Struct robotxt::Robots

pub struct Robots { /* private fields */ }

The Robots struct represents the set of directives related to the specific user-agent in the provided robots.txt file.

Implementations

impl Robots

pub fn from_bytes(robots: &[u8], user_agent: &str) -> Self

Creates a new Robots from the byte slice.

use robotxt::Robots;

let txt = r#"
    User-Agent: foobot
    Disallow: *
    Allow: /example/
    Disallow: /example/nope.txt
"#.as_bytes();

let r = Robots::from_bytes(txt, "foobot");
assert!(r.is_allowed("/example/yeah.txt"));
assert!(!r.is_allowed("/example/nope.txt"));
assert!(!r.is_allowed("/invalid/path.txt"));

pub fn from_reader<R: Read>( reader: R, user_agent: &str ) -> Result<Self, IoError>

Creates a new Robots from the generic reader.

use robotxt::Robots;

// Let's pretend it's something that actually needs a reader.
// The std::io::Read trait is implemented for &[u8].
let reader = r#"
    User-Agent: foobot
    Disallow: *
    Allow: /example/
    Disallow: /example/nope.txt
"#.as_bytes();

let r = Robots::from_reader(reader, "foobot").unwrap();
assert!(r.is_allowed("/example/yeah.txt"));
assert!(!r.is_allowed("/example/nope.txt"));
assert!(!r.is_allowed("/invalid/path.txt"));

pub fn from_access(access: AccessResult<'_>, user_agent: &str) -> Self

Creates a new Robots from the AccessResult.

use robotxt::{AccessResult, Robots};

let r = Robots::from_access(AccessResult::Redirect, "foobot");
assert!(r.is_allowed("/example/yeah.txt"));
assert!(r.is_allowed("/example/nope.txt"));

let r = Robots::from_access(AccessResult::Unavailable, "foobot");
assert!(r.is_allowed("/example/yeah.txt"));
assert!(r.is_allowed("/example/nope.txt"));

let r = Robots::from_access(AccessResult::Unreachable, "foobot");
assert!(!r.is_allowed("/example/yeah.txt"));
assert!(!r.is_allowed("/example/nope.txt"));

pub fn from_always(always: bool, user_agent: &str) -> Self

Creates a new Robots from the global rule.

use robotxt::Robots;

let r = Robots::from_always(true, "foobot");
assert!(r.is_allowed("/example/yeah.txt"));
assert!(r.is_allowed("/example/nope.txt"));

impl Robots

pub fn is_allowed(&self, path: &str) -> bool

Returns true if the path is allowed for the user-agent. NOTE: Expects relative path.

use robotxt::Robots;

let txt = r#"
    User-Agent: foobot
    Disallow: *
    Allow: /example/
    Disallow: /example/nope.txt
"#.as_bytes();

let r = Robots::from_bytes(txt, "foobot");
assert!(r.is_allowed("/example/yeah.txt"));
assert!(!r.is_allowed("/example/nope.txt"));
assert!(!r.is_allowed("/invalid/path.txt"));

pub fn is_always(&self) -> Option<bool>

Returns Some(_) if the site is fully allowed or disallowed.

use robotxt::Robots;

let r = Robots::from_always(true, "foobot");
assert_eq!(r.is_always(), Some(true));

let r = Robots::from_always(false, "foobot");
assert_eq!(r.is_always(), Some(false));

pub fn user_agent(&self) -> &str

Returns the longest matching user-agent.

use robotxt::Robots;

let txt = r#"
    User-Agent: foo
    User-Agent: foobot
"#.as_bytes();

let r = Robots::from_bytes(txt, "foobot-search");
assert_eq!(r.user_agent(), "foobot");

pub fn crawl_delay(&self) -> Option<Duration>

Returns the crawl-delay of the user-agent if specified.

use std::time::Duration;
use robotxt::Robots;

let txt = r#"
    User-Agent: foobot
    Crawl-Delay: 5
"#.as_bytes();

let r = Robots::from_bytes(txt, "foobot");
assert_eq!(r.crawl_delay(), Some(Duration::from_secs(5)));

pub fn sitemaps(&self) -> &Vec<Url>

Returns all collected sitemaps.

use robotxt::Robots;

let txt = r#"
    Sitemap: https://example.com/sitemap_1.xml
    Sitemap: https://example.com/sitemap_2.xml
"#.as_bytes();

let r = Robots::from_bytes(txt, "foobot");
assert_eq!(r.sitemaps().len(), 2);

Trait Implementations

impl Clone for Robots

fn clone(&self) -> Robots

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Robots

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.