update

README.MD

@@ -16,10 +16,14 @@
 
 #### 使用说明
 1. cd ./crawler_zhufumao
-2. python3 ./main/run_xx.py
+2. sh zhufumao.sh
 
 
 #### 需求
+2022/12/21
+1. 祝福猫更换成长寿视频
+2. 增加过滤条件:标题相似度>=80%
+
 2022/11/19
 1. 运行时间: 13:00:00 - 16:59:59
 2. 推荐列表全抓

main/zhufumao_recommend.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # @Author: wangkun
 # @Time: 2022/11/15
+import difflib
 import os
 import shutil
 import sys
@@ -44,8 +45,8 @@ class Recommend:
                 'enableWebviewDetailsCollection': True,
                 'setWebContentsDebuggingEnabled': True,
                 'recreateChromeDriverSessions': True,
-                # 'chromedriverExecutable': '/Users/wangkun/Downloads/chromedriver_v86/chromedriver',
-                'chromedriverExecutable': '/Users/piaoquan/Downloads/chromedriver',
+                'chromedriverExecutable': '/Users/wangkun/Downloads/chromedriver_v86/chromedriver',
+                # 'chromedriverExecutable': '/Users/piaoquan/Downloads/chromedriver',
                 "chromeOptions": {"androidProcess": "com.tencent.mm:appbrand0"},
                 'browserName': ''
             }
@@ -71,8 +72,8 @@ class Recommend:
                          int(size['width'] * 0.5), int(size['height'] * 0.8), 200)
             # 打开小程序"祝福猫视频"
             time.sleep(3)
-            Common.logger(log_type).info('打开小程序"祝福猫视频"')
-            driver.find_elements(By.XPATH, '//*[@text="祝福猫视频"]')[-1].click()
+            Common.logger(log_type).info('打开小程序"长寿视频"')
+            driver.find_elements(By.XPATH, '//*[@text="长寿视频"]')[-1].click()
             cls.get_recommend(log_type, driver, env)
             cls.quit(log_type, driver)
         except Exception as e:
@@ -208,6 +209,18 @@ class Recommend:
             cls.quit(log_type, driver)
             cls.start_wechat(log_type, env)
 
+    @classmethod
+    def title_like(cls, log_type, title):
+        sheet = Feishu.get_values_batch(log_type, 'zhufumao', 'e13bdf')
+        for i in range(1, len(sheet)):
+            video_title = sheet[i][7]
+            if video_title is None:
+                pass
+            elif difflib.SequenceMatcher(None, title, video_title).quick_ratio() >= 0.8:
+                return True
+            else:
+                pass
+
     @classmethod
     def download_publish(cls, log_type, driver: WebDriver, video_element, video_title, cover_url, env):
         try:
@@ -215,6 +228,8 @@ class Recommend:
                 Common.logger(log_type).info('无效视频\n')
             elif video_title in [x for y in Feishu.get_values_batch(log_type, 'zhufumao', 'e13bdf') for x in y]:
                 Common.logger(log_type).info('视频已下载\n')
+            elif cls.title_like(log_type, video_title) is True:
+                Common.logger(log_type).info('标题相似度>=80%:{}\n', video_title)
             elif any(word if word in video_title else False for word in cls.filter_words(log_type)) is True:
                 Common.logger(log_type).info('已中过滤词\n')
             else: