Improve experiments

test/beautifulSoup_test/example_html.txt → test/beautiful_soup/example.html

@@ -8,12 +8,13 @@
         var url2 = "https://www.example.com";
     </script>
     <p>Este é um exemplo</p>
-       "https://www.youtube.com/"
+    <span> https://www.youtube.com/ </span>
+    <span> "https://www.youtube.com/" </span>
     <script>
         var url3 = "https://www.example.org";
     </script>
     <script>
         "https://www.kotlin.com"
     </script>
 </body>
-</html>
+</html>

test/beautiful_soup/extract_urls.py

@@ -0,0 +1,37 @@
+from bs4 import BeautifulSoup
+import re
+import sys
+
+def extract_script_urls(html_content):
+    urls = []
+
+    soup = BeautifulSoup(html_content, 'html.parser')
+
+    script_tags = soup.find_all('script')
+
+    regex = re.compile('(https?:\/\/)?([a-zA-Z0-9\.-]+\.[a-z\.]{2,6})([\/\w \.-]*)*\/?')
+    for script_tag in script_tags:
+        if script_tag.string:
+            urls_found = [''.join(r) for r in regex.findall(script_tag.string)]
+            urls.extend(urls_found)
+
+    return urls
+
+def main():
+    # Check if an HTML file was passed as a command-line argument
+    if len(sys.argv) < 2:
+        print("Usage: python script.py input_file.html")
+        return
+
+    # Read the content of the HTML file
+    file_path = sys.argv[1]
+    input_html = open(file_path).read()
+
+    urls = extract_script_urls(input_html)
+
+    print("Extracted URLs:")
+    for url in urls:
+        print(url)
+
+if __name__ == "__main__":
+    main()

test/comby/count-for.txt

@@ -0,0 +1 @@
+for (:[_]) { for (:[_]) { :[_] } }

test/comby/count_loops.sh

@@ -0,0 +1,7 @@
+#!/bin/sh
+#
+# Usage: ./count_loops.sh "my-file.c"
+
+file=$1
+[ -z "$file" ] && echo "Please provide a file to process" && exit 1
+comby -count -match-only "$(cat count-for.txt)" '' "$file"

test/comby/main.c

@@ -0,0 +1,7 @@
+for (int i = 0; i < 10; i++) {
+  for (int j = 0; j < 20; j++) {
+    for (int k = 0; k < 30; k++) {
+      printf("%d %d %d\n", i, j, k);
+    }
+  }
+}