fix：去除富文本转义符号

pc_twitter.py

-# # 导入依赖库
+import json
 import time
-from telnetlib import EC
-
 from bs4 import BeautifulSoup
-from selenium.webdriver.common.by import By
-from selenium.webdriver.support.wait import WebDriverWait
-
+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
+# from pytube import YouTube
+import os
+from config.settings import get_base_file_url
 
 # 工具函数-下载图片
 '''
@@ -14,36 +16,30 @@ from utils.createBrowserDriver import create
 '''
 
 
-def reptile(browser):
-    # # json 数据
-    data = []
-    image_key = 0
-    fileDir = "./reptile_data/news/nytimes/"
-    # year = datetime(2021, 1, 1)
-    # startDate = datetime(2020, 12, 31)  # 初始日期
-    # endDate = datetime(2020, 12, 31)  # 结束日期
+def reptile(browser=None, search_word=""):
     url = "https://twitter.com/"
-    browser = browser or create(False)
-    print(browser)
+    option = ['--headless']
+    # ['--headless']
+    browser = browser or create()
+    # print(browser)
     # browser = webdriver.Firefox(executable_path='/usr/local/bin/geckodriver')
     # endDate = startDate = startDate + timedelta(days=i)
     # 打开网页
     browser.get(url)
-
     # WebDriverWait(browser,10).
     # 打开登录窗口
-    open_button_login = WebDriverWait(browser, 10).until(
-        EC.presence_of_element_located((By.XPATH, "//a[@data-testid='login']")))
-    open_button_login.click()
-    time.sleep(5)
+    # open_button_login = WebDriverWait(browser, 10).until(
+    #     EC.presence_of_element_located((By.XPATH, "//a[@data-testid='login']")))
+    # open_button_login.click()
+    # time.sleep(5)
 
     # 获取账号密码输入框
-    input_email_element = WebDriverWait(browser, 10).until(
-        EC.presence_of_element_located((By.XPATH, "//input[@autocomplete='username']")))
-    # 获取下一步按钮
-    buttons = WebDriverWait(browser, 10).until(EC.presence_of_all_elements_located((By.XPATH, "//div[@role='button']")))
-    for item in buttons:
-        print(BeautifulSoup(item, 'html.parser'))
+    # input_email_element = WebDriverWait(browser, 10).until(
+    #     EC.presence_of_element_located((By.XPATH, "//input[@autocomplete='username']")))
+    # # 获取下一步按钮
+    # buttons = WebDriverWait(browser, 10).until(EC.presence_of_all_elements_located((By.XPATH, "//div[@role='button']")))
+    # for item in buttons:
+    #     print(BeautifulSoup(item, 'html.parser'))
     # soup = BeautifulSoup(page_content, 'html.parser')
     # input_pwd_element = WebDriverWait(browser, 10).until(EC.presence_of_element_located((By.XPATH, "//input[@name='pass']")))
     # # 获取登录按钮
@@ -68,8 +64,8 @@ def reptile(browser):
     #         break
     # time.sleep(3)
     # 获取完整的分页数据
-    page_content = browser.page_source
-    soup = BeautifulSoup(page_content, 'html.parser')
+    # page_content = browser.page_source
+    # soup = BeautifulSoup(page_content, 'html.parser')
     # print("----------")
     # print(soup)
     # list_news = soup.find_all('li', {"class": "css-1l4w6pd"})
@@ -105,6 +101,34 @@ def reptile(browser):
     # with open(f'{fileDir}data.json', "w", encoding="utf-8") as file:
     #     json.dump(data, file, indent=2, ensure_ascii=False)
 
-    browser.close()
-    # 关闭浏览器驱动
-    browser.quit()
+    # browser.close()
+    # # 关闭浏览器驱动
+    # browser.quit()
+
+
+def main():
+    """
+
+    """
+    # 请求关键词
+    response = getReptileTask()
+    # print(response)
+    if response['status_code'] == 200 and response['data']['code'] == 200:
+        log.debug("call success")
+        search_word = ""
+        for item in response['data']['rows']:
+            if item['name'] == 'twitter':
+                search_word = item['keyword']
+                table_name = item['tableName']
+        reptile(None, convert_to_traditional(search_word))
+    else:
+        log.debug("call failed")
+        reptile(None, '')
+        # upload_control()
+
+
+# 全局变量
+data = []
+table_name = "pms_twitter"
+# 调用main函数
+main()
\ No newline at end of file

pc_youtube.py

@@ -29,7 +29,7 @@ def reptile(browser=None, search_word=""):
     # print(classify_item_list)
     length = len(classify_video_list)
     for index in range(length):
-        if 0 < index < 2:
+        if -1 < index < length:
             title = classify_video_list[index].get_attribute('title')
             link = classify_video_list[index].get_attribute('href')
             # yt = YouTube(link)
@@ -47,7 +47,7 @@ def reptile(browser=None, search_word=""):
                 # 组装数据
                 obj = {
                     "title": title,
-                    "content": f"<video src='{file_http_src}'></video>",
+                    "content": f"<video controls style='width:100%' src='{file_http_src}'></video>",
                     "videoUrl": file_http_src,
                     "link": link,
                     "reptileTime": str(int(time.time())),