README
¶
HTML 
This package is an HTML5 lexer written in Go. It follows the specification at The HTML syntax. The lexer takes an io.Reader and converts it into tokens until the EOF.
Installation
Run the following command
go get github.com/tdewolff/parse/html
or add the following import and run project with go get
import "github.com/tdewolff/parse/html"
Lexer
Usage
The following initializes a new Lexer with io.Reader r:
l := html.NewLexer(r)
To tokenize until EOF an error, use:
for {
tt, data := l.Next()
switch tt {
case html.ErrorToken:
// error or EOF set in l.Err()
return
case html.StartTagToken:
// ...
for {
ttAttr, dataAttr := l.Next()
if ttAttr != html.AttributeToken {
break
}
// ...
}
// ...
}
}
All tokens:
ErrorToken TokenType = iota // extra token when errors occur
CommentToken
DoctypeToken
StartTagToken
StartTagCloseToken
StartTagVoidToken
EndTagToken
AttributeToken
TextToken
Examples
package main
import (
"os"
"github.com/tdewolff/parse/html"
)
// Tokenize HTML from stdin.
func main() {
l := html.NewLexer(os.Stdin)
for {
tt, data := l.Next()
switch tt {
case html.ErrorToken:
if l.Err() != io.EOF {
fmt.Println("Error on line", l.Line(), ":", l.Err())
}
return
case html.StartTagToken:
fmt.Println("Tag", string(data))
for {
ttAttr, dataAttr := l.Next()
if ttAttr != html.AttributeToken {
break
}
key := dataAttr
val := l.AttrVal()
fmt.Println("Attribute", string(key), "=", string(val))
}
// ...
}
}
}
License
Released under the MIT license.
Documentation
¶
Overview ¶
Package html is an HTML5 lexer following the specifications at http://www.w3.org/TR/html5/syntax.html.
Index ¶
Examples ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func EscapeAttrVal ¶
EscapeAttrVal returns the escaped attribute value bytes without quotes.
Types ¶
type Hash ¶
type Hash uint32
uses github.com/tdewolff/hasher
const ( A Hash = 0x1 Abbr Hash = 0x4 Accept Hash = 0x3206 Accept_Charset Hash = 0x320e Accesskey Hash = 0x4409 Acronym Hash = 0xbb07 Action Hash = 0x2b906 Address Hash = 0x67607 Align Hash = 0x1605 Alink Hash = 0xd205 Allowfullscreen Hash = 0x23c0f Alt Hash = 0xeb03 Annotation Hash = 0x2060a AnnotationXml Hash = 0x2060d Applet Hash = 0x16106 Area Hash = 0x38604 Article Hash = 0x40707 Aside Hash = 0x8305 Async Hash = 0xf705 Audio Hash = 0x11305 Autocomplete Hash = 0x14a0c Autofocus Hash = 0x15609 Autoplay Hash = 0x16b08 Axis Hash = 0x17304 B Hash = 0x101 Background Hash = 0x1e0a Base Hash = 0x44d04 Basefont Hash = 0x44d08 Bdi Hash = 0xcb03 Bdo Hash = 0x18a03 Bgcolor Hash = 0x19d07 Bgsound Hash = 0x1a407 Big Hash = 0x1ac03 Blink Hash = 0x1af05 Blockquote Hash = 0x1b40a Body Hash = 0x4004 Border Hash = 0x33806 Br Hash = 0x202 Button Hash = 0x1be06 Canvas Hash = 0x7f06 Caption Hash = 0x27e07 Center Hash = 0x62306 Challenge Hash = 0x1eb09 Charset Hash = 0x3907 Checked Hash = 0x3ad07 Cite Hash = 0xfb04 Class Hash = 0x1c905 Classid Hash = 0x1c907 Clear Hash = 0x40b05 Code Hash = 0x1dc04 Codebase Hash = 0x44908 Codetype Hash = 0x1dc08 Col Hash = 0x19f03 Colgroup Hash = 0x1f408 Color Hash = 0x19f05 Cols Hash = 0x20104 Colspan Hash = 0x20107 Command Hash = 0x21307 Compact Hash = 0x21a07 Content Hash = 0x58107 Contenteditable Hash = 0x5810f Controls Hash = 0x22908 Coords Hash = 0x23506 Crossorigin Hash = 0x25a0b Data Hash = 0x4a604 Datalist Hash = 0x4a608 Datetime Hash = 0x2e908 Dd Hash = 0x31602 Declare Hash = 0x8607 Default Hash = 0x5407 DefaultChecked Hash = 0x4ea0e DefaultMuted Hash = 0x54b0c DefaultSelected Hash = 0x540f Defer Hash = 0x6205 Del Hash = 0x7203 Desc Hash = 0x7c04 Details Hash = 0x9207 Dfn Hash = 0xab03 Dialog Hash = 0xcc06 Dir Hash = 0xd903 Dirname Hash = 0xd907 Disabled Hash = 0x10108 Div Hash = 0x10803 Dl Hash = 0x1aa02 Download Hash = 0x47f08 Draggable Hash = 0x1cf09 Dropzone Hash = 0x41208 Dt Hash = 0x5ff02 Em Hash = 0x6e02 Embed Hash = 0x6e05 Enabled Hash = 0x4e07 Enctype Hash = 0x2ce07 Face Hash = 0x62104 Fieldset Hash = 0x26b08 Figcaption Hash = 0x27b0a Figure Hash = 0x28f06 Font Hash = 0x45104 For Hash = 0x29b03 ForeignObject Hash = 0x29b0d Foreignobject Hash = 0x2a80d Form Hash = 0x2b504 Formaction Hash = 0x2b50a Formenctype Hash = 0x2ca0b Formmethod Hash = 0x2d50a Formnovalidate Hash = 0x2df0e Formtarget Hash = 0x2f40a Frame Hash = 0xa305 Frameborder Hash = 0x3330b Frameset Hash = 0xa308 H1 Hash = 0x19b02 H2 Hash = 0x32402 H3 Hash = 0x34902 H4 Hash = 0x37f02 H5 Hash = 0x60102 H6 Hash = 0x2fe02 Head Hash = 0x36b04 Header Hash = 0x36b06 Headers Hash = 0x36b07 Height Hash = 0x30006 Hgroup Hash = 0x30806 Hidden Hash = 0x31406 High Hash = 0x32104 Hr Hash = 0xaf02 Href Hash = 0xaf04 Hreflang Hash = 0xaf08 Html Hash = 0x30404 Http_Equiv Hash = 0x3260a I Hash = 0x601 Icon Hash = 0x58004 Id Hash = 0x8502 Iframe Hash = 0x33206 Image Hash = 0x33e05 Img Hash = 0x34303 Inert Hash = 0x53605 Input Hash = 0x46c05 Ins Hash = 0x26303 Isindex Hash = 0x17507 Ismap Hash = 0x34b05 Itemid Hash = 0xfc06 Itemprop Hash = 0x56e08 Itemref Hash = 0x61b07 Itemscope Hash = 0x35609 Itemtype Hash = 0x36008 Kbd Hash = 0xca03 Keygen Hash = 0x4a06 Keytype Hash = 0x5b007 Kind Hash = 0xd604 Label Hash = 0x7405 Lang Hash = 0xb304 Language Hash = 0xb308 Legend Hash = 0x1d606 Li Hash = 0x1702 Link Hash = 0xd304 List Hash = 0x4aa04 Listing Hash = 0x4aa07 Longdesc Hash = 0x7808 Loop Hash = 0x11e04 Low Hash = 0x23e03 Main Hash = 0x1004 Malignmark Hash = 0xc10a Manifest Hash = 0x65708 Map Hash = 0x16003 Mark Hash = 0xc704 Marquee Hash = 0x69907 Math Hash = 0x36804 Max Hash = 0x37703 Maxlength Hash = 0x37709 Media Hash = 0xde05 Mediagroup Hash = 0xde0a Menu Hash = 0x3bd04 Meta Hash = 0x4b904 Meter Hash = 0x2ef05 Method Hash = 0x2d906 Mglyph Hash = 0x34406 Mi Hash = 0x2c02 Min Hash = 0x2c03 Mn Hash = 0x2e202 Mo Hash = 0x4dd02 Ms Hash = 0x35902 Mtext Hash = 0x38105 Multiple Hash = 0x38f08 Muted Hash = 0x39705 Name Hash = 0xdc04 Nobr Hash = 0x1a04 Noembed Hash = 0x6c07 Noframes Hash = 0xa108 Nohref Hash = 0xad06 Noresize Hash = 0x24a08 Noscript Hash = 0x31908 Noshade Hash = 0x4e507 Novalidate Hash = 0x2e30a Nowrap Hash = 0x57706 Object Hash = 0x2af06 Ol Hash = 0x12d02 Onabort Hash = 0x1c207 Onafterprint Hash = 0x2830c Onbeforeprint Hash = 0x2bd0d Onbeforeunload Hash = 0x66a0e Onblur Hash = 0x14406 Oncancel Hash = 0x11708 Oncanplay Hash = 0x18c09 Oncanplaythrough Hash = 0x18c10 Onchange Hash = 0x42808 Onclick Hash = 0x6a407 Onclose Hash = 0x39c07 Oncuechange Hash = 0x3c10b Ondblclick Hash = 0x3cc0a Ondrag Hash = 0x3d606 Ondragend Hash = 0x3d609 Ondragenter Hash = 0x3df0b Ondragleave Hash = 0x3ea0b Ondragover Hash = 0x3f50a Ondragstart Hash = 0x3ff0b Ondrop Hash = 0x41006 Ondurationchange Hash = 0x42010 Onemptied Hash = 0x41709 Onended Hash = 0x43007 Onerror Hash = 0x43707 Onfocus Hash = 0x43e07 Onhashchange Hash = 0x45e0c Oninput Hash = 0x46a07 Oninvalid Hash = 0x47109 Onkeydown Hash = 0x47a09 Onkeypress Hash = 0x4870a Onkeyup Hash = 0x49707 Onload Hash = 0x49e06 Onloadeddata Hash = 0x49e0c Onloadedmetadata Hash = 0x4b110 Onloadstart Hash = 0x4c70b Onmessage Hash = 0x4d209 Onmousedown Hash = 0x4db0b Onmousemove Hash = 0x4f80b Onmouseout Hash = 0x5030a Onmouseover Hash = 0x5100b Onmouseup Hash = 0x51b09 Onmousewheel Hash = 0x5240c Onoffline Hash = 0x53009 Ononline Hash = 0x53b08 Onpagehide Hash = 0x5430a Onpageshow Hash = 0x5570a Onpause Hash = 0x56307 Onplay Hash = 0x59006 Onplaying Hash = 0x59009 Onpopstate Hash = 0x5990a Onprogress Hash = 0x5a30a Onratechange Hash = 0x5b70c Onreset Hash = 0x5c307 Onresize Hash = 0x5ca08 Onscroll Hash = 0x5d208 Onseeked Hash = 0x5dd08 Onseeking Hash = 0x5e509 Onselect Hash = 0x5ee08 Onshow Hash = 0x5f806 Onstalled Hash = 0x60309 Onstorage Hash = 0x60c09 Onsubmit Hash = 0x61508 Onsuspend Hash = 0x62909 Ontimeupdate Hash = 0x4520c Onunload Hash = 0x63208 Onvolumechange Hash = 0x63a0e Onwaiting Hash = 0x64809 Open Hash = 0x57404 Optgroup Hash = 0x12008 Optimum Hash = 0x65107 Option Hash = 0x66606 Output Hash = 0x50a06 P Hash = 0xc01 Param Hash = 0xc05 Pattern Hash = 0x9b07 Pauseonexit Hash = 0x5650b Ping Hash = 0xe704 Placeholder Hash = 0x1270b Plaintext Hash = 0x17d09 Poster Hash = 0x1fb06 Pre Hash = 0x30d03 Preload Hash = 0x30d07 Profile Hash = 0x34f07 Progress Hash = 0x5a508 Prompt Hash = 0x66006 Public Hash = 0x57c06 Q Hash = 0x8d01 Radiogroup Hash = 0x30a Rb Hash = 0x1d02 Readonly Hash = 0x38708 Rel Hash = 0x30e03 Required Hash = 0x8b08 Rev Hash = 0x29303 Reversed Hash = 0x29308 Rows Hash = 0x6604 Rowspan Hash = 0x6607 Rp Hash = 0x28902 Rt Hash = 0x1c702 Rtc Hash = 0x1c703 Ruby Hash = 0xf304 Rules Hash = 0x13105 S Hash = 0x3d01 Samp Hash = 0x9804 Sandbox Hash = 0x13507 Scope Hash = 0x35a05 Scoped Hash = 0x35a06 Script Hash = 0x31b06 Scrolling Hash = 0x5d409 Seamless Hash = 0x3a108 Section Hash = 0x13f07 Select Hash = 0x5f006 Selected Hash = 0x5f008 Shape Hash = 0x23005 Size Hash = 0x24e04 Sizes Hash = 0x24e05 Small Hash = 0x23a05 Sortable Hash = 0x25208 Source Hash = 0x26506 Spacer Hash = 0x37106 Span Hash = 0x6904 Spellcheck Hash = 0x3a80a Src Hash = 0x44403 Srcdoc Hash = 0x44406 Srclang Hash = 0x49007 Start Hash = 0x40505 Step Hash = 0x65d04 Strike Hash = 0x5ac06 Strong Hash = 0x67c06 Style Hash = 0x68205 Sub Hash = 0x61703 Summary Hash = 0x68707 Sup Hash = 0x68e03 Svg Hash = 0x69103 System Hash = 0x69406 Tabindex Hash = 0x4bf08 Table Hash = 0x25505 Target Hash = 0x2f806 Tbody Hash = 0x3f05 Td Hash = 0xaa02 Text Hash = 0x18204 Textarea Hash = 0x38208 Tfoot Hash = 0xed05 Th Hash = 0x19502 Thead Hash = 0x36a05 Time Hash = 0x2ed04 Title Hash = 0x16605 Tr Hash = 0x18502 Track Hash = 0x18505 Translate Hash = 0x22009 Truespeed Hash = 0x27209 Tt Hash = 0x9d02 Type Hash = 0x10f04 Typemustmatch Hash = 0x1e00d U Hash = 0xb01 Ul Hash = 0x5802 Undeterminate Hash = 0x250d Usemap Hash = 0x15d06 Valign Hash = 0x1506 Value Hash = 0x10a05 Valuetype Hash = 0x10a09 Var Hash = 0x32f03 Video Hash = 0x6a005 Visible Hash = 0x6ab07 Vlink Hash = 0x6b205 Wbr Hash = 0x56003 Width Hash = 0x5fd05 Wrap Hash = 0x57904 Xmlns Hash = 0x13b05 Xmp Hash = 0x17b03 )
type Lexer ¶
type Lexer struct {
// contains filtered or unexported fields
}
Lexer is the state for the lexer.
func NewLexer ¶
NewLexer returns a new Lexer for a given io.Reader.
Example ¶
l := NewLexer(bytes.NewBufferString("<span class='user'>John Doe</span>"))
out := ""
for {
tt, data, n := l.Next()
if tt == ErrorToken {
break
}
if tt == StartTagToken {
out += "<"
} else if tt == EndTagToken {
out += "</"
}
out += string(data)
if tt == StartTagToken {
out += " "
} else if tt == EndTagToken {
out += ">"
} else if tt == AttributeToken {
out += "=" + string(l.AttrVal())
}
l.Free(n)
}
fmt.Println(out)
Output: <span class='user'>John Doe</span>
func (*Lexer) AttrVal ¶
AttrVal returns the attribute value when an AttributeToken was returned from Next.
func (*Lexer) Err ¶
Err returns the error encountered during lexing, this is often io.EOF but also other errors can be returned.
type TokenType ¶
type TokenType uint32
TokenType determines the type of token, eg. a number or a semicolon.
Source Files
Click to show internal directories.
Click to hide internal directories.