feat:ptt 后处理优化

pc_ptt.py

@@ -18,7 +18,12 @@ from utils.filse import save_json
 import os
 from config.settings import get_base_file_url
 from utils.download_image import download_image
+# ---------------   selenium 依赖 start ----------------
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
 
+# ---------------   selenium 依赖 end ----------------
 '''
 爬取台湾PTT论坛的热门帖子，包括帖子的标题、内容【文本、图片、视频】
 
@@ -28,7 +33,7 @@ from utils.download_image import download_image
 
 def reptile(browser=None, search_word=""):
     url = "https://www.ptt.cc/bbs/hotboards.html"
-    browser = browser or create(no_headless=True,using_user_data=True)
+    browser = browser or create(no_headless=True, using_user_data=True)
     # 有头模式执行
     # browser = browser or create()
     # 打开网页
@@ -39,10 +44,18 @@ def reptile(browser=None, search_word=""):
     length = len(classify_item_list)
     for index in range(length):
         # 暂时先爬取 第2个 分类
-        if 0 < index < 4:
+        if 0 <= index < 4:
             type_title = classify_item_list[index].text
             classify_item_list[index].click()
             time.sleep(0.1)
+            if index == 0:
+                try:
+                    button = browser.find_element("xpath", "//form/div[1]//button")
+                    button.click()
+                except:
+                    error = ""
+            wait = WebDriverWait(browser, 10)
+            wait.until(EC.presence_of_element_located((By.XPATH, "//div[@class='r-ent']")))
             element_list = browser.find_elements('xpath', "//div[@class='r-ent']//div[@class='title']//a")
             length_two = len(element_list)
             for index_two in range(length_two):
@@ -183,6 +196,8 @@ def reptile(browser=None, search_word=""):
                     element_list = browser.find_elements('xpath', "//div[@class='r-ent']//div[@class='title']//a")
             # 浏览器返回上一页
             browser.back()
+            if index == 0:
+                browser.back()
             time.sleep(0.1)
             # 重新获取
             classify_item_list = browser.find_elements('xpath', "//div[@class='board-class']")
@@ -214,6 +229,7 @@ def script_close(browser):
         log.debug("浏览器驱动关闭失败")
     sys.exit()
 
+
 def main():
     """