From 34c0d035873ae3a5960a72eb9aeaa4dc8a7bdd9c Mon Sep 17 00:00:00 2001
From: Benjamin Loison <Benjamin_Loison@users.noreply.gitea.lemnoslife.com>
Date: Tue, 14 Feb 2023 00:59:37 +0100
Subject: [PATCH] #31: Add a first search only captions support

---
 website/index.php | 5 +++--
 website/search.py | 5 +++++
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/website/index.php b/website/index.php
index 288133c..7d07c60 100644
--- a/website/index.php
+++ b/website/index.php
@@ -13,7 +13,8 @@ Access raw data with: <?php echoUrl('channels/'); ?>.
 
 <form id="form">
     <input type="text" autofocus id="search" pattern="[A-Za-z0-9-_ ]+" placeholder="Your [A-Za-z0-9-_ ]+ search"></input>
-    <input type="submit" value="Search">
+    <input type="submit" id="search" value="Search">
+    <input type="submit" id="search-only-captions" value="Search only captions">
 </form>
 
 <ul id="channels">
@@ -64,7 +65,7 @@ Access raw data with: <?php echoUrl('channels/'); ?>.
     function search(event) {
         // We don't want to refresh the webpage which is the default behavior.
         event.preventDefault();
-        const query = document.getElementById('search').value;
+        const query = event.submitter.id + ' ' + document.getElementById('search').value;
         if (firstRun) {
             firstRun = false;
             conn = new WebSocket('wss://crawler.yt.lemnoslife.com/websocket');
diff --git a/website/search.py b/website/search.py
index c8f0bda..ff4038c 100755
--- a/website/search.py
+++ b/website/search.py
@@ -7,6 +7,9 @@ path = '/mnt/HDD0/YouTube_captions_search_engine/channels/'
 clientId = sys.argv[1]
 message = sys.argv[2]
 
+searchOnlyCaptions = message.startswith('search-only-captions ')
+message = message[message.find(' ') + 1:]
+
 clientFilePath = f'users/{clientId}.txt'
 
 def write(s):
@@ -31,6 +34,8 @@ for file in os.listdir(path):
     if file.endswith('.zip'):
         zip = zipfile.ZipFile(path + file)
         for fileInZip in zip.namelist():
+            if searchOnlyCaptions and not fileInZip.endswith('.vtt'):
+                continue
             f = zip.open(fileInZip)
             for line in f.readlines():
                 if message in str(line):