awesome/awesome-rust
1
0
Fork 0
mirror of https://github.com/rust-unofficial/awesome-rust.git synced 2024-11-21 10:45:55 +02:00
Code Issues Releases Activity

Kill all the HTML images in favour of Markdown

Browse Source
This commit is contained in:
Tom Parker-Shemilt 2020-10-09 09:37:09 +01:00
parent 7001e25e03
commit b49400cd8b
2 changed files with 480 additions and 494 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

959
README.md
View File

File diff suppressed because it is too large Load Diff

15
src/main.rs
View File

@ -9,7 +9,6 @@ use log::{warn, debug, info};
use std::io::Write; use std::io::Write;
use reqwest::{Client, redirect::Policy, StatusCode, header, Url}; use reqwest::{Client, redirect::Policy, StatusCode, header, Url};
use regex::Regex; use regex::Regex;
use scraper::{Html, Selector};
use failure::{Fail, Error, format_err}; use failure::{Fail, Error, format_err};
use chrono::{Local, DateTime, Duration}; use chrono::{Local, DateTime, Duration};
use std::env; use std::env;
@ -287,19 +286,7 @@ async fn main() -> Result<(), Error> {
} }
} }
Event::Html(content) => { Event::Html(content) => {
let fragment = Html::parse_fragment(&content); return Err(format_err!("Contains HTML content, not markdown: {}", content));
for element in fragment.select(&Selector::parse("img").unwrap()) {
let img_src = element.value().attr("src");
if let Some(src) = img_src {
do_check(src.to_string());
}
}
for element in fragment.select(&Selector::parse("a").unwrap()) {
let a_href = element.value().attr("href");
if let Some(href) = a_href {
do_check(href.to_string());
}
}
} }
_ => {} _ => {}
} }