wip: parsing school range

Cargo.lock

@@ -2,6 +2,15 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "aho-corasick"
+version = "0.7.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e37cfd5e7657ada45f742d6e99ca5788580b5c529dc78faf11ece6dc702656f"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "autocfg"
 version = "1.1.0"
@@ -42,6 +51,7 @@ checksum = "ec8a7b6a70fde80372154c65702f00a0f56f3e1c36abbc6c440484be248856db"
 name = "cal8tor"
 version = "0.1.0"
 dependencies = [
+ "regex",
  "reqwest",
  "scraper",
  "tokio",
@@ -893,6 +903,23 @@ dependencies = [
  "bitflags",
 ]
 
+[[package]]
+name = "regex"
+version = "1.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4c4eb3267174b8c6c2f654116623910a0fef09c4753f8dd83db29c48a0df988b"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.6.27"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3f87b73ce11b1619a3c6332f45341e0047173771e8b8b73f87bfeefb7b56244"
+
 [[package]]
 name = "remove_dir_all"
 version = "0.5.3"

Cargo.toml

@@ -9,3 +9,4 @@ edition = "2021"
 reqwest = { version = "0.11" }
 tokio = { version = "1", features = ["full"] }
 scraper = "0.13.0"
+regex = "1"

src/info.rs

@@ -1,3 +1,4 @@
+use regex::Regex;
 use scraper::{Html, Selector};
 
 pub async fn info() {
@@ -5,13 +6,53 @@ pub async fn info() {
 
     // Selectors
     let sel_ul = Selector::parse("ul").unwrap();
+    let sel_li = Selector::parse("li").unwrap();
 
     // Find the raw infos in html page
+    let mut raw_data = Vec::new();
     for (i, data) in document.select(&sel_ul).enumerate() {
         if [1, 2].contains(&i) {
-            println!("\n{} - {:#?}", data.value().name(), data.inner_html());
+            raw_data.push(data);
         }
     }
+
+    let mut data = std::collections::HashMap::new();
+    // d => date
+    // r => repetition
+    let re = Regex::new(r"(?P<d>\d{1,2} \w+ \d{4}).+(?P<r>\d)").unwrap();
+    for (i, ul) in raw_data.into_iter().enumerate() {
+        for element in ul.select(&sel_li) {
+            match element.inner_html() {
+                e if e.starts_with("Début") => {
+                    let captures = re.captures(&e).unwrap();
+                    data.insert(
+                        i,
+                        format!(
+                            "{} pendant {}s",
+                            captures.name("d").unwrap().as_str(),
+                            captures.name("r").unwrap().as_str()
+                        ),
+                    );
+                }
+                e if e.starts_with("Reprise") => {
+                    let captures = re.captures(&e).unwrap();
+                    captures.name("g");
+                    data.insert(
+                        i,
+                        format!(
+                            "{} puis reprise {} pendant {}s",
+                            data.get(&i).unwrap(),
+                            captures.name("d").unwrap().as_str(),
+                            captures.name("r").unwrap().as_str()
+                        ),
+                    );
+                }
+                _ => (),
+            }
+        }
+    }
+
+    println!("{:#?}", data);
 }
 
 async fn get_webpage() -> Result<Html, Box<dyn std::error::Error>> {