demo

Author: monkey2025-coder

AutoScraperX.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: AutoScraperX
-Version: 0.1.0
+Version: 0.1.1
 Summary: A common spider tool based on Selenium
 Home-page: https://github.com/chenziying1/AutoScraperX
 Author: czy
@@ -42,7 +42,7 @@ pip install selenium undetected-chromedriver beautifulsoup4
 ### 初始化爬虫
 
 ```
-from common_spider import Spider
+from AutoScraperX import common_spider  # 确保 Spider 类已正确导入
 
 options = {
     'headless': True,  # 以无头模式运行
@@ -51,7 +51,7 @@ options = {
     'driver_executable_path': "C:\\Path\\To\\chromedriver.exe"
 }
 
-spider = Spider(options)
+spider = common_spider.Spider(options)
 ```
 
 ### 打开网页

AutoScraperX/common_spider.py

@@ -90,7 +90,7 @@ def __init__(self, options: dict = {}, path: str=None, name: str = None):
             defualt_options.add_argument('--start-maximized')
 
         # 设置浏览器选项
-        defualt_options.binary_location = options.get('binary_location', "C:\Users\Administrator\AppData\Local\Google\Chrome\Bin\chrome.exe")
+        defualt_options.binary_location = options.get('binary_location', r"C:\Users\Administrator\AppData\Local\Google\Chrome\Bin\chrome.exe")
 
         if options.get('fastest', False):
             defualt_options.add_argument("--disable-extensions")

README.md

@@ -27,7 +27,7 @@ pip install selenium undetected-chromedriver beautifulsoup4
 ### 初始化爬虫
 
 ```
-from common_spider import Spider
+from AutoScraperX import common_spider  # 确保 Spider 类已正确导入
 
 options = {
     'headless': True,  # 以无头模式运行
@@ -36,7 +36,7 @@ options = {
     'driver_executable_path': "C:\\Path\\To\\chromedriver.exe"
 }
 
-spider = Spider(options)
+spider = common_spider.Spider(options)
 ```
 
 ### 打开网页

build/lib/AutoScraperX/common_spider.py

@@ -90,7 +90,7 @@ def __init__(self, options: dict = {}, path: str=None, name: str = None):
             defualt_options.add_argument('--start-maximized')
 
         # 设置浏览器选项
-        defualt_options.binary_location = options.get('binary_location', "C:\Users\Administrator\AppData\Local\Google\Chrome\Bin\chrome.exe")
+        defualt_options.binary_location = options.get('binary_location', r"C:\Users\Administrator\AppData\Local\Google\Chrome\Bin\chrome.exe")
 
         if options.get('fastest', False):
             defualt_options.add_argument("--disable-extensions")

dist/AutoScraperX-0.1.0-py3-none-any.whl

@@ -2,7 +2,7 @@
 
 setup(
     name="AutoScraperX",  # 你的库名称
-    version="0.1.0",  # 版本号
+    version="0.1.1",  # 版本号
     author="czy",
     author_email="1060324818@qq.com",
     description="A common spider tool based on Selenium",

dist/AutoScraperX-0.1.1-py3-none-any.whl

@@ -8,17 +8,22 @@
 email      :1060324818@qq.com
 '''
 
-from AutoScraperX import Spider  # 确保 Spider 类已正确导入
+from AutoScraperX import common_spider  # 确保 Spider 类已正确导入
 
 def main():
     # 创建 Spider 实例
-    spider = Spider(
-        headless=True,  # 是否无头模式运行
-        proxy=None,  # 可选代理设置
-        timeout=10,  # 超时时间（秒）
-        user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
-        wait_time=5  # 页面加载后等待时间
-    )
+    # 配置爬虫选项
+    options = {
+        "driver_executable_path": "chromedriver\\chromedriver.exe",  # 替换为你的 chromedriver 路径
+        "user_data_dir": "data\\User Data",  # Chrome 用户数据路径
+        "profile_directory": "Default",  # Chrome 配置文件
+        "headless": False,  # 是否启用无头模式（True = 不显示浏览器窗口）
+        "maximized": True,  # 是否最大化窗口
+        "logging_level": 2  # 日志级别
+    }
+
+    # 创建 Spider 实例
+    spider = common_spider.Spider(options=options)
 
     try:
         # 打开网页