From d4d695c747cba4cdee92982833f3f27f81a4d43c Mon Sep 17 00:00:00 2001 From: naibo Date: Sun, 9 Jul 2023 01:44:35 +0800 Subject: [PATCH] V0.3.5 --- .../EasySpider_windows_x64/Code/easyspider_executestage.py | 5 ++++- .temp_to_pub/compress.py | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/.temp_to_pub/EasySpider_windows_x64/Code/easyspider_executestage.py b/.temp_to_pub/EasySpider_windows_x64/Code/easyspider_executestage.py index 62ff0d1..e4df6ae 100644 --- a/.temp_to_pub/EasySpider_windows_x64/Code/easyspider_executestage.py +++ b/.temp_to_pub/EasySpider_windows_x64/Code/easyspider_executestage.py @@ -1144,7 +1144,10 @@ class BrowserThread(Thread): # 提取数据事件 def getData(self, para, loopElement, isInLoop=True, parentPath="", index=0): - pageHTML = etree.HTML(self.browser.page_source) + try: + pageHTML = etree.HTML(self.browser.page_source) + except: + pageHTML = "" if loopElement != "": # 只在数据在循环中提取时才需要获取循环元素 try: loopElementOuterHTML = loopElement.get_attribute('outerHTML') diff --git a/.temp_to_pub/compress.py b/.temp_to_pub/compress.py index a4750a0..b929fce 100644 --- a/.temp_to_pub/compress.py +++ b/.temp_to_pub/compress.py @@ -65,7 +65,7 @@ if __name__ == "__main__": os.remove("./EasySpider_windows_x64/mysql_config.json") os.mkdir("./EasySpider_windows_x64/Data") os.mkdir("./EasySpider_windows_x64/execution_instances") - # compress_folder_to_7z_split("./EasySpider_windows_x64", file_name) + compress_folder_to_7z_split("./EasySpider_windows_x64", file_name) print(f"Compress {file_name} Split successfully!") compress_folder_to_7z("./EasySpider_windows_x64", file_name) print(f"Compress {file_name} successfully!")