Rust 简单爬虫程序

extern crate hyper;
extern crate hyper_tls;
extern crate scraper;
extern crate tokio;
extern crate rand;

use hyper::client::Client;
use hyper::Uri;
use hyper::body;
use hyper::body::HttpBody;
use hyper_tls::HttpsConnector;

use scraper::ElementRef;
use scraper::Html;
use scraper::Selector;
use std::fs::create_dir;
use std::fs::File;
use std::io::Write;
use std::path::Path;
use std::collections::HashMap;
use rand::{thread_rng, Rng};
use rand::distributions::Alphanumeric;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    //新建Https请求
    let https = HttpsConnector::new();
    //构建Https Client
    let client = Client::builder().build::<_, hyper::Body>(https);
    let url = String::from("https://xxx.com");
    
    //Http::get
    let res = client
    .get(hyper::Uri::from_str(url.as_ref()).unwrap())
    .await?;
    
    //读入数据
    let bytes = body::to_bytes(res.into_body()).await?;
    
    // Scraper 开始解析HTML
    let document = Html::parse_document(String::from_utf8(bytes.to_vec()).unwrap().as_ref());

    // Css 选择器 提取信息
    let selector = Selector::parse("div.pimg-box").unwrap();
    let selector_a = Selector::parse("a").unwrap();
    
    let product_list : Vec<String> = Vec::new();
    // 获取信息
    for element in document.select(&selector) {
        for element_a in element.select(&selector_a) {
            let href = element_a.value().attr("href").unwrap();
            product_list.push(href.to_string());
        }
    }
    Ok(())
}