fix:ptt debug

pc_ptt.py

@@ -39,8 +39,9 @@ def reptile(browser=None, search_word=""):
     # 打开网页
     browser.get(url)
     # log.debug("已打开浏览器")
-    classify_item_list = browser.find_elements('xpath', "//div[@class='board-class']")
+    item_list = browser.find_elements('xpath', "//div[@class='board-class']")
     # log.debug(classify_item_list)
+    classify_item_list = item_list.copy()
     length = len(classify_item_list)
     for index in range(length):
         # 暂时先爬取 第2个 分类
@@ -209,7 +210,7 @@ def reptile(browser=None, search_word=""):
                 browser.back()
             time.sleep(0.1)
             # 重新获取
-            classify_item_list = browser.find_elements('xpath', "//div[@class='board-class']")
+            # classify_item_list = browser.find_elements('xpath', "//div[@class='board-class']")
 
     # 发送爬取数据到java服务
     # print('----------------------')

test.py

-# set options to be headless, ..
-from selenium import webdriver
-options = webdriver.ChromeOptions()
-options.add_argument('--headless')
-options.add_argument('--no-sandbox')
-options.add_argument('--disable-dev-shm-usage')
-
-# open it, go to a website, and get results
-wd = webdriver.Chrome(options=options)
-wd.get("https://www.youtube.com/results?search_query=俄乌战争")
-
-print(wd.page_source)  # results
+classify_item_list = browser.find_elements('xpath', "//div[@class='board-class']")
+# log.debug(classify_item_list)
+length = len(classify_item_list)
+for index in range(length):
+    # 暂时先爬取 第2个 分类
+    if 0 <= index < 4:
+        type_title = classify_item_list[index].text
+        classify_item_list[index].click()
+        time.sleep(0.1)
+        for index_two in range(length_two):
+            print(element_list[index_two].text)
+        # 浏览器返回上一页
\ No newline at end of file
+        browser.back()
+        if index == 0:
+            browser.back()
+        time.sleep(0.1)
+        classify_item_list = browser.find_elements('xpath', "//div[@class='board-class']")
\ No newline at end of file