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

made scraper stop once there are no post urls

Browse Source
This commit is contained in:
danmax 2024-10-15 00:20:24 -04:00
parent 7b73c942b8
commit 36c0bfb0fe
1 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
src/main.rs
View File

@ -9,7 +9,7 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
r34pid += 42;
let r34_url = format!(
"https://rule34.xxx/index.php?page=post&s=list&tags=1girls&pid={}",
"https://rule34.xxx/index.php?page=post&s=list&tags=kaguya_jinguu&pid={}",
r34pid
);
@ -17,11 +17,19 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
.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 {
println!("no urls found, exiting...");
std::process::exit(1);
}
println!("-------------------------------");
println!(" now scraping page {}", r34pid / 42 + 1);
println!("-------------------------------");
let urls = extract_urls(&body);
for url in urls {
println!("found post: {}", url);
@ -50,9 +58,7 @@ fn extract_urls(html: &str) -> Vec<String> {
}
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-z]+\?[0-9]+")
.unwrap();
let re = Regex::new(r"https://us\.rule34\.xxx//([A-Za-z0-9]+(/[A-Za-z0-9]+)+)\.[A-Za-z]+\?[0-9]+").unwrap();
match re.find(html) {
Some(img_url) => img_url.as_str().to_string(),
None => String::new(),