diff --git a/website/index.php b/website/index.php index 2d7fd93..ad2d919 100644 --- a/website/index.php +++ b/website/index.php @@ -13,7 +13,8 @@ Access raw data with: .
Access found channels with: .
- +
+
@@ -82,7 +83,7 @@ Progress: channels function search(event) { // We don't want to refresh the webpage which is the default behavior. event.preventDefault(); - const query = event.submitter.id + ' ' + document.getElementById('search').value; + const query = event.submitter.id + ' ' + document.getElementById('path-search').value + ' ' + 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 6d81556..b90e0e0 100755 --- a/website/search.py +++ b/website/search.py @@ -6,10 +6,11 @@ from io import StringIO path = '/mnt/HDD0/YouTube_captions_search_engine/channels/' clientId = sys.argv[1] -message = sys.argv[2] +pathSearchMessageParts = sys.argv[2].split(' ') +pathSearch = pathSearchMessageParts[1] +message = ' '.join(pathSearchMessageParts[2:]) -searchOnlyCaptions = message.startswith('search-only-captions ') -message = message[message.find(' ') + 1:] +searchOnlyCaptions = pathSearchMessageParts[0] == 'search-only-captions' clientFilePath = f'users/{clientId}.txt' @@ -41,8 +42,10 @@ for fileIndex, file in enumerate(files): endsWithVtt = fileInZip.endswith('.vtt') if searchOnlyCaptions and not endsWithVtt: continue + toWrite = f'{file}/{fileInZip}' + if not pathSearch in toWrite: + continue with zip.open(fileInZip) as f: - toWrite = f'{file}/{fileInZip}' if endsWithVtt: content = f.read().decode('utf-8') stringIOf = StringIO(content)