From 5aedfb0baa930c12a29e3f9a3e6467b5d2077e82 Mon Sep 17 00:00:00 2001 From: yoshiko2 Date: Sun, 22 May 2022 23:14:47 +0800 Subject: [PATCH] Fix japanese number parse --- WebCrawler/__init__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/WebCrawler/__init__.py b/WebCrawler/__init__.py index 2efa04c..cb15ef0 100644 --- a/WebCrawler/__init__.py +++ b/WebCrawler/__init__.py @@ -86,7 +86,7 @@ def get_data_from_json(file_number, oCC): sources = insert(sources,"carib") elif "item" in file_number: sources = insert(sources,"getchu") - elif "rj" in lo_file_number or "vj" in lo_file_number or re.match(r"[\u30a0-\u30ff]+", file_number): + elif "rj" in lo_file_number or "vj" in lo_file_number or re.match(r"[\u3040-\u309F\u30A0-\u30FF]+", file_number): sources = insert(sources, "getchu") sources = insert(sources, "dlsite") elif re.match(r"^\d{5,}", file_number) or "heyzo" in lo_file_number: