change robots.txt to cache
This commit is contained in:
@@ -1,7 +1,7 @@
|
||||
use std::path::{PathBuf};
|
||||
use ini::Ini;
|
||||
use crate::config::types::{ApplicationConfig, BasicConfig};
|
||||
use crate::constants::{APP_CONFIG_DIR, APP_CONIFG_FILE_PATH};
|
||||
use crate::constants::{APP_CONFIG_DIR, APP_CONIFG_FILE_PATH, APP_DATA_DIR};
|
||||
|
||||
pub mod types;
|
||||
|
||||
@@ -21,7 +21,7 @@ impl ApplicationConfig {
|
||||
pub fn new() -> Self {
|
||||
let conf = Self {
|
||||
basic_config: BasicConfig {
|
||||
db_path: APP_CONFIG_DIR.clone().join("games.db").to_str().unwrap().to_string(),
|
||||
db_path: APP_DATA_DIR.clone().join("games.db").to_str().unwrap().to_string(),
|
||||
tick_rate: 250
|
||||
}
|
||||
};
|
||||
|
||||
@@ -9,6 +9,8 @@ lazy_static!(
|
||||
.join(APP_DIR_NAME);
|
||||
pub static ref APP_DATA_DIR: PathBuf = BASE_DIRS.data_dir().to_path_buf()
|
||||
.join(APP_DIR_NAME);
|
||||
pub static ref APP_CACHE_PATH: PathBuf = BASE_DIRS.cache_dir().to_path_buf()
|
||||
.join(APP_DIR_NAME);
|
||||
pub static ref APP_CONIFG_FILE_PATH: PathBuf = APP_CONFIG_DIR.clone()
|
||||
.join("config.ini");
|
||||
);
|
||||
@@ -1,9 +1,6 @@
|
||||
use std::fs;
|
||||
use reqwest::{Client, Url};
|
||||
use robotstxt::DefaultMatcher;
|
||||
use robotstxt::matcher::{LongestMatchRobotsMatchStrategy, RobotsMatcher};
|
||||
use crate::constants::APP_DATA_DIR;
|
||||
use crate::crawler;
|
||||
use reqwest::{Client, ClientBuilder, Url};
|
||||
use robotstxt::{DefaultMatcher, RobotsParseHandler};
|
||||
use crate::constants::{APP_CACHE_PATH, APP_DATA_DIR};
|
||||
|
||||
pub(crate) struct Crawler {
|
||||
id: String,
|
||||
@@ -27,7 +24,8 @@ impl Crawler {
|
||||
}
|
||||
|
||||
async fn get_robots_txt(id: &str, base_url: &Url) -> String {
|
||||
let local_robots_path = APP_DATA_DIR.clone().join(id).join("robots.txt");
|
||||
let local_robots_path = APP_CACHE_PATH.clone()
|
||||
.join(id).join("robots.txt");
|
||||
if !local_robots_path.exists() {
|
||||
let mut robots_url = base_url.clone();
|
||||
robots_url.set_path("/robots.txt");
|
||||
|
||||
Reference in New Issue
Block a user