feat:dcard debug

pc_dcard.py

@@ -6,7 +6,7 @@ from utils.createBrowserDriver import create
 from utils.filse import save_json
 from api.index import importJson, getReptileTask, importJsonPath
 from utils.index import convert_to_traditional, yt_dlp_download, convert_string_to_time, parse_twitter_time_string, \
-    is_base64_image, save_base64_image, get_screen_resolution,create_directory_if_not_exists, delete_directory
+    is_base64_image, save_base64_image, get_screen_resolution, create_directory_if_not_exists, delete_directory
 # from pytube import YouTube
 from selenium.common.exceptions import NoSuchElementException
 import os
@@ -35,55 +35,56 @@ def reptile(browser=None, search_word=""):
     """
     print(f"搜索词:{search_word}")
     base_url = "https://www.dcard.tw"
-    browser = browser or create(no_headless=False, using_user_data=True)
+    # Chrome 无痕模式选项
+    # option=["--incognito"]
+    browser = browser or create(no_headless=False, using_user_data=False)
     # 打开网页
     browser.get(f"{base_url}/search?query={search_word}")
     time.sleep(6)
     # 滚动一页
     # 使用 JavaScript 将网页滚动到底部
     # browser.execute_script("window.scrollTo(0, document.body.scrollHeight);")
-    # time.sleep(6)
-    base_xpath = "//div[@role='main']//div[@data-key]//article"
+    # time.sleep(3)
     # 内容块
-    element_content_list = browser.find_elements('xpath', base_xpath)
-    # 作者
-    element_authors_list = browser.find_elements('xpath', f"{base_xpath}/div[1]/div[1]/div[2]/div/div[1]")
-    # 时间
-    element_time_list = browser.find_elements('xpath', f"{base_xpath}/div[1]/div[1]/div[2]/div/div[2]/time")
-    # 标题
-    element_title_list = browser.find_elements('xpath', f"{base_xpath}//h2")
-    # 点赞
-    # element_like_list = browser.find_elements('xpath', f"{base_xpath}/div[3]/div[1]/div/div[2]")
-    # 评论
-    # element_comment_list = browser.find_elements('xpath', f"{base_xpath}/div[3]/div[2]/div/span")
+    element_content_list = browser.find_elements('xpath', "//div[@role='main']//article")
 
-    for index,item in enumerate(element_content_list):
+    for index, item in enumerate(element_content_list):
+        # 点赞
+        # element_like_list = browser.find_elements('xpath', f"{base_xpath}/div[3]/div[1]/div/div[2]")
+        # 评论
+        # element_comment_list = browser.find_elements('xpath', f"{base_xpath}/div[3]/div[2]/div/span")
+        # 时间
+        # element_time_list = browser.find_elements('xpath', f"{base_xpath}/div[1]/div[1]/div[2]/div/div[2]/time")
         # 提取时间,并转为时间戳
-        timestamp = datetime.fromisoformat(element_time_list[index].get_attribute("datetime")[:-1]).timestamp()
+        tag = item.find_element('xpath', ".//time")
+        timestamp_str = tag.get_attribute("datetime")[:-1]
+        timestamp = datetime.fromisoformat(timestamp_str).timestamp()
 
         # 过滤时间
         # # 如果'releaseTime'不是整数，则将其转换为整数
         new_releaseTime = int(timestamp)
+        print(f"开始时间：{beginFiltrationTime};结束时间：{endFiltrationTime};当前时间：{new_releaseTime}")
         if new_releaseTime < beginFiltrationTime or new_releaseTime > endFiltrationTime:
             # 如果'new_releaseTime'不在指定范围内，则跳过当前迭代，继续下一个项目
             continue
 
         # 提取作者
-        author = element_authors_list[index].text
+        author = item.find_element('xpath', f"./div[1]/div[1]/div[2]/div/div[1]")
         # 提取标题
-        title = element_title_list[index].text
+        title = item.find_element('xpath', f".//h2")
         # 提取点赞
         # like = element_like_list[index].text
         # 提取评论
         # comment = element_comment_list[index].text
 
         # -------------提取内容---------------
-        element_content_list[index].click()
+        item.click()
+        # browser.execute_script("arguments[0].click();", item)
         # 等待弹窗内容出现，设置最长等待时间为10秒
         wait = WebDriverWait(browser, 10)
         # 通过 expected_conditions 来定义等待条件，这里以弹窗内容的某个元素为例
         wait.until(EC.presence_of_element_located((By.XPATH, "//div[@data-testid='overlay']")))
-        time.sleep(3)
+        # time.sleep(3)
         click_dom = browser.find_element("xpath",
                                          "//div[@data-testid='overlay']")
         # 处理弹窗内容加载失败的情况
@@ -221,7 +222,6 @@ def script_close(browser):
         print("sys.exit() 执行失败")
 
 
-
 def main():
     """