add kyk_video_id

kanyikan/kanyikan_main/run_kykfeed_recommend.py

@@ -10,6 +10,8 @@ from common.common import Common
 from common.public import get_consumer, ack_message, task_fun_mq
 from common.scheduling_db import MysqlHelper
 from kanyikan.kanyikan_recommend.kanyikan_recommend_feed import KanyikanRecommend
+from kanyikan.kanyikan_recommend.kanyikan_recommend_video_id import KanyikanViodeRecommend
+
 
 
 def main(log_type, crawler, topic_name, group_id, env):
@@ -72,12 +74,16 @@ def main(log_type, crawler, topic_name, group_id, env):
                 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')
-
                 KanyikanRecommend.get_videoList(log_type=log_type,
                                                 crawler=crawler,
                                                 rule_dict=rule_dict,
                                                 our_uid=our_uid,
                                                 env=env)
+                KanyikanViodeRecommend.get_videoList_video_id(log_type=log_type,
+                                                crawler=crawler,
+                                                rule_dict=rule_dict,
+                                                our_uid=our_uid,
+                                                env=env)
                 Common.del_charles_files(log_type, crawler)
                 Common.logger(log_type, crawler).info('抓取一轮结束\n')
                 Common.logging(log_type, crawler, env, '抓取一轮结束\n')

kanyikan/kanyikan_recommend/kanyikan_recommend_plus.py

@@ -28,6 +28,11 @@ class KanyikanRecommend:
         repeat_video = MysqlHelper.get_values(log_type, crawler, sql, env)
         return len(repeat_video)
 
+    @classmethod
+    def insert_video_id(cls, log_type, crawler, video_id, env):
+        insert_sql = f"""insert into crawler_kyk_video_id( kyk_video_id , status) values ("{video_id}",0)"""
+        MysqlHelper.update_values(log_type, crawler, insert_sql, env, action='')
+
     @classmethod
     def get_videoList(cls, log_type, crawler, our_uid, rule_dict, env):
         mq = MQ(topic_name="topic_crawler_etl_" + env)
@@ -160,8 +165,8 @@ class KanyikanRecommend:
                             video_url = feeds[i]["videoInfo"]["videoCdnInfo"]["ctnInfo"]["urlInfo"][0]["url"]
                         else:
                             video_url = feeds[i]["videoInfo"]["videoCdnInfo"]["urlInfo"][0]["url"]
-                        videoId = feeds[i].get("videoId", "")
-                        videoId = "{}kyk_plus".format(videoId)
+                        video_id = feeds[i].get("videoId", "")
+                        videoId = "{}kyk_plus".format(video_id)
                         playCount = int(feeds[i].get("playCount", 0))
                         shared_cnt = int(feeds[i].get("shared_cnt", 0))
                         video_dict = {
@@ -273,6 +278,14 @@ class KanyikanRecommend:
                             video_dict["crawler_rule"] = json.dumps(rule_dict)
                             video_dict["user_id"] = our_uid
                             video_dict["publish_time"] = video_dict["publish_time_str"]
+                            cls.insert_video_id(log_type, crawler, video_id, env)
+                            AliyunLogger.logging(
+                                code="1010",
+                                platform=crawler,
+                                mode=log_type,
+                                env=env,
+                                message=f"看一看video_id:{video_id}入库",
+                            )
                             mq.send_msg(video_dict)
                         time.sleep(random.randint(10, 15))
                     except Exception as e:

kanyikan/kanyikan_recommend/kanyikan_recommend_video_id.py

@@ -0,0 +1,287 @@
+# -*- coding: utf-8 -*-
+# @Time: 2023/11/23
+import json
+import os
+import random
+import sys
+import time
+import requests
+import urllib3
+
+
+sys.path.append(os.getcwd())
+from common import AliyunLogger
+from common.mq import MQ
+from common.common import Common
+from common.scheduling_db import MysqlHelper
+from common.public import get_config_from_mysql, download_rule
+proxies = {"http": None, "https": None}
+
+
+
+
+
+class KanyikanViodeRecommend:
+    platform = "看一看"
+    strategy = "video_id-feed流"
+
+
+    @classmethod
+    def repeat_video(cls, log_type, crawler, video_id, env):
+        sql = f""" select * from crawler_video where platform in ("{crawler}","{cls.platform}") and create_time>='2023-10-09' and out_video_id="{video_id}"; """
+        repeat_video = MysqlHelper.get_values(log_type, crawler, sql, env)
+        return len(repeat_video)
+
+    @classmethod
+    def get_video_id(cls, log_type, crawler, env):
+        sql = f""" select kyk_video_id from crawler_kyk_video_id where status = 0 """
+        repeat_video = MysqlHelper.get_values(log_type, crawler, sql, env)
+        return repeat_video
+
+    @classmethod
+    def update_video_id(cls, log_type, crawler, env, vid):
+        sql = f""" update crawler_kyk_video_id set status={1}  WHERE kyk_video_id ="{vid}" """
+        MysqlHelper.update_values(log_type, crawler, sql, env, action="")
+
+
+    @classmethod
+    def get_videoList_video_id(cls, log_type, crawler, our_uid, rule_dict, env):
+        mq = MQ(topic_name="topic_crawler_etl_" + env)
+        try:
+            session = Common.get_session(log_type, crawler, env)
+            if session is None:
+                time.sleep(1)
+                cls.get_videoList_video_id(log_type, crawler, our_uid, rule_dict, env)
+            vid_list = cls.get_video_id(log_type, crawler, env,)
+            if len(vid_list) == 0:
+                Common.logger(log_type, crawler).info(f"vid_list:{vid_list}")
+                Common.logging(log_type, crawler, env, f"vid_list:{vid_list}")
+                return
+            for video_id in vid_list:
+                vid = video_id["kyk_video_id"]
+                url1 = "https://search.weixin.qq.com/cgi-bin/recwxa/recwxavideolist?"
+                header = {
+                    'Host': 'search.weixin.qq.com',
+                    'Content-Type': 'application/json',
+                    'X-WX-ClientVersion': '0x33050520',
+                    'X-WECHAT-UIN': 'b2hfbTQ1WGNjSzQxemdfanpMSml1TEtfbEtsVQ==',
+                    'Accept': '*/*',
+                    'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E217 MicroMessenger/6.8.0(0x16080000) NetType/WIFI Language/en Branch/Br_trunk MiniProgramEnv/Mac',
+                    'Referer': 'https://servicewechat.com/wxbb9a805eb4f9533c/269/page-frame.html',
+                    'Accept-Language': 'zh-cn'
+                }
+                params = {
+                    "session": session,
+                    "offset": 0,
+                    "count": "30",
+                    "channelid": "200201",
+                    "vid": vid,
+                    "scene": "310",
+                    "subscene": '1098'
+                }
+                urllib3.disable_warnings()
+                response = requests.get(url=url1, headers=header, params=params, proxies=proxies, verify=False)
+                if "data" not in response.text:
+                    Common.logger(log_type, crawler).info("获取视频list时，session过期，随机睡眠 31-50 秒")
+                    Common.logging(log_type, crawler, env, "获取视频list时，session过期，随机睡眠 31-50 秒")
+                    AliyunLogger.logging(
+                        code="2000",
+                        platform=crawler,
+                        mode=log_type,
+                        env=env,
+                        message=f"获取视频list时，session过期，随机睡眠 31-50 秒"
+                    )
+                    # 如果返回空信息，则随机睡眠 31-40 秒
+                    time.sleep(random.randint(31, 40))
+                    cls.get_videoList_video_id(log_type, crawler, our_uid, rule_dict, env)
+                elif "items" not in response.json()["data"]:
+                    Common.logger(log_type, crawler).info(f"get_feeds:{response.json()}，随机睡眠 1-3 分钟")
+                    Common.logging(log_type, crawler, env, f"get_feeds:{response.json()}，随机睡眠 1-3 分钟")
+                    AliyunLogger.logging(
+                        code="2000",
+                        platform=crawler,
+                        mode=log_type,
+                        env=env,
+                        message=f"get_feeds:{response.json()}，随机睡眠 1-3 分钟"
+                    )
+                    # 如果返回空信息，则随机睡眠 1-3 分钟
+                    time.sleep(random.randint(60, 180))
+                    cls.get_videoList_video_id(log_type, crawler, our_uid, rule_dict, env)
+                feeds = response.json().get("data", {}).get("items", "")
+                if feeds == "":
+                    Common.logger(log_type, crawler).info(f"feeds:{feeds}")
+                    Common.logging(log_type, crawler, env, f"feeds:{feeds}")
+                    AliyunLogger.logging(
+                        code="2001",
+                        platform=crawler,
+                        mode=log_type,
+                        env=env,
+                        message=f"没有更多视频啦 ~\n"
+                    )
+                    return
+                for j in range(len(feeds)):
+                    try:
+                        AliyunLogger.logging(
+                            code="1001",
+                            platform=crawler,
+                            mode=log_type,
+                            env=env,
+                            message='扫描到一条视频\n'
+                        )
+                        cls.update_video_id(log_type, crawler, env, vid)
+                        AliyunLogger.logging(
+                            code="1011",
+                            platform=crawler,
+                            mode=log_type,
+                            env=env,
+                            message=f"看一看video_id:{vid}，状态修改为已抓取",
+                        )
+                        video_title = feeds[j].get("title", "").strip().replace("\n", "") \
+                            .replace("/", "").replace("\\", "").replace("\r", "") \
+                            .replace(":", "").replace("*", "").replace("？", "") \
+                            .replace("?", "").replace('"', "").replace("<", "") \
+                            .replace(">", "").replace("|", "").replace(" ", "") \
+                            .replace("&NBSP", "").replace(".", "。").replace(" ", "") \
+                            .replace("'", "").replace("#", "").replace("Merge", "")
+                        publish_time_stamp = feeds[j].get("date", 0)
+                        publish_time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(publish_time_stamp))
+                        # 获取播放地址
+                        if "videoInfo" not in feeds[j]:
+                            video_url = ""
+                        elif "mpInfo" in feeds[j]["videoInfo"]["videoCdnInfo"]:
+                            if len(feeds[j]["videoInfo"]["videoCdnInfo"]["mpInfo"]["urlInfo"]) > 2:
+                                video_url = feeds[j]["videoInfo"]["videoCdnInfo"]["mpInfo"]["urlInfo"][2]["url"]
+                            else:
+                                video_url = feeds[j]["videoInfo"]["videoCdnInfo"]["mpInfo"]["urlInfo"][0]["url"]
+                        elif "ctnInfo" in feeds[j]["videoInfo"]["videoCdnInfo"]:
+                            video_url = feeds[j]["videoInfo"]["videoCdnInfo"]["ctnInfo"]["urlInfo"][0]["url"]
+                        else:
+                            video_url = feeds[j]["videoInfo"]["videoCdnInfo"]["urlInfo"][0]["url"]
+                        video_id = feeds[j].get("videoId", "")+"video_id"
+                        s_cnt = int(feeds[j].get("shared_cnt", 0))
+                        p_count = int(feeds[j].get("playCount", 0))
+                        l_cnt = int(feeds[j].get("liked_cnt", 0))
+                        if p_count < 100000:
+                            if s_cnt < 200 and p_count < 15000:
+                                Common.logger(log_type, crawler).info(f"分享:{s_cnt},播放量:{p_count}\n")
+                                Common.logging(log_type, crawler, env, f"分享:{s_cnt},播放量:{p_count}\n")
+                                continue
+                        video_dict = {
+                            "video_title": video_title,
+                            "video_id": video_id,
+                            "play_cnt": feeds[j].get("playCount", 0),
+                            "like_cnt": feeds[j].get("liked_cnt", 0),
+                            "comment_cnt": feeds[j].get("comment_cnt", 0),
+                            "share_cnt": feeds[j].get("shared_cnt", 0),
+                            "duration": feeds[j].get("mediaDuration", 0),
+                            "video_width": feeds[j].get("short_video_info", {}).get("width", 0),
+                            "video_height": feeds[j].get("short_video_info", {}).get("height", 0),
+                            "publish_time_stamp": publish_time_stamp,
+                            "publish_time_str": publish_time_str,
+                            "user_name": feeds[j].get("source", "").strip().replace("\n", ""),
+                            "user_id": feeds[j].get("openid", ""),
+                            "avatar_url": feeds[j].get("bizIcon", ""),
+                            "cover_url": feeds[j].get("thumbUrl", ""),
+                            "video_url": video_url,
+                            "session": session,
+                        }
+                        for k, v in video_dict.items():
+                            Common.logger(log_type, crawler).info(f"{k}:{v}")
+                        Common.logging(log_type, crawler, env, f"video_dict:{video_dict}")
+                        AliyunLogger.logging(
+                            code="1000",
+                            platform=crawler,
+                            mode=log_type,
+                            env=env,
+                            message=f"{video_dict}\n"
+                        )
+
+                        if video_dict["video_id"] == "" or video_dict["video_title"] == "" or video_dict[
+                            "video_url"] == "":
+                            Common.logger(log_type, crawler).info("无效视频\n")
+                            Common.logging(log_type, crawler, env, "无效视频\n")
+                            AliyunLogger.logging(
+                                code="2004",
+                                platform=crawler,
+                                mode=log_type,
+                                env=env,
+                                message='无效视频\n'
+                            )
+                        elif download_rule(log_type=log_type, crawler=crawler, video_dict=video_dict,
+                                           rule_dict=rule_dict) is False:
+                            Common.logger(log_type, crawler).info("不满足抓取规则\n")
+                            Common.logging(log_type, crawler, env, "不满足抓取规则\n")
+                            AliyunLogger.logging(
+                                code="2004",
+                                platform=crawler,
+                                mode=log_type,
+                                env=env,
+                                message='不满足抓取规则\n'
+                            )
+                        elif any(str(word) if str(word) in video_dict["video_title"] else False
+                                 for word in get_config_from_mysql(log_type=log_type,
+                                                                   source=crawler,
+                                                                   env=env,
+                                                                   text="filter",
+                                                                   action="")) is True:
+                            Common.logger(log_type, crawler).info('已中过滤词\n')
+                            Common.logging(log_type, crawler, env, '已中过滤词\n')
+                            AliyunLogger.logging(
+                                code="2004",
+                                platform=crawler,
+                                mode=log_type,
+                                env=env,
+                                message='已中过滤词\n'
+                            )
+                        elif cls.repeat_video(log_type, crawler, video_dict["video_id"], env) != 0:
+                            Common.logger(log_type, crawler).info('视频已下载\n')
+                            Common.logging(log_type, crawler, env, '视频已下载\n')
+                            AliyunLogger.logging(
+                                code="2002",
+                                platform=crawler,
+                                mode=log_type,
+                                env=env,
+                                message='视频已下载\n'
+                            )
+                        else:
+                            video_dict["out_user_id"] = video_dict["user_id"]
+                            video_dict["platform"] = crawler
+                            video_dict["strategy"] = log_type
+                            video_dict["strategy_type"] = "hcm"
+                            video_dict["out_video_id"] = video_dict["video_id"]
+                            video_dict["width"] = video_dict["video_width"]
+                            video_dict["height"] = video_dict["video_height"]
+                            video_dict["crawler_rule"] = json.dumps(rule_dict)
+                            video_dict["user_id"] = our_uid
+                            video_dict["publish_time"] = video_dict["publish_time_str"]
+                            mq.send_msg(video_dict)
+                    except Exception as e:
+                        Common.logger(log_type, crawler).error(f"抓取单条视频异常:{e}\n")
+                        Common.logging(log_type, crawler, env, f"抓取单条视频异常:{e}\n")
+                        AliyunLogger.logging(
+                            code="3000",
+                            platform=crawler,
+                            mode=log_type,
+                            env=env,
+                            message=f"抓取单条视频异常:{e}\n"
+                        )
+        except Exception as e:
+            Common.logger(log_type, crawler).error(f"抓取列表页时异常:{e}\n")
+            Common.logging(log_type, crawler, env, f"抓取列表页时异常:{e}\n")
+            AliyunLogger.logging(
+                code="3000",
+                platform=crawler,
+                mode=log_type,
+                env=env,
+                message=f"抓取列表页时异常:{e}\n"
+            )
+
+
+if __name__ == "__main__":
+    KanyikanViodeRecommend.get_videoList_video_id(
+        log_type="recommend",
+        crawler="kanyikan",
+        env="prod",
+        rule_dict={'share_cnt': {'min': 300, 'max': 0}},
+        our_uid=64080779
+    )