xiaoniangao_plus_by_ljh

common/public.py

@@ -111,8 +111,7 @@ def get_config_from_mysql(log_type, source, env, text, action=''):
 def get_rule_from_mysql(task_id, log_type, crawler, env):
     select_rule_sql = f"""select rule from crawler_task_v3 where id={task_id}"""
     rule_list = MysqlHelper.get_values(log_type, crawler, select_rule_sql, env, action="")
-    # print(rule_list)
-    return rule_list
+    return json.loads(rule_list[0]['rule'])
 
 
 def random_title(log_type, crawler, env, text):

xiaoniangaoplus/xiaoniangaoplus/xiaoniangao_plus_scheduling2.py

@@ -168,135 +168,137 @@ class XiaoNianGaoPlusRecommend:
         element_list = [i for i in video_list][index:]
         return element_list[0]
 
-    def get_video_info(self, video_element):
-        try:
-            Common.logger(self.log_type, self.crawler).info(f"本轮已抓取{self.download_cnt}条视频\n")
-            # Common.logging(self.log_type, self.crawler, self.env, f"本轮已抓取{self.download_cnt}条视频\n")
-            if self.download_cnt >= int(self.rule_dict.get("videos_cnt", {}).get("min", 10)):
-                self.count = 0
-                self.download_cnt = 0
-                self.element_list = []
-                return
-            self.count += 1
-            Common.logger(self.log_type, self.crawler).info(f"第{self.count}条视频")
-            # Common.logging(self.log_type, self.crawler, self.env, f"第{self.count}条视频")
-            # 标题
-            video_title = video_element.find("wx-view", class_="dynamic--title").text
-            # 播放量字符串
-            play_str = video_element.find("wx-view", class_="dynamic--views").text
-            info_list = video_element.findAll("wx-view", class_="dynamic--commerce-btn-text")
-            # 点赞数量
-            like_str = info_list[1].text
-            # 评论数量
-            comment_str = info_list[2].text
-            # 视频时长
-            duration_str = video_element.find("wx-view", class_="dynamic--duration").text
-            user_name = video_element.find("wx-view", class_="dynamic--nick-top").text
-            # 头像 URL
-            avatar_url = video_element.find("wx-image", class_="avatar--avatar")["src"]
-            # 封面 URL
-            cover_url = video_element.find("wx-image", class_="dynamic--bg-image")["src"]
-            play_cnt = int(play_str.replace("+", "").replace("次播放", ""))
-            duration = int(duration_str.split(":")[0].strip()) * 60 + int(duration_str.split(":")[-1].strip())
-            if "点赞" in like_str:
-                like_cnt = 0
-            elif "万" in like_str:
-                like_cnt = int(like_str.split("万")[0]) * 10000
-            else:
-                like_cnt = int(like_str)
-            if "评论" in comment_str:
-                comment_cnt = 0
-            elif "万" in comment_str:
-                comment_cnt = int(comment_str.split("万")[0]) * 10000
-            else:
-                comment_cnt = int(comment_str)
-            out_video_id = md5(video_title.encode('utf8')).hexdigest()
-            out_user_id = md5(user_name.encode('utf8')).hexdigest()
-
-            video_dict = {
-                "video_title": video_title,
-                "video_id": out_video_id,
-                "duration_str": duration_str,
-                "duration": duration,
-                "play_str": play_str,
-                "play_cnt": play_cnt,
-                "like_str": like_str,
-                "like_cnt": like_cnt,
-                "comment_cnt": comment_cnt,
-                "share_cnt": 0,
-                "user_name": user_name,
-                "user_id": out_user_id,
-                'publish_time_stamp': int(time.time()),
-                'publish_time_str': time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(int(time.time()))),
-                "avatar_url": avatar_url,
-                "cover_url": cover_url,
-                "session": f"xiaoniangao-{int(time.time())}"
-            }
-            for k, v in video_dict.items():
-                Common.logger(self.log_type, self.crawler).info(f"{k}:{v}")
-            Common.logging(self.log_type, self.crawler, self.env, f"video_dict:{video_dict}")
-            # Common.logger(self.log_type, self.crawler).info(f"==========分割线==========\n")
+    def get_video_info_2(self, video_element):
+        Common.logger(self.log_type, self.crawler).info(f"本轮已抓取{self.download_cnt}条视频\n")
+        # Common.logging(self.log_type, self.crawler, self.env, f"本轮已抓取{self.download_cnt}条视频\n")
+        if self.download_cnt >= int(self.rule_dict.get("videos_cnt", {}).get("min", 10)):
+            self.count = 0
+            self.download_cnt = 0
+            self.element_list = []
+            return
+        self.count += 1
+        Common.logger(self.log_type, self.crawler).info(f"第{self.count}条视频")
+        # Common.logging(self.log_type, self.crawler, self.env, f"第{self.count}条视频")
+        # 标题
+        video_title = video_element.find("wx-view", class_="dynamic--title").text
+        # 播放量字符串
+        play_str = video_element.find("wx-view", class_="dynamic--views").text
+        info_list = video_element.findAll("wx-view", class_="dynamic--commerce-btn-text")
+        # 点赞数量
+        like_str = info_list[1].text
+        # 评论数量
+        comment_str = info_list[2].text
+        # 视频时长
+        duration_str = video_element.find("wx-view", class_="dynamic--duration").text
+        user_name = video_element.find("wx-view", class_="dynamic--nick-top").text
+        # 头像 URL
+        avatar_url = video_element.find("wx-image", class_="avatar--avatar")["src"]
+        # 封面 URL
+        cover_url = video_element.find("wx-image", class_="dynamic--bg-image")["src"]
+        play_cnt = int(play_str.replace("+", "").replace("次播放", ""))
+        duration = int(duration_str.split(":")[0].strip()) * 60 + int(duration_str.split(":")[-1].strip())
+        if "点赞" in like_str:
+            like_cnt = 0
+        elif "万" in like_str:
+            like_cnt = int(like_str.split("万")[0]) * 10000
+        else:
+            like_cnt = int(like_str)
+        if "评论" in comment_str:
+            comment_cnt = 0
+        elif "万" in comment_str:
+            comment_cnt = int(comment_str.split("万")[0]) * 10000
+        else:
+            comment_cnt = int(comment_str)
+        out_video_id = md5(video_title.encode('utf8')).hexdigest()
+        out_user_id = md5(user_name.encode('utf8')).hexdigest()
 
-            if video_title is None or cover_url is None:
-                Common.logger(self.log_type, self.crawler).info("无效视频\n")
-                Common.logging(self.log_type, self.crawler, self.env, '无效视频\n')
-                # self.swipe_up()
-                time.sleep(0.5)
-            elif download_rule(log_type=self.log_type,
-                               crawler=self.crawler,
-                               video_dict=video_dict,
-                               rule_dict=self.rule_dict) is False:
-                Common.logger(self.log_type, self.crawler).info("不满足抓取规则\n")
-                Common.logging(self.log_type, self.crawler, self.env, "不满足抓取规则\n")
-                # self.swipe_up()
-                time.sleep(0.5)
-            elif any(str(word) if str(word) in video_dict["video_title"] else False
-                     for word in get_config_from_mysql(log_type=self.log_type,
-                                                       source=self.crawler,
-                                                       env=self.env,
-                                                       text="filter",
-                                                       action="")) is True:
-                Common.logger(self.log_type, self.crawler).info('已中过滤词\n')
-                Common.logging(self.log_type, self.crawler, self.env, '已中过滤词\n')
-                # self.swipe_up()
-                time.sleep(0.5)
-            elif self.repeat_video(out_video_id) != 0:
-                Common.logger(self.log_type, self.crawler).info('视频已下载\n')
-                Common.logging(self.log_type, self.crawler, self.env, '视频已下载\n')
-                # self.swipe_up()
-                time.sleep(5)
-            else:
-                video_title_element = self.search_elements(f'//*[contains(text(), "{video_title}")]')
-                if video_title_element is None:
-                    Common.logger(self.log_type, self.crawler).warning(
-                        f"未找到该视频标题的element:{video_title_element}")
-                    Common.logging(self.log_type, self.crawler, self.env,
-                                   f"未找到该视频标题的element:{video_title_element}")
-                    # continue
-                    return
-                Common.logger(self.log_type, self.crawler).info("点击标题，进入视频详情页")
-                Common.logging(self.log_type, self.crawler, self.env, "点击标题，进入视频详情页")
-                video_url = self.get_video_url(video_title_element)
-                if video_url is None:
-                    Common.logger(self.log_type, self.crawler).info("未获取到视频播放地址\n")
-                    self.driver.press_keycode(AndroidKey.BACK)
-                    time.sleep(5)
-                    return
-                video_dict['video_url'] = video_url
-                Common.logger(self.log_type, self.crawler).info(f"video_url:{video_url}")
+        video_dict = {
+            "video_title": video_title,
+            "video_id": out_video_id,
+            "duration_str": duration_str,
+            "duration": duration,
+            "play_str": play_str,
+            "play_cnt": play_cnt,
+            "like_str": like_str,
+            "like_cnt": like_cnt,
+            "comment_cnt": comment_cnt,
+            "share_cnt": 0,
+            "user_name": user_name,
+            "user_id": out_user_id,
+            'publish_time_stamp': int(time.time()),
+            'publish_time_str': time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(int(time.time()))),
+            "avatar_url": avatar_url,
+            "cover_url": cover_url,
+            "session": f"xiaoniangao-{int(time.time())}"
+        }
+        for k, v in video_dict.items():
+            Common.logger(self.log_type, self.crawler).info(f"{k}:{v}")
+        Common.logging(self.log_type, self.crawler, self.env, f"video_dict:{video_dict}")
+        # Common.logger(self.log_type, self.crawler).info(f"==========分割线==========\n")
 
-                video_dict["platform"] = self.crawler
-                video_dict["strategy"] = self.log_type
-                video_dict["out_video_id"] = video_dict["video_id"]
-                video_dict["crawler_rule"] = json.dumps(self.rule_dict)
-                video_dict["user_id"] = self.our_uid
-                video_dict["publish_time"] = video_dict["publish_time_str"]
-                self.mq.send_msg(video_dict)
-                # print(video_dict)
-                self.download_cnt += 1
+        if video_title is None or cover_url is None:
+            Common.logger(self.log_type, self.crawler).info("无效视频\n")
+            Common.logging(self.log_type, self.crawler, self.env, '无效视频\n')
+            # self.swipe_up()
+            time.sleep(0.5)
+        elif download_rule(log_type=self.log_type,
+                           crawler=self.crawler,
+                           video_dict=video_dict,
+                           rule_dict=self.rule_dict) is False:
+            Common.logger(self.log_type, self.crawler).info("不满足抓取规则\n")
+            Common.logging(self.log_type, self.crawler, self.env, "不满足抓取规则\n")
+            # self.swipe_up()
+            time.sleep(0.5)
+        elif any(str(word) if str(word) in video_dict["video_title"] else False
+                 for word in get_config_from_mysql(log_type=self.log_type,
+                                                   source=self.crawler,
+                                                   env=self.env,
+                                                   text="filter",
+                                                   action="")) is True:
+            Common.logger(self.log_type, self.crawler).info('已中过滤词\n')
+            Common.logging(self.log_type, self.crawler, self.env, '已中过滤词\n')
+            # self.swipe_up()
+            time.sleep(0.5)
+        elif self.repeat_video(out_video_id) != 0:
+            Common.logger(self.log_type, self.crawler).info('视频已下载\n')
+            Common.logging(self.log_type, self.crawler, self.env, '视频已下载\n')
+            # self.swipe_up()
+            time.sleep(5)
+        else:
+            video_title_element = self.search_elements(f'//*[contains(text(), "{video_title}")]')
+            if video_title_element is None:
+                Common.logger(self.log_type, self.crawler).warning(
+                    f"未找到该视频标题的element:{video_title_element}")
+                Common.logging(self.log_type, self.crawler, self.env,
+                               f"未找到该视频标题的element:{video_title_element}")
+                # continue
+                return
+            Common.logger(self.log_type, self.crawler).info("点击标题，进入视频详情页")
+            Common.logging(self.log_type, self.crawler, self.env, "点击标题，进入视频详情页")
+            video_url = self.get_video_url(video_title_element)
+            if video_url is None:
+                Common.logger(self.log_type, self.crawler).info("未获取到视频播放地址\n")
                 self.driver.press_keycode(AndroidKey.BACK)
                 time.sleep(5)
-                # self.swipe_up()
+                return
+            video_dict['video_url'] = video_url
+            Common.logger(self.log_type, self.crawler).info(f"video_url:{video_url}")
+
+            video_dict["platform"] = self.crawler
+            video_dict["strategy"] = self.log_type
+            video_dict["out_video_id"] = video_dict["video_id"]
+            video_dict["crawler_rule"] = json.dumps(self.rule_dict)
+            video_dict["user_id"] = self.our_uid
+            video_dict["publish_time"] = video_dict["publish_time_str"]
+            self.mq.send_msg(video_dict)
+            # print(video_dict)
+            self.download_cnt += 1
+            self.driver.press_keycode(AndroidKey.BACK)
+            time.sleep(5)
+
+    def get_video_info(self, video_element):
+        try:
+            self.get_video_info_2(video_element)
         except Exception as e:
             Common.logger(self.log_type, self.crawler).error(f"抓取单条视频异常:{e}\n")
             # Common.logging(self.log_type, self.crawler, self.env, f"抓取单条视频异常:{e}\n")
@@ -338,7 +340,7 @@ def run():
     rule_dict1 = {"period": {"min": 365, "max": 365},
                   "duration": {"min": 30, "max": 1800},
                   "favorite_cnt": {"min": 0, "max": 0},
-                  "videos_cnt": {"min": 10000, "max": 0},
+                  "videos_cnt": {"min": 5000, "max": 0},
                   "share_cnt": {"min": 0, "max": 0}}
     XiaoNianGaoPlusRecommend("recommend", "xiaoniangao", "dev", rule_dict1, 6267141)
 

xiaoniangaoplus/xiaoniangaoplus_main/run_xngplus_recommend.py

@@ -82,14 +82,22 @@ def main(log_type, crawler, topic_name, group_id, env):
                 our_uid = random.choice(our_uid_list)
                 Common.logger(log_type, crawler).info(f"调度任务:{task_dict}")
                 Common.logging(log_type, crawler, env, f"调度任务:{task_dict}")
-                Common.logger(log_type, crawler).info(f"抓取规则:{rule_dict}")
-                Common.logging(log_type, crawler, env, f"抓取规则:{rule_dict}")
-                # Common.logger(log_type, crawler).info(f"用户列表:{user_list}\n")
+                # Common.logger(log_type, crawler).info(f"抓取规则:{rule_dict}")
+                # Common.logging(log_type, crawler, env, f"抓取规则:{rule_dict}")
+                Common.logger(log_type, crawler).info(f"用户列表:{user_list}\n")
                 Common.logger(log_type, crawler).info(f'开始抓取:{task_dict["taskName"]}\n')
                 Common.logging(log_type, crawler, env, f'开始抓取:{task_dict["taskName"]}\n')
+                new_r = get_rule_from_mysql(task_id=task_id, log_type=log_type, crawler=crawler, env=env)
+                # Common.logger(log_type, crawler).info(f'rule_dict:{new_r}\n')
+                r_d = {}
+                for item in new_r:
+                    for k, val in item.items():
+                        r_d[k] = val
+                Common.logger(log_type, crawler).info(f"抓取规则:{r_d}")
+                Common.logging(log_type, crawler, env, f"抓取规则:{r_d}")
                 process = multiprocessing.Process(
                     target=run,
-                    args=(log_type, crawler, env, rule_dict, our_uid)
+                    args=(log_type, crawler, env, r_d, our_uid)
                 )
                 process.start()
                 print("进程开始")
@@ -101,7 +109,13 @@ def main(log_type, crawler, topic_name, group_id, env):
                         os.system("adb forward --remove-all")
                         time.sleep(60)
                         new_r = get_rule_from_mysql(task_id=task_id, log_type=log_type, crawler=crawler, env=env)
-                        process = multiprocessing.Process(target=run, args=(log_type, crawler, env, new_r, our_uid))
+                        r_d = {}
+                        for item in new_r:
+                            for k, val in item.items():
+                                r_d[k] = val
+                        Common.logger(log_type, crawler).info(f'抓取规则:{r_d}')
+                        Common.logging(log_type, crawler, env, f"抓取规则:{r_d}")
+                        process = multiprocessing.Process(target=run, args=(log_type, crawler, env, r_d, our_uid))
                         process.start()
                     time.sleep(60)
                 # XiaoNianGaoPlusRecommend.start_wechat(log_type=log_type,