python的HTMLParser学习
先来大致看看HTMLParser的源代码吧： 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 """A parser for HTML and XHTML.""" # This file is based on sgmllib.py, but the API is slightly different. # XXX There should be a way to distinguish between PCDATA (parsed # character data -- the normal case), RCDATA (replaceable character # data -- only char and entity references and end tags are special) # and CDATA (character data -- only end tags are special). import markupbase import re # Regular expressions used for parsing interesting_normal = re. compile ( '[&<]' ) interesting_cdata = re. compile (r '<(/|\Z)' ) incomplete = re. compile ( '&[a-zA-Z#]' ) entityref = re. compile ( '&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]' ) charref = re. compile ( '&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]' ) starttagopen = re. compile ( '<[a-zA-Z]' ) piclose = re. compile ( '>' ) commentclose = re. compile (r '--\s*>' ) tagfind = re. compile ( '[a-zA-Z][-.a-zA-Z0-9:_]*' ) attrfind = re. compile ( r '\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' r '(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?' ) locatestarttagend = re. compile (r """ <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name (?:\s+ # whitespace before attribute name (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name (?:\s*=\s* # value indicator (?:'[^']*' # LITA-enclosed value |\"[^\"]*\" # LIT-enclosed value |[^'\">\s]+ # bare value ) )? ) )* \s* # trailing whitespace """ , re.VERBOSE) endendtag = re. compile ( '>' ) endtagfind = re. compile ( '</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>' ) class HTMLParseError(Exception): """Exception raised for all parse errors.""" def __init__( self , msg, position = ( None , None )): assert msg self .msg = msg self .lineno = position[ 0 ] self .offset = position[ 1 ] def __str__( self ): result = self .msg if self .lineno is not None : result = result + ", at line %d" % self .lineno if self .offset is not None : result = result + ", column %d" % ( self .offset + 1 ) return result class HTMLParser(markupbase.ParserBase): """Find tags and other markup and call handler functions. Usage: p = HTMLParser() p.feed(data) ... p.close() Start tags are handled by calling self.handle_starttag() or self.handle_startendtag(); end tags by self.handle_endtag(). The data between tags is passed from the parser to the derived class by calling self.handle_data() with the data as argument (the data may be split up in arbitrary chunks). Entity references are passed by calling self.handle_entityref() with the entity reference as the argument. Numeric character references are passed to self.handle_charref() with the string containing the reference as the argument. """ CDATA_CONTENT_ELEMENTS = ( "script" , "style" ) def __init__( self ): """Initialize and reset this instance.""" self .reset() def reset( self ): """Reset this instance. Loses all unprocessed data.""" self .rawdata = '' self .lasttag = '???' self .interesting = interesting_normal markupbase.ParserBase.reset( self ) def feed( self , data): """Feed data to the parser. Call this as often as you want, with as little or as much text as you want (may include '\n'). """ self .rawdata = self .rawdata + data self .goahead( 0 ) def close( self ): """Handle any buffered data.""" self .goahead( 1 ) def error( self , message): raise HTMLParseError(message, self .getpos()) __starttag_text = None def get_starttag_text( self ): """Return full source of start tag: '<...>'.""" return self .__starttag_text def set_cdata_mode( self ): self .interesting = interesting_cdata def clear_cdata_mode( self ): self .interesting = interesting_normal # Internal -- handle data as far as reasonable. May leave state # and data to be processed by a subsequent call. If 'end' is # true, force handling all data as if followed by EOF marker. def goahead( self , end): rawdata = self .rawdata i = 0 n = len (rawdata) while i < n: match = self .interesting.search(rawdata, i) # < or & if match: j = match.start() else : j = n if i < j: self .handle_data(rawdata[i:j]) i = self .updatepos(i, j) if i = = n: break startswith = rawdata.startswith if startswith( '<' , i): if starttagopen.match(rawdata, i): # < + letter k = self .parse_starttag(i) elif startswith( "</" , i): k = self .parse_endtag(i) elif startswith( "<!--" , i): k = self .parse_comment(i) elif startswith( "<?" , i): k = self .parse_pi(i) elif startswith( "<!" , i): k = self .parse_declaration(i) elif (i + 1 ) < n: self .handle_data( "<" ) k = i + 1 else : break if k < 0 : if end: self .error( "EOF in middle of construct" ) break i = self .updatepos(i, k) elif startswith( "&#" , i): match = charref.match(rawdata, i) if match: name = match.group()[ 2 : - 1 ] self .handle_charref(name) k = match.end() if not startswith( ';' , k - 1 ): k = k - 1 i = self .updatepos(i, k) continue else : if ";" in rawdata[i:]: #bail by consuming &# self .handle_data(rawdata[ 0 : 2 ]) i = self .updatepos(i, 2 ) break elif startswith( '&' , i): match = entityref.match(rawdata, i) if match: name = match.group( 1 ) self .handle_entityref(name) k = match.end() if not startswith( ';' , k - 1 ): k = k - 1 i = self .updatepos(i, k) continue match = incomplete.match(rawdata, i) if match: # match.group() will contain at least 2 chars if end and match.group() = = rawdata[i:]: self .error( "EOF in middle of entity or char ref" ) # incomplete break elif (i + 1 ) < n: # not the end of the buffer, and can't be confused # with some other construct self .handle_data( "&" ) i = self .updatepos(i, i + 1 ) else : break else : assert 0 , "interesting.search() lied" # end while if end and i < n: self .handle_data(rawdata[i:n]) i = self .updatepos(i, n) self .rawdata = rawdata[i:] # Internal -- parse processing instr, return end or -1 if not terminated def parse_pi( self , i): rawdata = self .rawdata assert rawdata[i:i + 2 ] = = '<?' , 'unexpected call to parse_pi()' match = piclose.search(rawdata, i + 2 ) # > if not match: return - 1 j = match.start() self .handle_pi(rawdata[i + 2 : j]) j = match.end() return j # Internal -- handle starttag, return end or -1 if not terminated def parse_starttag( self , i): self .__starttag_text = None endpos = self .check_for_whole_start_tag(i) if endpos < 0 : return endpos rawdata = self .rawdata self .__starttag_text = rawdata[i:endpos] # Now parse the data between i+1 and j into a tag and attrs attrs = [] match = tagfind.match(rawdata, i + 1 ) assert match, 'unexpected call to parse_starttag()' k = match.end() self .lasttag = tag = rawdata[i + 1 :k].lower() while k < endpos: m = attrfind.match(rawdata, k) if not m: break attrname, rest, attrvalue = m.group( 1 , 2 , 3 ) if not rest: attrvalue = None elif attrvalue[: 1 ] = = '\'' = = attrvalue[ - 1 :] or \ attrvalue[: 1 ] = = '"' = = attrvalue[ - 1 :]: attrvalue = attrvalue[ 1 : - 1 ] attrvalue = self .unescape(attrvalue) attrs.append((attrname.lower(), attrvalue)) k = m.end() end = rawdata[k:endpos].strip() if end not in ( ">" , "/>" ): lineno, offset = self .getpos() if "\n" in self .__starttag_text: lineno = lineno + self .__starttag_text.count( "\n" ) offset = len ( self .__starttag_text) \ - self .__starttag_text.rfind( "\n" ) else : offset = offset + len ( self .__starttag_text) self .error( "junk characters in start tag: %r" % (rawdata[k:endpos][: 20 ],)) if end.endswith( '/>' ): # XHTML-style empty tag: <span attr="value" /> self .handle_startendtag(tag, attrs) else : self .handle_starttag(tag, attrs) if tag in self .CDATA_CONTENT_ELEMENTS: self .set_cdata_mode() return endpos # Internal -- check to see if we have a complete starttag; return end # or -1 if incomplete. def check_for_whole_start_tag( self , i): rawdata = self .rawdata m = locatestarttagend.match(rawdata, i) if m: j = m.end() next = rawdata[j:j + 1 ] if next = = ">" : return j + 1 if next = = "/" : if rawdata.startswith( "/>" , j): return j + 2 if rawdata.startswith( "/" , j): # buffer boundary return - 1 # else bogus input self .updatepos(i, j + 1 ) self .error( "malformed empty start tag" ) if next = = "": # end of input return - 1 if next in ( "abcdefghijklmnopqrstuvwxyz=/" "ABCDEFGHIJKLMNOPQRSTUVWXYZ" ): # end of input in or before attribute value, or we have the # '/' from a '/>' ending return - 1 self .updatepos(i, j) self .error( "malformed start tag" ) raise AssertionError( "we should not get here!" ) # Internal -- parse endtag, return end or -1 if incomplete def parse_endtag( self , i): rawdata = self .rawdata assert rawdata[i:i + 2 ] = = "</" , "unexpected call to parse_endtag" match = endendtag.search(rawdata, i + 1 ) # > if not match: return - 1 j = match.end() match = endtagfind.match(rawdata, i) # </ + tag + > if not match: self .error( "bad end tag: %r" % (rawdata[i:j],)) tag = match.group( 1 ) self .handle_endtag(tag.lower()) self .clear_cdata_mode() return j # Overridable -- finish processing of start+end tag: <tag.../> def handle_startendtag( self , tag, attrs): self .handle_starttag(tag, attrs) self .handle_endtag(tag) # Overridable -- handle start tag def handle_starttag( self , tag, attrs): pass # Overridable -- handle end tag def handle_endtag( self , tag): pass # Overridable -- handle character reference def handle_charref( self , name): pass # Overridable -- handle entity reference def handle_entityref( self , name): pass # Overridable -- handle data def handle_data( self , data): pass # Overridable -- handle comment def handle_comment( self , data): pass # Overridable -- handle declaration def handle_decl( self , decl): pass # Overridable -- handle processing instruction def handle_pi( self , data): pass def unknown_decl( self , data): self .error( "unknown declaration: %r" % (data,)) # Internal -- helper to remove special character quoting entitydefs = None def unescape( self , s): if '&' not in s: return s def replaceEntities(s): s = s.groups()[ 0 ] if s[ 0 ] = = "#" : s = s[ 1 :] if s[ 0 ] in [ 'x' , 'X' ]: c = int (s[ 1 :], 16 ) else : c = int (s) return unichr (c) else : # Cannot use name2codepoint directly, because HTMLParser supports apos, # which is not part of HTML 4 import htmlentitydefs if HTMLParser.entitydefs is None : entitydefs = HTMLParser.entitydefs = { 'apos' :u "'" } for k, v in htmlentitydefs.name2codepoint.iteritems(): entitydefs[k] = unichr (v) try : return self .entitydefs[s] except KeyError: return '&' + s + ';' return re.sub(r "&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));" , replaceEntities, s) 大家可以看到，其实内部的很多的方法都是没有实现的，所以需要我们继承这个类，自己去实现一些方法。关于HTMLParser的方法，大家可以参考官方文档： http://docs.python.org/library/htmlparser.html#HTMLParser.HTMLParser（英文，笔者没有多少时间去翻译这些） 另外，给一个例子大家对照着看看，我相信这么简单的例子，大家都能看懂的。 假设我们要处理的文件在d盘根目录下，名字为hello.html,文件的内容为： <! DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> < html xmlns="http://www.w3.org/1999/xhtml"> < head > < meta http-equiv="Content-Type" content="text/html; charset=utf-8"/> < title >Rollen Holt - cnblogs</ title > < meta name="keywords" content="Rollen Holt,rollenholt" /> < link type="text/css" rel="stylesheet" href="http://www.cnblogs.com/css/common.css"/> < link id="MainCss" type="text/css" rel="stylesheet" href="http://www.cnblogs.com/Skins/kubrick/style.css"/> < link type="text/css" rel="stylesheet" href="http://www.cnblogs.com/css/common2.css"/> < link type="text/css" rel="stylesheet" href="http://common.cnblogs.com/css/shCore.css"/> < link type="text/css" rel="stylesheet" href="http://common.cnblogs.com/css/shThemeDefault.css"/> < link title="RSS" type="application/rss+xml" rel="alternate" href="http://www.cnblogs.com/rollenholt/rss"/> < link title="RSD" type="application/rsd+xml" rel="EditURI" href="http://www.cnblogs.com/rollenholt/rsd.xml"/> < link type="application/wlwmanifest+xml" rel="wlwmanifest" href="http://www.cnblogs.com/rollenholt/wlwmanifest.xml"/> < script src="http://common.cnblogs.com/script/jquery.js" type="text/javascript"></ script > < script src="/script/common.js" type="text/javascript"></ script > < script src="http://common.cnblogs.com/script/jquery.json-2.2.min.js" type="text/javascript"></ script > < script type="text/javascript" src="http://common.cnblogs.com/script/shCore.js"></ script > < script type="text/javascript" src="http://common.cnblogs.com/script/shLanguage.js"></ script > </ head > < body > < a name="top"></ a > < form method="post" action="" id="Form1"> < div class="aspNetHidden"> < input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE" value="" /> </ div > </ form > </ body > </ html > 我们的python代码为： #coding=utf-8 from HTMLParser import HTMLParser class MyParser(HTMLParser): """一个简单的HTMLparser的例子""" def handle_decl( self , decl): """处理头文档""" HTMLParser.handle_decl( self , decl) print decl def handle_starttag( self , tag, attrs): """处理起始标签""" HTMLParser.handle_starttag( self , tag, attrs) if not HTMLParser.get_starttag_text( self ).endswith( "/>" ): print "<" ,tag, ">" def handle_data( self , data): """处理文本元素""" HTMLParser.handle_data( self , data) print data, def handle_endtag( self , tag): """处理结束标签""" HTMLParser.handle_endtag( self , tag) if not HTMLParser.get_starttag_text( self ).endswith( "/>" ): print "</" ,tag, ">" def handle_startendtag( self , tag, attrs): """处理自闭标签""" HTMLParser.handle_startendtag( self , tag, attrs) print HTMLParser.get_starttag_text( self ) def handle_comment( self , data): """处理注释""" HTMLParser.handle_comment( self , data) print data def close( self ): HTMLParser.close( self ) print "parser over" demo = MyParser() demo.feed( open ( "d:\\hello.html" ).read()) demo.close() 输出的结果为： DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd" < html > < head > <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/> < title > Rollen Holt - cnblogs </ title > <meta name="keywords" content="Rollen Holt,rollenholt" /> <link type="text/css" rel="stylesheet" href="http://www.cnblogs.com/css/common.css"/> <link id="MainCss" type="text/css" rel="stylesheet" href="http://www.cnblogs.com/Skins/kubrick/style.css"/> <link type="text/css" rel="stylesheet" href="http://www.cnblogs.com/css/common2.css"/> <link type="text/css" rel="stylesheet" href="http://common.cnblogs.com/css/shCore.css"/> <link type="text/css" rel="stylesheet" href="http://common.cnblogs.com/css/shThemeDefault.css"/> <link title="RSS" type="application/rss+xml" rel="alternate" href="http://www.cnblogs.com/rollenholt/rss"/> <link title="RSD" type="application/rsd+xml" rel="EditURI" href="http://www.cnblogs.com/rollenholt/rsd.xml"/> <link type="application/wlwmanifest+xml" rel="wlwmanifest" href="http://www.cnblogs.com/rollenholt/wlwmanifest.xml"/> < script > </ script > < script > </ script > < script > </ script > < script > </ script > < script > </ script > </ head > < body > < a > </ a > < form > < div > <input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE" value="" /> parser over ============================================================================== 本文转自被遗忘的博客园博客，原文链接：http://www.cnblogs.com/rollenholt/archive/2011/12/01/2271058.html，如需转载请自行联系原作者
