|
@@ -10,18 +10,6 @@ fn main() {
|
|
|
|
|
|
|
|
|
fn scrape_feats(url: &str) {
|
|
|
- // let bookstrs = [
|
|
|
- // "ACG",
|
|
|
- // "APG",
|
|
|
- // "ARG",
|
|
|
- // "ISWG",
|
|
|
- // "OA",
|
|
|
- // "UC",
|
|
|
- // "UI",
|
|
|
- // "(see the Pathfinder RPG Advanced Player's Guide)"
|
|
|
- // ];
|
|
|
-
|
|
|
- // commenting out -- going local for a bit
|
|
|
let resp = reqwest::get(url).unwrap();
|
|
|
assert!(resp.status().is_success());
|
|
|
|
|
@@ -29,9 +17,6 @@ fn scrape_feats(url: &str) {
|
|
|
|
|
|
//let doc = Document::from(include_str!("/home/jmelesky/code/featscraper/assets/feats.html"));
|
|
|
|
|
|
- // compile this regex once, not once per node
|
|
|
- let re_uppers = Regex::new(r"[A-Z]{2}").unwrap();
|
|
|
-
|
|
|
let mut header = true;
|
|
|
for node in doc.find(Name("tr")) {
|
|
|
// skip the first one
|
|
@@ -56,11 +41,7 @@ fn scrape_feats(url: &str) {
|
|
|
let prereqs = prereqs.trim();
|
|
|
|
|
|
|
|
|
- // print only the ones with two consecutive uppercase letters
|
|
|
- // in the prereqs -- figure out what to trim
|
|
|
- if re_uppers.is_match(prereqs) {
|
|
|
- println!("|{}|{}|{}|", featname, prereqs, featurl);
|
|
|
- }
|
|
|
+ println!("|{}|{}|{}|", featname, prereqs, featurl);
|
|
|
}
|
|
|
}
|
|
|
|
|
@@ -69,3 +50,13 @@ fn scrape_feats(url: &str) {
|
|
|
|
|
|
|
|
|
|
|
|
+// list of "book strings" to strip eventually:
|
|
|
+// ACG
|
|
|
+// APG
|
|
|
+// ARG
|
|
|
+// ISWG
|
|
|
+// OA
|
|
|
+// UC
|
|
|
+// UI
|
|
|
+// (see the Pathfinder RPG Advanced Player's Guide)
|
|
|
+
|