fix：facebook 富文本删除视频相关html标签，增加video标签占位

config/settings.py

@@ -3,7 +3,7 @@ def get_log_path():
     return "../"
 
 def get_base_url():
-    return "http://192.168.0.127:8081/"
+    return "http://192.168.0.118:8081/"
 
 def get_base_file_url():
-    return "http://192.168.0.127:8186/"
\ No newline at end of file
+    return "http://192.168.0.118:8186/"
\ No newline at end of file

pc_facebook.py

@@ -5,7 +5,7 @@ from utils.Logger import log
 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_time_string
+from utils.index import convert_to_traditional, yt_dlp_download, convert_string_to_time, parse_time_string
 # from pytube import YouTube
 from datetime import datetime
 import os
@@ -25,7 +25,7 @@ def reptile(browser=None, search_word=""):
     browser.get(url)
     try:
         # 检测是否要登录
-        login_input = browser.find_element('xpath',"//input[@name='email']")
+        login_input = browser.find_element('xpath', "//input[@name='email']")
         password_input = browser.find_element('xpath', "//input[@name='pass']")
         login_input.send_keys("liyang19970814@gmail.com")
         password_input.send_keys("xn89kiPT/^Kaeg#")
@@ -34,37 +34,74 @@ def reptile(browser=None, search_word=""):
         button_login.click()
         time.sleep(3)
     except:
-        print("error")
+        print("已登录")
     url = f"https://www.facebook.com/search/top?q={search_word}"
     browser.get(url)
     # 使用 JavaScript 将网页滚动到底部
     browser.execute_script("window.scrollTo(0, document.body.scrollHeight);")
     time.sleep(3)
-    # 帖子块集合
-    elements = browser.find_elements('xpath',"//div[@role='feed']/div//div[@aria-describedby]")
+
+    # 内容
+    element_content_list = browser.find_elements('xpath',
+                                                 "//div[@role='feed']/div//div[@aria-describedby]/div/div/div/div/div/div[2]/div/div/div[3]")
     # 作者
-    element_authors_list = browser.find_elements('xpath',
-                                          "//div[@role='feed']/div//div[@aria-describedby]//h3/span[1]")
+    element_authors_list = browser.find_elements('xpath', "//div[@role='feed']/div//div[@aria-describedby]//h3/span[1]")
     # 发布时间
     element_release_list = browser.find_elements('xpath',
                                                  "//div[@role='feed']/div//div[@aria-describedby]//span[@dir]/span//a[@role='link' and @aria-label]")
     # 查找所有 展开 按钮，循环点击后在查找内容
-    elements_expand_list = browser.find_elements('xpath',"//div[@role='feed']/div//div[@aria-describedby]//div[@role='button' and text()='展开']")
-    for item in elements_expand_list:
-        item.click()
-    # 内容
-    element_content_list = browser.find_elements('xpath',"//div[@role='feed']/div//div[@aria-describedby]/div/div/div/div/div/div[2]/div/div/div[3]")
-    # print(element_content_list)
-    length = len(elements)
+    elements_expand_list = browser.find_elements('xpath',
+                                                 "//div[@role='feed']/div//div[@aria-describedby]//div[@role='button' and text()='展开']")
+    for key, element in enumerate(elements_expand_list):
+        try:
+            # 使用JavaScript 执行点击操作
+            browser.execute_script("arguments[0].click();", element)
+        except Exception as e:
+            print("Clicking element failed: " + str(e))
+
+    length = len(element_content_list)
     # print(length)
     for index in range(length):
         author = element_authors_list[index].text
-        release_time = str(int(parse_time_string(element_release_list[index].text)))
-        content = element_content_list[index].get_attribute("outerHTML")
+        # print(element_release_list[index].text)
+        # print(parse_time_string(element_release_list[index].text))
+        release_time_timestamp = int(parse_time_string(element_release_list[index].text))
+        release_time = str(release_time_timestamp)
+        # release_time = ""
+        # content = element_content_list[index].get_attribute("outerHTML")
         # 使用BeautifulSoup解析HTML
-        soup = BeautifulSoup(element_content_list[index].get_attribute('innerHTML'), 'html.parser')
+        text = element_content_list[index].text
+        soup = BeautifulSoup(element_content_list[index].get_attribute('outerHTML'), 'html.parser')
+        soup_str = soup.prettify()
+        # 查找是否含有视频
+        # ignore_list = soup.find_all("div", {"data-visualcompletion": "video"})
+        video_list = soup.find_all("video")
+        # lth = len(ignore_list)
+        if len(video_list) > 0:
+            # 删除第二个子元素
+            # 找到包含两个 <div> 元素的父级元素
+            parent_div = soup.find('div')
+            # 找到所有的 <div> 子元素
+            div_elements = parent_div.find_all('div', recursive=False)
+            # div_tags = soup.find_all("div", recursive=False)
+            # 确保列表中至少有两个 <div> 子元素
+            if len(div_elements) >= 2:
+                # 获取第二个 <div> 元素，并将其从父级元素中移除
+                div_to_remove = div_elements[1]
+                div_to_remove.extract()
+                # 删除
+                # div.decompose()
+                # 创建video标签占位
+                custom_video = soup.new_tag("video")
+                custom_video["src"] = ""
+                parent_div.append(custom_video)
+        else:
+            print("")
+
+        content = soup.prettify()
         # 标题取：作者+日期
-        title = f"{author}-{datetime.fromtimestamp(int(parse_time_string(element_release_list[index].text)))}"
+        title = f"{author}-{datetime.fromtimestamp(release_time_timestamp)}"
+        # title = ""
         # ---------------- 判断类型 start ----------
         # 类型
         content_type = ""
@@ -183,6 +220,7 @@ def reptile(browser=None, search_word=""):
 
     browser.quit()
 
+
 def main():
     """
 

utils/index.py

@@ -38,9 +38,9 @@ def parse_time_string(time_str):
     else:
         try:
             datetime_str = time_str.replace("月", " ").replace("日", "")
-            month, day, hour, minute = map(int, datetime_str.split())
+            month, day = map(int, datetime_str.split())
             current_year = datetime.datetime.now().year
-            datetime_obj = datetime.datetime(year=current_year, month=month, day=day, hour=hour, minute=minute)
+            datetime_obj = datetime.datetime(year=current_year, month=month, day=day)
             return int(datetime_obj.timestamp())
         except ValueError:
             return None