Own the memory for url & selector in Job structs

This commit is contained in:
Kienan Stewart 2022-09-24 11:57:07 -04:00
parent b1dee1f5a8
commit 20870b6444
1 changed files with 27 additions and 20 deletions

View File

@ -1,6 +1,7 @@
use std::cmp::Ordering;
use std::env;
use std::path::Path;
use std::str::FromStr;
use std::thread;
use std::time::Duration;
use std::time::Instant;
@ -10,15 +11,27 @@ use thirtyfour_sync::WebDriverCommands;
mod conf;
use conf::Conf;
struct Job<'a> {
url: &'a str,
selector: &'a str,
struct Job {
url: String,
selector: String,
every: Duration,
last_run: Option<Instant>,
}
struct ThreadJob<'a> {
job: Job<'a>,
impl Job {
fn new(url: &str, selector: &str, conf: &Conf) -> Job {
let job = Job {
url: String::from_str(url).unwrap(),
selector: String::from_str(selector).unwrap(),
every: conf.check_interval,
last_run: None,
};
return job;
}
}
struct ThreadJob {
job: Job,
handle: Option<
std::thread::JoinHandle<
Result<String, &'static str>
@ -27,7 +40,7 @@ struct ThreadJob<'a> {
last_result: Option<String>,
}
impl ThreadJob<'_> {
impl ThreadJob {
fn lru_not_running(&self, b: &ThreadJob) -> Option<Ordering> {
// the "greater" value is one that is running, but we
// don't recheck the thread state every time. If there's
@ -87,18 +100,12 @@ fn main() {
}
let mut jobs = Vec::new();
let some_job = Job {
url: "https://www.rust-lang.org",
selector: "a.download-link",
every: Duration::new(60, 0),
last_run: None,
};
let other_job = Job {
url: "https://arstechnica.com/",
selector: "li.split-feature:nth-child(1) > header:nth-child(4) > h2:nth-child(1) > a:nth-child(1)",
every: Duration::new(120, 0),
last_run: None,
};
let some_job = Job::new("https://www.rust-lang.org", "a.download-link", &conf);
let other_job = Job::new(
"https://arstechnica.com/",
"li.split-feature:nth-child(1) > header:nth-child(4) > h2:nth-child(1) > a:nth-child(1)",
&conf
);
jobs.push(ThreadJob {
job: some_job,
handle: None,
@ -125,7 +132,7 @@ fn main() {
continue;
}
let fragment = scraper::Html::parse_document(source.unwrap().unwrap().as_str());
let selector = scraper::Selector::parse(tj.job.selector).expect("Failed to parse selector");
let selector = scraper::Selector::parse(&tj.job.selector.as_str()).expect("Failed to parse selector");
let mut result = String::from("");
for element in fragment.select(&selector) {
result.push_str(element.inner_html().as_str());
@ -160,7 +167,7 @@ fn main() {
let driver = conf.driver_url.clone();
let url = tj.job.url.clone();
tj.handle = Some(thread::spawn(move || {
return get_source(driver.as_str(), url);
return get_source(driver.as_str(), url.as_str());
}));
println!("Started thread for '{}'", tj.job.url);
tj.job.last_run = Some(Instant::now());