ErrorNoInternet/r34-scraper
1
0
Fork 0
forked from danmax/r34-scraper
Code Pull Requests Activity

refactor: tidy main.rs

Browse Source
This commit is contained in:
Ryan 2024-10-15 18:47:17 -04:00
parent 75ad148f55
commit 9931bd8eaa
Signed by: ErrorNoInternet
GPG Key ID: 2486BFB7B1E6A4A3
1 changed files with 53 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

96
src/main.rs
View File

@ -1,68 +1,78 @@
use std::process::ExitCode;
use regex::Regex;
use reqwest::Client;
const USER_AGENT: &str = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36";
#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
let mut r34_tags = String::new();
async fn main() -> ExitCode {
println!("which tags do you want to scrape? ex: 1girls+1boys+yomama");
std::io::stdin().read_line(&mut r34_tags).unwrap();
r34_tags.trim().to_string();
let tags = std::io::stdin()
.lines()
.next()
.unwrap()
.unwrap()
.trim()
.to_string();
let client = Client::builder().user_agent(USER_AGENT).build().unwrap();
let mut page = 0;
let mut r34pid = -42;
loop {
r34pid += 42;
println!("now scraping page {page}");
let r34_url = format!(
"https://rule34.xxx/index.php?page=post&s=list&tags={}&pid={}", r34_tags, r34pid);
let body = Client::new()
.get(r34_url)
.header("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36").send().await?.text().await?;
let urls = extract_urls(&body);
if !urls.is_empty() {
} else {
let urls = extract_urls(
&client
.get(format!(
"https://rule34.xxx/index.php?page=post&s=list&tags={tags}&pid={}",
page * 42
))
.send()
.await
.unwrap()
.text()
.await
.unwrap(),
);
if urls.is_empty() {
println!("no urls found, exiting...");
std::process::exit(1);
return ExitCode::FAILURE;
}
println!("-------------------------------");
println!(" now scraping page {}", r34pid / 42 + 1);
println!("-------------------------------");
for url in urls {
println!("found post: {}", url);
println!("found post: {url}");
let post = Client::new()
.get(url)
.header("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36").send().await?.text().await?;
let img_url = extract_img_url(&post);
match !img_url.is_empty() {
true => println!("found image url: {}", img_url),
false => println!("image url not found"),
let img_url =
extract_img_url(&client.get(url).send().await.unwrap().text().await.unwrap());
if img_url.is_empty() {
println!("image url not found");
} else {
println!("found image url: {img_url}");
}
}
page += 1;
}
}
fn extract_urls(html: &str) -> Vec<String> {
let re = Regex::new(r"/index\.php\?page=post&s=view&id=\d+").unwrap();
let urls: Vec<String> = re
Regex::new(r"/index\.php\?page=post&s=view&id=\d+")
.unwrap()
.find_iter(html)
.map(|mat| format!("https://rule34.xxx{}", mat.as_str().to_string()))
.collect();
urls
.map(|mat| format!("https://rule34.xxx{}", mat.as_str()))
.collect()
}
fn extract_img_url(html: &str) -> String {
let re = Regex::new(r"https://us\.rule34\.xxx//([A-Za-z0-9]+(/[A-Za-z0-9]+)+)\.[A-Za-z0-9]+\?[0-9]+").unwrap();
match re.find(html) {
Some(img_url) => img_url.as_str().to_string(),
None => String::new(),
if let Some(img_url) =
Regex::new(r"https://us\.rule34\.xxx//([A-Za-z0-9]+(/[A-Za-z0-9]+)+)\.[A-Za-z0-9]+\?[0-9]+")
.unwrap()
.find(html)
{
img_url.as_str().to_string()
} else {
String::new()
}
}