From f0fdcf60a44429b95c3d6e262d6cdff37084c746 Mon Sep 17 00:00:00 2001
From: oscarz <oscar@vip.qq.com>
Date: Thu, 26 Jun 2025 09:29:03 +0800
Subject: [PATCH] modify scripts

---
 src/javbus/fetch.py | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/src/javbus/fetch.py b/src/javbus/fetch.py
index 1a93c53..07b9841 100644
--- a/src/javbus/fetch.py
+++ b/src/javbus/fetch.py
@@ -96,7 +96,7 @@ def fetch_movies_common(tbl):
         row_id = row['id']
         uncensored = row['uncensored'] if row['uncensored'] > 0 else None
         if not utils.is_valid_url(url):
-            logging.info(f'invalid url {url} in {tbl}, skipping...')
+            logging.info(f'invalid url ({url}) in {tbl}, row id: {row_id}. skipping...')
             continue
         # 去掉可下载的标志（如果有）
         next_url = url
@@ -163,8 +163,9 @@ def update_multilang_common(tbl):
 
     for row in url_list:
         url = row['href']
+        row_id = row['id']
         if not utils.is_valid_url(url):
-            logging.info(f'invalid url {url} in {tbl}, skipping...')
+            logging.info(f'invalid url ({url}) in {tbl}, row id: {row_id}. skipping...')
             continue
         langs_url = utils.generate_multilang_urls(url)
         for lang, next_url in langs_url.items():
@@ -216,8 +217,9 @@ def update_multilang_tags():
 
     for row in url_list:
         url = row['href']
+        row_id = row['id']
         if not utils.is_valid_url(url):
-            logging.info(f'invalid url {url}, skipping...')
+            logging.info(f'invalid url ({url}), row id: {row_id}. skipping...')
             continue
         langs_url = utils.generate_multilang_urls(url)
         for lang, next_url in langs_url.items():
@@ -292,6 +294,9 @@ def fetch_performers_detail():
             person = performer['name']
             uncensored = int(performer['uncensored'])
             avatar = None
+            if not utils.is_valid_url(url):
+                logging.info(f'invalid url ({url}), name: {person}. skipping...')
+                continue
 
             next_url = url
             all_movies = []
@@ -388,6 +393,10 @@ def fetch_movies_detail():
             title = movie['title']
             curr_id = movie['id']
             uncensored = int(movie['uncensored'])
+            if not utils.is_valid_url(url):
+                logging.info(f'invalid url ({url}), row id: {curr_id}. skipping...')
+                continue
+
             logging.debug(f"Fetching data for movie ({title}), url {url} ...")
             soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="container", attr_type="class"))
             # 从本地读取的文件，忽略