去掉sehuat自动处理

main.py

@@ -110,9 +110,9 @@ def jobs(robot: Robot):
         await robot.generate_and_send_ranking()
 
     # ✅ 每天 15:30 发涩图 PDF
-    @async_job.at_times(["15:30"])
-    async def sehuatang_pdf_job():
-        await robot.generate_sehuatang_pdf()
+    # @async_job.at_times(["15:30"])
+    # async def sehuatang_pdf_job():
+    #     await robot.generate_sehuatang_pdf()
 
     # ✅ 每天 01:30 下载秀人网帖子
     @async_job.at_times(["01:30"])

utils/sehuatang/sehuatang_bot.py

@@ -7,6 +7,8 @@ from selenium import webdriver
 from selenium.webdriver.chrome.service import Service
 from selenium.webdriver.common.by import By
 from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
 from webdriver_manager.chrome import ChromeDriverManager
 from bs4 import BeautifulSoup
 from loguru import logger
@@ -15,7 +17,7 @@ from datetime import datetime, timedelta
 # ================= 配置区域 =================
 
 # 运行模式: 'full' (全量) 或 'daily' (增量)
-RUN_MODE = 'full'
+RUN_MODE = 'daily'
 
 DB_CONFIG = {
     'host': '192.168.2.41',
@@ -111,9 +113,16 @@ class SehuatangCrawler:
         options = Options()
         # options.add_argument('--headless')
         options.add_argument('--disable-gpu')
+        options.add_argument('--headless')  # 使用新的headless模式
         options.add_argument('--no-sandbox')
         options.add_argument('--disable-dev-shm-usage')
         options.add_argument('--blink-settings=imagesEnabled=false')
+        options.add_argument('--disable-logging')
+        options.add_argument('--log-level=3')
+        options.add_argument('--disable-blink-features=AutomationControlled')
+        options.add_experimental_option('excludeSwitches', ['enable-automation', 'enable-logging'])
+        options.add_experimental_option('useAutomationExtension', False)
+        options.add_argument('user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36')
 
         if os.name == 'nt':
             chrome_driver_path = os.path.join(os.getcwd(), "utils", "chromedriver", "chromedriver.exe")
@@ -123,24 +132,28 @@ class SehuatangCrawler:
         try:
             if os.name == 'nt' and not os.path.exists(chrome_driver_path):
                 chrome_driver_path = ChromeDriverManager().install()
-            service = Service(chrome_driver_path)
+            service = Service(chrome_driver_path, log_path=os.devnull)
             driver = webdriver.Chrome(service=service, options=options)
         except Exception:
             chrome_driver_path = ChromeDriverManager().install()
-            driver = webdriver.Chrome(service=Service(chrome_driver_path), options=options)
+            driver = webdriver.Chrome(service=Service(chrome_driver_path, log_path=os.devnull), options=options)
+        driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {"source": "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})"})
         return driver
 
     def bypass_age_verification(self):
         try:
-            self.driver.get("https://www.sehuatang.org/forum.php")
-            time.sleep(2)
+            self.driver.get("https://www.sehuatang.org/")
             try:
-                enter_button = self.driver.find_element(By.XPATH, '//a[contains(text(), "满18岁")]')
-                enter_button.click()
+                btn = WebDriverWait(self.driver, 6).until(EC.element_to_be_clickable((By.XPATH, '//a[contains(text(), "满18岁，请点此进入")]')))
+                btn.click()
                 logger.success("通过年龄验证")
-                time.sleep(2)
             except Exception:
-                pass
+                try:
+                    btn2 = WebDriverWait(self.driver, 4).until(EC.element_to_be_clickable((By.XPATH, '//a[contains(text(), "满18岁")]')))
+                    btn2.click()
+                    logger.success("通过年龄验证")
+                except Exception:
+                    pass
         except Exception as e:
             logger.warning(f"主页访问异常: {e}")
 
@@ -337,7 +350,7 @@ class SehuatangCrawler:
 
             try:
                 self.driver.get(list_url)
-                time.sleep(0.5)
+                WebDriverWait(self.driver, 10).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, 'tbody[id^="normalthread"]')))
 
                 soup = BeautifulSoup(self.driver.page_source, 'html.parser')
                 threads = soup.find_all('tbody', {'id': lambda x: x and x.startswith('normalthread')})
@@ -419,4 +432,4 @@ class SehuatangCrawler:
 
 if __name__ == "__main__":
     crawler = SehuatangCrawler()
-    crawler.run()
+    crawler.run()