graymap', |
|---|
| 473 | n/a | '.pl' : 'text/plain', |
|---|
| 474 | n/a | '.png' : 'image/png', |
|---|
| 475 | n/a | '.pnm' : 'image/x-portable-anymap', |
|---|
| 476 | n/a | '.pot' : 'application/vnd.ms-powerpoint', |
|---|
| 477 | n/a | '.ppa' : 'application/vnd.ms-powerpoint', |
|---|
| 478 | n/a | '.ppm' : 'image/x-portable-pixmap', |
|---|
| 479 | n/a | '.pps' : 'application/vnd.ms-powerpoint', |
|---|
| 480 | n/a | '.ppt' : 'application/vnd.ms-powerpoint', |
|---|
| 481 | n/a | '.ps' : 'application/postscript', |
|---|
| 482 | n/a | '.pwz' : 'application/vnd.ms-powerpoint', |
|---|
| 483 | n/a | '.py' : 'text/x-python', |
|---|
| 484 | n/a | '.pyc' : 'application/x-python-code', |
|---|
| 485 | n/a | '.pyo' : 'application/x-python-code', |
|---|
| 486 | n/a | '.qt' : 'video/quicktime', |
|---|
| 487 | n/a | '.ra' : 'audio/x-pn-realaudio', |
|---|
| 488 | n/a | '.ram' : 'application/x-pn-realaudio', |
|---|
| 489 | n/a | '.ras' : 'image/x-cmu-raster', |
|---|
| 490 | n/a | '.rdf' : 'application/xml', |
|---|
| 491 | n/a | '.rgb' : 'image/x-rgb', |
|---|
| 492 | n/a | '.roff' : 'application/x-troff', |
|---|
| 493 | n/a | '.rtx' : 'text/richtext', |
|---|
| 494 | n/a | '.sgm' : 'text/x-sgml', |
|---|
| 495 | n/a | '.sgml' : 'text/x-sgml', |
|---|
| 496 | n/a | '.sh' : 'application/x-sh', |
|---|
| 497 | n/a | '.shar' : 'application/x-shar', |
|---|
| 498 | n/a | '.snd' : 'audio/basic', |
|---|
| 499 | n/a | '.so' : 'application/octet-stream', |
|---|
| 500 | n/a | '.src' : 'application/x-wais-source', |
|---|
| 501 | n/a | '.sv4cpio': 'application/x-sv4cpio', |
|---|
| 502 | n/a | '.sv4crc' : 'application/x-sv4crc', |
|---|
| 503 | n/a | '.svg' : 'image/svg+xml', |
|---|
| 504 | n/a | '.swf' : 'application/x-shockwave-flash', |
|---|
| 505 | n/a | '.t' : 'application/x-troff', |
|---|
| 506 | n/a | '.tar' : 'application/x-tar', |
|---|
| 507 | n/a | '.tcl' : 'application/x-tcl', |
|---|
| 508 | n/a | '.tex' : 'application/x-tex', |
|---|
| 509 | n/a | '.texi' : 'application/x-texinfo', |
|---|
| 510 | n/a | '.texinfo': 'application/x-texinfo', |
|---|
| 511 | n/a | '.tif' : 'image/tiff', |
|---|
| 512 | n/a | '.tiff' : 'image/tiff', |
|---|
| 513 | n/a | '.tr' : 'application/x-troff', |
|---|
| 514 | n/a | '.tsv' : 'text/tab-separated-values', |
|---|
| 515 | n/a | '.txt' : 'text/plain', |
|---|
| 516 | n/a | '.ustar' : 'application/x-ustar', |
|---|
| 517 | n/a | '.vcf' : 'text/x-vcard', |
|---|
| 518 | n/a | '.wav' : 'audio/x-wav', |
|---|
| 519 | n/a | '.webm' : 'video/webm', |
|---|
| 520 | n/a | '.wiz' : 'application/msword', |
|---|
| 521 | n/a | '.wsdl' : 'application/xml', |
|---|
| 522 | n/a | '.xbm' : 'image/x-xbitmap', |
|---|
| 523 | n/a | '.xlb' : 'application/vnd.ms-excel', |
|---|
| 524 | n/a | # Duplicates :( |
|---|
| 525 | n/a | '.xls' : 'application/excel', |
|---|
| 526 | n/a | '.xls' : 'application/vnd.ms-excel', |
|---|
| 527 | n/a | '.xml' : 'text/xml', |
|---|
| 528 | n/a | '.xpdl' : 'application/xml', |
|---|
| 529 | n/a | '.xpm' : 'image/x-xpixmap', |
|---|
| 530 | n/a | '.xsl' : 'application/xml', |
|---|
| 531 | n/a | '.xwd' : 'image/x-xwindowdump', |
|---|
| 532 | n/a | '.zip' : 'application/zip', |
|---|
| 533 | n/a | } |
|---|
| 534 | n/a | |
|---|
| 535 | n/a | # These are non-standard types, commonly found in the wild. They will |
|---|
| 536 | n/a | # only match if strict=0 flag is given to the API methods. |
|---|
| 537 | n/a | |
|---|
| 538 | n/a | # Please sort these too |
|---|
| 539 | n/a | common_types = { |
|---|
| 540 | n/a | '.jpg' : 'image/jpg', |
|---|
| 541 | n/a | '.mid' : 'audio/midi', |
|---|
| 542 | n/a | '.midi': 'audio/midi', |
|---|
| 543 | n/a | '.pct' : 'image/pict', |
|---|
| 544 | n/a | '.pic' : 'image/pict', |
|---|
| 545 | n/a | '.pict': 'image/pict', |
|---|
| 546 | n/a | '.rtf' : 'application/rtf', |
|---|
| 547 | n/a | '.xul' : 'text/xul' |
|---|
| 548 | n/a | } |
|---|
| 549 | n/a | |
|---|
| 550 | n/a | |
|---|
| 551 | n/a | _default_mime_types() |
|---|
| 552 | n/a | |
|---|
| 553 | n/a | |
|---|
| 554 | n/a | if __name__ == '__main__': |
|---|
| 555 | n/a | import getopt |
|---|
| 556 | n/a | |
|---|
| 557 | n/a | USAGE = """\ |
|---|
| 558 | n/a | Usage: mimetypes.py [options] type |
|---|
| 559 | n/a | |
|---|
| 560 | n/a | Options: |
|---|
| 561 | n/a | --help / -h -- print this message and exit |
|---|
| 562 | n/a | --lenient / -l -- additionally search of some common, but non-standard |
|---|
| 563 | n/a | types. |
|---|
| 564 | n/a | --extension / -e -- guess extension instead of type |
|---|
| 565 | n/a | |
|---|
| 566 | n/a | More than one type argument may be given. |
|---|
| 567 | n/a | """ |
|---|
| 568 | n/a | |
|---|
| 569 | n/a | def usage(code, msg=''): |
|---|
| 570 | n/a | print(USAGE) |
|---|
| 571 | n/a | if msg: print(msg) |
|---|
| 572 | n/a | sys.exit(code) |
|---|
| 573 | n/a | |
|---|
| 574 | n/a | try: |
|---|
| 575 | n/a | opts, args = getopt.getopt(sys.argv[1:], 'hle', |
|---|
| 576 | n/a | ['help', 'lenient', 'extension']) |
|---|
| 577 | n/a | except getopt.error as msg: |
|---|
| 578 | n/a | usage(1, msg) |
|---|
| 579 | n/a | |
|---|
| 580 | n/a | strict = 1 |
|---|
| 581 | n/a | extension = 0 |
|---|
| 582 | n/a | for opt, arg in opts: |
|---|
| 583 | n/a | if opt in ('-h', '--help'): |
|---|
| 584 | n/a | usage(0) |
|---|
| 585 | n/a | elif opt in ('-l', '--lenient'): |
|---|
| 586 | n/a | strict = 0 |
|---|
| 587 | n/a | elif opt in ('-e', '--extension'): |
|---|
| 588 | n/a | extension = 1 |
|---|
| 589 | n/a | for gtype in args: |
|---|
| 590 | n/a | if extension: |
|---|
| 591 | n/a | guess = guess_extension(gtype, strict) |
|---|
| 592 | n/a | if not guess: print("I don't know anything about type", gtype) |
|---|
| 593 | n/a | else: print(guess) |
|---|
| 594 | n/a | else: |
|---|
| 595 | n/a | guess, encoding = guess_type(gtype, strict) |
|---|
| 596 | n/a | if not guess: print("I don't know anything about type", gtype) |
|---|
| 597 | n/a | else: print('type:', guess, 'encoding:', encoding) |
|---|