[BE] Broken scrappin with reqwest

master
Araozu 2023-09-30 11:16:20 -05:00
parent 8c1883d5dd
commit 495c60c323
5 changed files with 139 additions and 42 deletions

45
backend/Cargo.lock generated
View File

@ -125,6 +125,7 @@ dependencies = [
"scraper", "scraper",
"serde", "serde",
"sqlx", "sqlx",
"ureq",
] ]
[[package]] [[package]]
@ -317,6 +318,15 @@ version = "2.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9cace84e55f07e7301bae1c519df89cdad8cc3cd868413d3fdbdeca9ff3db484" checksum = "9cace84e55f07e7301bae1c519df89cdad8cc3cd868413d3fdbdeca9ff3db484"
[[package]]
name = "crc32fast"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b540bd8bc810d3885c6ea91e2018302f68baba2129ab3e88f32389ee9370880d"
dependencies = [
"cfg-if",
]
[[package]] [[package]]
name = "crossbeam-queue" name = "crossbeam-queue"
version = "0.3.8" version = "0.3.8"
@ -551,6 +561,16 @@ dependencies = [
"version_check", "version_check",
] ]
[[package]]
name = "flate2"
version = "1.0.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c6c98ee8095e9d1dcbf2fcc6d95acccb90d1c81db1e44725c6a984b1dbdfb010"
dependencies = [
"crc32fast",
"miniz_oxide",
]
[[package]] [[package]]
name = "flume" name = "flume"
version = "0.10.14" version = "0.10.14"
@ -1967,6 +1987,7 @@ version = "0.21.5"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "79ea77c539259495ce8ca47f53e66ae0330a8819f67e23ac96ca02f50e7b7d36" checksum = "79ea77c539259495ce8ca47f53e66ae0330a8819f67e23ac96ca02f50e7b7d36"
dependencies = [ dependencies = [
"log",
"ring", "ring",
"rustls-webpki", "rustls-webpki",
"sct", "sct",
@ -2335,7 +2356,7 @@ dependencies = [
"tokio-stream", "tokio-stream",
"tracing", "tracing",
"url", "url",
"webpki-roots", "webpki-roots 0.24.0",
] ]
[[package]] [[package]]
@ -2928,6 +2949,22 @@ version = "0.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a156c684c91ea7d62626509bce3cb4e1d9ed5c4d978f7b4352658f96a4c26b4a" checksum = "a156c684c91ea7d62626509bce3cb4e1d9ed5c4d978f7b4352658f96a4c26b4a"
[[package]]
name = "ureq"
version = "2.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f5ccd538d4a604753ebc2f17cd9946e89b77bf87f6a8e2309667c6f2e87855e3"
dependencies = [
"base64",
"flate2",
"log",
"once_cell",
"rustls",
"rustls-webpki",
"url",
"webpki-roots 0.25.2",
]
[[package]] [[package]]
name = "url" name = "url"
version = "2.4.0" version = "2.4.0"
@ -3078,6 +3115,12 @@ dependencies = [
"rustls-webpki", "rustls-webpki",
] ]
[[package]]
name = "webpki-roots"
version = "0.25.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "14247bb57be4f377dfb94c72830b8ce8fc6beac03cf4bf7b9732eadd414123fc"
[[package]] [[package]]
name = "whoami" name = "whoami"
version = "1.4.1" version = "1.4.1"

View File

@ -14,3 +14,4 @@ dotenvy = "0.15.7"
serde = "1.0.188" serde = "1.0.188"
chrono = "0.4.27" chrono = "0.4.27"
scraper = "0.17.1" scraper = "0.17.1"
ureq = "2.8.0"

View File

@ -1,10 +1,12 @@
use std::time::{SystemTime, UNIX_EPOCH}; use std::time::{SystemTime, UNIX_EPOCH};
use once_cell::sync::OnceCell; use once_cell::sync::OnceCell;
use reqwest::{Client, cookie::Jar, Url}; use reqwest::{cookie::Jar, Client, Url};
/// Stores the ch_sid cookie value use std::io::prelude::*;
static SESSION_COOKIE: OnceCell<String> = OnceCell::new();
/// Stores a client with a persistent cookie store
static SESSION_COOKIE: OnceCell<Client> = OnceCell::new();
/// Stores the last time a request was made, in seconds since UNIX epoch /// Stores the last time a request was made, in seconds since UNIX epoch
static SESSION_TIME: OnceCell<u64> = OnceCell::new(); static SESSION_TIME: OnceCell<u64> = OnceCell::new();
@ -14,37 +16,34 @@ pub async fn request(url: String) -> Result<String, String> {
ensure_session().await?; ensure_session().await?;
// Create a client & set cookies // Get the stored client
let cookie = SESSION_COOKIE.get().expect("SESSION_COOKIE was not set, even after calling ensure_session"); let client = SESSION_COOKIE
let cookie = format!("ch_sid={};", cookie); .get()
let cookie_url = format!("{}", classroom_url).parse::<Url>().expect("Error parsing CLASSROOM_URL into a url"); .expect("SESSION_COOKIE was not set, even after calling ensure_session");
let jar = Jar::default();
jar.add_cookie_str(cookie.as_str(), &cookie_url);
let client = reqwest::Client::builder()
.cookie_provider(jar.into())
.build();
let client = match client {
Ok(c) => c,
Err(error) => return Err(format!("Error creating client: {:?}", error))
};
// Do the request // Do the request
let response = client let req_builder = client
.get(format!("{}{}", classroom_url, url)) .get(format!("{}{}", classroom_url, url))
.send() .build()
.await; .unwrap();
println!("{:?}", req_builder);
let response = client.execute(req_builder).await;
let response = match response { let response = match response {
Ok(r) => r, Ok(r) => r,
Err(err) => return Err(format!("Error sending request: {:?}", err)) Err(err) => return Err(format!("Error sending request: {:?}", err)),
}; };
// Check if there's a new cookie
if let Some(session_cookie) = response.cookies().find(|c| c.name() == "ch_sid") {
println!("new cookie: {}", session_cookie.value());
}
match response.text().await { match response.text().await {
Ok(t) => Ok(t), Ok(t) => Ok(t),
Err(err) => Err(format!("Error getting text from response: {:?}", err)) Err(err) => Err(format!("Error getting text from response: {:?}", err)),
} }
} }
@ -77,33 +76,60 @@ pub async fn ensure_session() -> Result<(), String> {
/// Logins to the online classroom, and sets the session cookie /// Logins to the online classroom, and sets the session cookie
async fn login() -> Result<(), String> { async fn login() -> Result<(), String> {
let classroom_url = std::env::var("CLASSROOM_URL").expect("CLASSROOM_URL env var is not set!"); let classroom_url = std::env::var("CLASSROOM_URL").expect("CLASSROOM_URL env var is not set!");
let clasroom_user = let classroom_user =
std::env::var("CLASSROOM_USER").expect("CLASSROOM_USER env var is not set!"); std::env::var("CLASSROOM_USER").expect("CLASSROOM_USER env var is not set!");
let clasroom_password = let classroom_password =
std::env::var("CLASSROOM_PASSWORD").expect("CLASSROOM_PASSWORD env var is not set!"); std::env::var("CLASSROOM_PASSWORD").expect("CLASSROOM_PASSWORD env var is not set!");
let params = [ let params = [
("login", clasroom_user), ("login", classroom_user),
("password", clasroom_password), ("password", classroom_password),
("submitAuth", "".into()), ("submitAuth", "".into()),
("_qf__formLogin", "".into()), ("_qf__formLogin", "".into()),
]; ];
let client = Client::new(); let jar = Jar::default();
let result = client
let client = Client::builder()
.cookie_store(true)
.cookie_provider(jar.into())
.build()
.unwrap();
// let client = Client::new();
let req = client
.post(format!("{}/index.php", classroom_url)) .post(format!("{}/index.php", classroom_url))
.form(&params) .form(&params)
.send() .build().unwrap();
println!("{:?}\n", req);
let body_bytes= req.body().unwrap().as_bytes().unwrap();
println!("{:?}\n", std::str::from_utf8(body_bytes));
let result = client.execute(req)
.await; .await;
match result { match result {
Ok(response) => { Ok(response) => {
println!("{:?}\n\n", response);
let Some(session_cookie) = response.cookies().find(|c| c.name() == "ch_sid") else { let Some(session_cookie) = response.cookies().find(|c| c.name() == "ch_sid") else {
return Err("Response succeeded, but no session cookie was foun".into()); return Err("Response succeeded, but no session cookie was found".into());
}; };
match SESSION_COOKIE.set(session_cookie.value().into()) { // Save the client with the session cookie
println!("Got a cookie: {}", session_cookie.value());
let text = response.text().await.unwrap();
// save text to file
let mut f = std::fs::File::create("scraps/test.html").unwrap();
f.write_all(text.as_bytes()).unwrap();
match SESSION_COOKIE.set(client) {
Ok(_) => Ok(()), Ok(_) => Ok(()),
Err(error) => Err(format!("Error setting session cookie: {:?}", error)), Err(error) => Err(format!("Error saving client: {:?}", error)),
} }
} }
Err(error) => Err(format!("Error connecting to online classroom: {:?}", error)), Err(error) => Err(format!("Error connecting to online classroom: {:?}", error)),

View File

@ -1,9 +1,10 @@
import { Show, createSignal } from "solid-js"; import { For, Show, createSignal, onMount } from "solid-js";
import { Search } from "../certs/Search"; import { Search } from "../certs/Search";
import { Person } from "../types/Person"; import { Person } from "../types/Person";
import { FilledCard } from "../components/FilledCard"; import { FilledCard } from "../components/FilledCard";
import { LinkIcon } from "../icons/LinkIcon"; import { LinkIcon } from "../icons/LinkIcon";
import { ClassroomUserCreation } from "./ClassroomUserCreation"; import { ClassroomUserCreation } from "./ClassroomUserCreation";
import { ClassroomRegistrationUser } from "../types/ClassroomRegistrationUser";
type TabType = "Vinculate" | "Create"; type TabType = "Vinculate" | "Create";
@ -15,7 +16,9 @@ export function OnlineClassroom() {
<Search setPerson={setPerson} /> <Search setPerson={setPerson} />
<div> <div>
<ClassroomUser person={person()!} /> <Show when={person() !== null && !person()!.person_classroom_id}>
<ClassroomUser person={person()!} />
</Show>
</div> </div>
</div> </div>
@ -37,7 +40,9 @@ function ClassroomUser(props: {person: Person}) {
<div class="bg-c-surface"> <div class="bg-c-surface">
<Show when={active() === "Vinculate"}> <Show when={active() === "Vinculate"}>
<ClassroomVinculation /> <ClassroomVinculation
person_surname={`${props.person.person_paternal_surname} ${props.person.person_maternal_surname}`}
/>
</Show> </Show>
<Show when={active() === "Create"}> <Show when={active() === "Create"}>
<ClassroomUserCreation /> <ClassroomUserCreation />
@ -49,15 +54,31 @@ function ClassroomUser(props: {person: Person}) {
); );
} }
function ClassroomVinculation() { function ClassroomVinculation(props: {person_surname: string}) {
const [classroomUsers, setClassroomUsers] = createSignal<ClassroomRegistrationUser[]>([]);
const loadUsers = async() => {
const response = await fetch(`${import.meta.env.VITE_BACKEND_URL}/api/classroom/users/${encodeURIComponent(props.person_surname)}`);
const json = await response.json();
if (response.ok) {
setClassroomUsers(json);
} else {
console.error("Error loading users", json);
}
};
onMount(loadUsers);
return ( return (
<div> <div>
<p class="py-2 px-4"> <p class="py-2 px-4">
Vincule un usuario existente: Vincule un usuario existente:
</p> </p>
<ClassroomSingleUser /> <For each={classroomUsers()}>
<ClassroomSingleUser /> {(_) => <ClassroomSingleUser />}
<ClassroomSingleUser /> </For>
</div> </div>
); );
} }

View File

@ -0,0 +1,6 @@
export type ClassroomRegistrationUser = {
name: string,
surname: string,
username: string,
user_id: string,
}