added tests

.github/workflows/run-tests.yaml

@@ -0,0 +1,20 @@
+name: Build & Run Tests
+run-name: Build & Test Project Across 10+ Test Cases 🚀
+on: [push]
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      - name: Build project
+        run: cargo build -r --verbose
+
+      - name: Install Test Runner
+        run: cargo install qbtt
+
+      - name: Run Tests
+        id: run_tests
+        run: cd tests && cargo run

src/utils/request_handler.rs

@@ -8,7 +8,7 @@ lazy_static! {
 }
 
 pub async fn get_text_elements_from_url(url: String, use_chrome: Option<bool>) -> Vec<String> {
-    let text_selector = Selector::parse("p, h1, h2, h3, h4, h5, blockquote, dd, div, dl, dt, figcaption, figure, hr, li, menu, ol, p, pre, ul, a, abbr, b, bdi, bdo, br, cite, code, data, dfn, em, i, kbd, mark, q, rp, rt, ruby, s, samp, small, span, strong, sub, sup, time, u, var, wbr, caption, col, colgroup, table, tbody, td, tfoot, th, thead, tr, noscript").unwrap();
+    let text_selector = Selector::parse("p, h1, h2, h3, h4, h5, blockquote, dd, div, dl, dt, figcaption, figure, hr, li, menu, ol, p, pre, ul, a, abbr, b, bdi, bdo, br, cite, code, data, dfn, em, i, kbd, mark, q, rp, rt, ruby, s, samp, small, span, strong, sub, sup, time, u, var, wbr, caption, col, colgroup, table, tbody, td, tfoot, th, thead, tr, noscript, font").unwrap();
     let mut parsed_html = Html::new_document();
     if use_chrome.is_some() && use_chrome.unwrap() {
         parsed_html = browse_for_html_from_url(url.clone()).await;

tests/test_cases.toml

@@ -0,0 +1,59 @@
+[[test_cases]]
+name = "HttpRequest/Basic"
+run_type = "output"
+cmd = "../target/release/webgrep https://quinnpatwardhan.com"
+expect = "JavaScript"
+
+[[test_cases]]
+name = "HttpRequest/html"
+run_type = "output"
+cmd = "../target/release/webgrep https://trec.nist.gov/faq.html"
+expect = "DARPA"
+
+[[test_cases]]
+name = "HttpRequest/Recursive1-FoundLink"
+run_type = "output"
+cmd = "../target/release/webgrep https://trec.nist.gov/overview.html -r 1"
+expect = "Traversed http://www.nist.gov/privacy-policy"
+
+[[test_cases]]
+name = "HttpRequest/Recursive1-ExploredLink"
+run_type = "output"
+cmd = "../target/release/webgrep https://trec.nist.gov/overview.html -r 1"
+expect = "Cookies"
+
+[[test_cases]]
+name = "HttpRequest/Recursive1-PathContains"
+run_type = "checksum"
+cmd = "../target/release/webgrep http://infolab.stanford.edu/pub/voy/museum.html shsadu --pathcontains people -r 1"
+expect = "05a09747b2f15d953cccb061cd39c971"
+
+[[test_cases]]
+name = "HttpRequest/Recursive1-SameHost"
+run_type = "output"
+cmd = "../target/release/webgrep https://exhibits.stanford.edu/cs/about/timeline sdhb -r 1 --samehost"
+expect = "Not Traversing policies.google.com due to samehost being true"
+
+[[test_cases]]
+name = "ChromeRequest/Basic"
+run_type = "output"
+cmd = "../target/release/webgrep https://quinnpatwardhan.com/aboutme -c"
+expect = "New York Times"
+
+[[test_cases]]
+name = "ChromeRequest/Recursive"
+run_type = "output"
+cmd = "../target/release/webgrep https://quinnpatwardhan.com/aboutme -c -r 1 --samehost"
+expect = "https://quinnpatwardhan.com/contact:"
+
+[[test_cases]]
+name = "PDF/NoRecursive"
+run_type = "output"
+cmd = "../target/release/webgrep https://quinnpatwardhan.com/Assets/Resume.pdf"
+expect = "InfoSense"
+
+[[test_cases]]
+name = "Search/Basic"
+run_type = "output"
+cmd = "../target/release/webgrep https://quinnpatwardhan.com/aboutme Ravens -c"
+expect = "die-hard"