17个版本

0.8.0	2020年11月7日
0.7.5	2020年2月11日
0.7.4	2019年10月1日
0.5.2	2019年2月12日
0.3.0	2018年12月12日

#100 in #html-parser

每月 50次下载
用于 6 个crate (3个直接使用)

MIT 协议

44KB
342 行

unhtml的 derive

#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
#[html(selector = "#test")]
struct SingleUser {
    #[html(selector = "p:nth-child(1)", attr = "inner")]
    name: String,

    #[html(selector = "p:nth-child(2)", attr = "inner")]
    age: u8,

    #[html(selector = "p:nth-child(3)", attr = "inner")]
    like_lemon: bool,
}

let user = SingleUser::from_html(r#"<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
    <div id="test">
        <div>
            <p>Hexilee</p>
            <p>20</p>
            <p>true</p>
        </div>
    </div>
</body>
</html>"#).unwrap();
assert_eq!("Hexilee", &user.name);
assert_eq!(20, user.age);
assert!(user.like_lemon);

属性

html

target

derive target 或 field

specification

#[html(selector= "...",attr= "...",default= ...)]

selector、attr、default 或 html 本身可能是多余的。

这是有效的

#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};


#[derive(FromHtml)]
struct SingleString {
    value: String,
}

selector

target

derive target 或 field

字面类型

字符串

specification

选择器必须是有效的 CSS 选择器，无效的选择器将导致编译时 panic

// panic
#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
#[html(selector = "<>")]
struct SingleUser {}

// panic
#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::*;

#[derive(FromHtml)]
struct SingleUser {
    #[html(selector = "<>", attr = "inner")]
    name: String,
}

如果选择多个元素且字段类型不是 Vec，则选择第一个


#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
#[html(selector = "a")]
struct Link {
    #[html(attr = "href")]
    href: String,

    #[html(attr = "inner")]
    value: String,
}

let link = Link::from_html(r#"
<a href="https://github.com">Github</a> 
<a href="https://google.com">Google</a> 
"#).unwrap();
assert_eq!("https://github.com", &link.href);
assert_eq!("Github", &link.value);

默认行为

根元素的 HTML


#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
#[html(selector = "a")]
struct Link {
    #[html(attr = "href")]
    href: String,

    #[html(attr = "inner")]
    value: String,
}

let link = Link::from_html(r#"<a href="https://github.com">Github</a>"#).unwrap();
assert_eq!("https://github.com", &link.href);
assert_eq!("Github", &link.value);

attr

target

字段

字面类型

字符串

specification

inner 指的是 innerHtml
任何其他 attr 指的是 html 元素属性

#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
#[html(selector = "a")]
struct Link {
    #[html(attr = "href")]
    href: String,

    #[html(attr = "inner")]
    value: String,
}

let link = Link::from_html(r#"<a href="https://github.com">Github</a>"#).unwrap();
assert_eq!("https://github.com", &link.href);
assert_eq!("Github", &link.value);

默认行为

整个元素的 HTML（不是 innerHtml！)

#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
#[html(selector = "a")]
struct Link {
    #[html(attr = "href")]
    href: String,

    #[html(attr = "inner")]
    value: String,
    
    source: String,
}

let link = Link::from_html(r#"<a href="https://github.com">Github</a>"#).unwrap();
assert_eq!("https://github.com", &link.href);
assert_eq!("Github", &link.value);
assert_eq!(r#"<a href="https://github.com">Github</a>"#, &link.source);

default

target

字段

字面类型

任何 literal 类型

specification

与 field 相同的类型

#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
struct DefaultUser {
    // invoke String::from_html
    #[html(selector = "#non-exist", default = "Hexilee")]
    name: String,

    // invoke u8::from<u8>
    #[html(default = 20)]
    age: u8,

    #[html(default = true)]
    like_lemon: bool,
}

let user = DefaultUser::from_html("<p></p>").unwrap();
assert_eq!("Hexilee", &user.name);
assert_eq!(20, user.age);
assert_eq!(-1000, user.assets);
assert!(user.like_lemon);

字符串

#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
#[html(selector = "a")]
struct Link {
    #[html(attr = "href")]
    href: String,

    #[html(attr = "inner")]
    value: String,
}

#[derive(FromHtml)]
struct Website {
    #[html(default = "10")]
    age: u8,

    #[html(default = "<a href='https://github.com'>Github</a>")]
    link: Link,
}

let website = Website::from_html("<p></p>").unwrap();
let link = website.link;
assert_eq!(10u8, website.age);
assert_eq!("https://github.com", &link.href);
assert_eq!("Github", &link.value);

默认行为

当选择无内容时返回 Err(unhtml::failure::Error)

// panic
#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]

#[html(selector = "a")]struct Link {
    // no default
    #[html(attr = "href")]
    href: String,

    #[html(attr = "inner")]
    value: String,
}

let link = Link::from_html(r#"<a>Github</a>"#).unwrap();

字段类型

实现 FromHtml 的任何类型，不使用泛型

// panic
#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]

#[html(selector = "a")]struct Link {
    // no default
    #[html(attr = "href")]
    href: &str,
}

// panic
#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
struct Website {
    // no default
    #[html(attr = "href")]
    hrefs: std::collections::LinkedList<String>,
}

// panic
#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
struct Website {
    // no default
    #[html(attr = "href")]
    hrefs: [String],
}

Vec

应使用 use unhtml::VecFromHtml

extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml, VecFromHtml};

#[derive(FromHtml)]
struct TestUser {
    #[html(selector = "p:nth-child(1)", attr = "inner")]
    name: String,

    #[html(selector = "p:nth-child(2)", attr = "inner")]
    age: u8,

    #[html(selector = "p:nth-child(3)", attr = "inner")]
    like_lemon: bool,
}

#[derive(FromHtml)]
#[html(selector = "#test")]
struct TestUsers {
    #[html(selector = "div")]
    users: Vec<TestUser>,
}

let users = TestUsers::from_html(r#"<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
    <div id="test">
        <div>
            <p>Hexilee</p>
            <p>20</p>
            <p>true</p>
        </div>
        <div>
            <p>BigBrother</p>
            <p>21</p>
            <p>false</p>
        </div>
    </div>
</body>
</html>"#).unwrap();
let hexilee = &users.users[0];
let big_brother = &users.users[1];
assert_eq!("Hexilee", &hexilee.name);
assert_eq!(20, hexilee.age);
assert!(hexilee.like_lemon);
assert_eq!("BigBrother", &big_brother.name);
assert_eq!(21, big_brother.age);
assert!(!big_brother.like_lemon);

作为 crate unhtml 的文档，如果您想直接使用 Vec<TestUser>，则可以这样做

extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, VecFromHtml};

#[derive(FromHtml)]
struct TestUser {
    #[html(selector = "p:nth-child(1)", attr = "inner")]
    name: String,

    #[html(selector = "p:nth-child(2)", attr = "inner")]
    age: u8,

    #[html(selector = "p:nth-child(3)", attr = "inner")]
    like_lemon: bool,
}

let users = Vec::<TestUser>::from_html("#test > div", r#"<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
    <div id="test">
        <div>
            <p>Hexilee</p>
            <p>20</p>
            <p>true</p>
        </div>
        <div>
            <p>BigBrother</p>
            <p>21</p>
            <p>false</p>
        </div>
    </div>
</body>
</html>"#).unwrap();
let hexilee = &users[0];
let big_brother = &users[1];
assert_eq!("Hexilee", &hexilee.name);
assert_eq!(20, hexilee.age);
assert!(hexilee.like_lemon);
assert_eq!("BigBrother", &big_brother.name);
assert_eq!(21, big_brother.age);
assert!(!big_brother.like_lemon);

源HTML

带有顶级选择器

所有源 HTML 都将解析为 fragment。顶级元素是 html，且没有 DOCTYPE、head 或 body。

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
    <div id="test">
        <div>
            <p>Hexilee</p>
            <p>20</p>
            <p>true</p>
        </div>
    </div>
</body>
</html>

将解析为

<html lang="en">
    <meta charset="UTF-8">
    <title>Title</title>
    <div id="test">
        <div>
            <p>Hexilee</p>
            <p>20</p>
            <p>true</p>
        </div>
    </div>
</html>

和

<p>Hexilee</p>

将解析为

<html>
    <p>Hexilee</p>
</html>


// panic

extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
struct Document {
    // no default
    #[html(selector = "head")]
    head: String,

    #[html(selector = "body")]
    body: String,
}

let dicument = Document::from_html(r#"<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
    <div id="test">
        <div>
            <p>Hexilee</p>
            <p>20</p>
            <p>true</p>
        </div>
    </div>
</body>
</html>"#).unwrap();

没有顶级选择器

当派生结构体没有 top selector 时，所有源HTML将被解析为 纯片段。没有 DOCTYPE，html，head 或 body。

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
    <div id="test">
        <div>
            <p>Hexilee</p>
            <p>20</p>
            <p>true</p>
        </div>
    </div>
</body>
</html>

将解析为

<meta charset="UTF-8">
<title>Title</title>
<div id="test">
   <div>
       <p>Hexilee</p>
       <p>20</p>
       <p>true</p>
   </div>
</div>

和

<p>Hexilee</p>

将解析为

<p>Hexilee</p>

#[macro_use]
extern crate unhtml_derive;
extern crate unhtml;
use unhtml::{self, FromHtml};

#[derive(FromHtml)]
#[html(selector = "a")]
struct Link {
    #[html(attr = "href")]
    href: String,

    #[html(attr = "inner")]
    value: String,
}

let link = Link::from_html(r#"<a href="https://github.com">Github</a>"#).unwrap();
assert_eq!("https://github.com", &link.href);
assert_eq!("Github", &link.value);

依赖项

~4–9MB
~93K SLoC

宏 unhtml_derive

17个版本

unhtml的 derive

目录

derive 目标

基本用法

属性

html

target

specification

selector

target

字面类型

specification

默认行为

attr

target

字面类型

specification

默认行为

default

target

字面类型

specification

默认行为

字段类型

实现 FromHtml 的任何类型，不使用泛型

Vec

源HTML

带有顶级选择器

没有顶级选择器

依赖项