fix:ptt执行效率

pc_ptt.py

@@ -33,17 +33,15 @@ from selenium.webdriver.support import expected_conditions as EC
 
 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=False, using_user_data=True)
     # 有头模式执行
     # browser = browser or create()
     # 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']")
-    # log.debug(classify_item_list)
-    # classify_item_list = item_list.copy()
-    length = len(classify_item_list)
-    for index in range(length):
+
+    for index,item_element in enumerate(classify_item_list):
         # 暂时先爬取 第2个 分类
         if 0 <= index < 4:
             type_title = classify_item_list[index].text
@@ -62,23 +60,23 @@ def reptile(browser=None, search_word=""):
             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):
+
+            for index_two, item in enumerate(element_list):
                 # print(element_list[index_two].text)
                 try:
-                    re.findall("公告", element_list[index_two].text)
+                    re.findall("公告", item.text)
                 except IndexError:
                     log.debug(f"正在爬取分类：{type_title}-第{index_two + 1}条")
-                    print("当前连接："+str(browser.current_url))
-                    print(data[len(data)-1]["title"])
+                    print("当前连接：" + str(browser.current_url))
+                    print(data[len(data) - 1]["title"])
                 # 使用正则表达式进行匹配关键词
-                if re.findall(search_word, element_list[index_two].text):
+                if re.findall(search_word, item.text):
                     # log.debug(f"找到了匹配的字符串：{matches}")
                     error = ""
                 else:
-                    # log.debug("未找到匹配的字符串")
-                    # 退出本次迭代，进入下一次迭代
+                    # 本次迭代帖子标题未匹配关键词，退出本次迭代，进入下一次迭代
                     continue
+
                 # 标题不包含"公告"和"看板"
                 if re.findall("公告", element_list[index_two].text) or re.findall("看板", element_list[index_two].text):
                     a = 1
@@ -201,10 +199,13 @@ def reptile(browser=None, search_word=""):
                         "picture_url": ",".join(picture_url)
                     }
                     # --------------- 组装数据 end---------------------
+                    data.append(obj)
                     # 浏览器返回上一页
                     browser.back()
                     time.sleep(0.1)
                     element_list = browser.find_elements('xpath', "//div[@class='r-ent']//div[@class='title']//a")
+
+            print("循环结束")
             # 浏览器返回上一页
             browser.back()
             if index == 0:
@@ -224,11 +225,11 @@ def reptile(browser=None, search_word=""):
             log.debug('save file success')
         else:
             log.debug('save file failed')
-        # script_close(browser)
+        script_close(browser)
     else:
         # 爬取数据为空
         log.info("未爬取到数据")
-        # script_close(browser)
+        script_close(browser)
 
 
 def script_close(browser):