dan/robotparser-rs
1
0
Fork 0
mirror of https://github.com/danbulant/robotparser-rs synced 2026-05-24 12:35:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

style: rustfmt source codes

Browse source
This commit is contained in:
messense 2016-08-21 10:58:18 +08:00
parent e501f4c3b9
commit a5254dbc52
2 changed files with 28 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
rustfmt.toml Normal file
View file

@ -0,0 +1,3 @@
max_width = 120
ideal_width = 100
write_mode = "Overwrite"

34
src/lib.rs
View file

@ -1,4 +1,3 @@
//!
//! robots.txt parser for Rust
//!
//! The robots.txt Exclusion Protocol is implemented as specified in
@ -40,8 +39,8 @@ use std::io::Read;
use std::cell::{Cell, RefCell};
use std::borrow::Cow;
use url::Url;
use hyper::{Client};
use hyper::header::{UserAgent};
use hyper::Client;
use hyper::header::UserAgent;
use hyper::status::StatusCode;
use std::time::{Duration, SystemTime, UNIX_EPOCH};
@ -133,7 +132,7 @@ impl<'a> Entry<'a> {
let rulelines = self.rulelines.borrow();
for line in &*rulelines {
if line.applies_to(filename) {
return line.allowance
return line.allowance;
}
}
true
@ -240,17 +239,17 @@ impl<'a> RobotFileParser<'a> {
match res.status {
StatusCode::Unauthorized | StatusCode::Forbidden => {
self.disallow_all.set(true);
},
}
status if status >= StatusCode::BadRequest && status < StatusCode::InternalServerError => {
self.allow_all.set(true);
},
}
StatusCode::Ok => {
let mut buf = String::new();
res.read_to_string(&mut buf).unwrap();
let lines: Vec<&str> = buf.split('\n').collect();
self.parse(&lines);
},
_ => {},
}
_ => {}
}
}
@ -292,13 +291,13 @@ impl<'a> RobotFileParser<'a> {
1 => {
entry = Entry::new();
state = 0;
},
}
2 => {
self._add_entry(entry);
entry = Entry::new();
state = 0;
},
_ => {},
}
_ => {}
}
}
// remove optional comment and strip line
@ -312,7 +311,8 @@ impl<'a> RobotFileParser<'a> {
let parts: Vec<&str> = ln.splitn(2, ':').collect();
if parts.len() == 2 {
let part0 = parts[0].trim().to_lowercase();
let part1 = String::from_utf8(percent_decode(parts[1].trim().as_bytes()).collect()).unwrap_or("".to_owned());
let part1 = String::from_utf8(percent_decode(parts[1].trim().as_bytes()).collect())
.unwrap_or("".to_owned());
match part0 {
ref x if x == "user-agent" => {
if state == 2 {
@ -321,19 +321,19 @@ impl<'a> RobotFileParser<'a> {
}
entry.push_useragent(&part1);
state = 1;
},
}
ref x if x == "disallow" => {
if state != 0 {
entry.push_ruleline(RuleLine::new(part1, false));
state = 2;
}
},
}
ref x if x == "allow" => {
if state != 0 {
entry.push_ruleline(RuleLine::new(part1, true));
state = 2;
}
},
}
ref x if x == "crawl-delay" => {
if state != 0 {
if let Ok(delay) = part1.parse::<f64>() {
@ -344,14 +344,14 @@ impl<'a> RobotFileParser<'a> {
}
state = 2;
}
},
}
ref x if x == "sitemap" => {
if state != 0 {
entry.add_sitemap(&part1);
state = 2;
}
}
_ => {},
_ => {}
}
}
}