开心快乐常相伴———上线

kaixinkuailechangxiangban/kaixinkuailechangxiangban_main/run_kxklcxb_recommend.py

@@ -0,0 +1,153 @@
+import argparse
+from mq_http_sdk.mq_client import *
+from mq_http_sdk.mq_consumer import *
+from mq_http_sdk.mq_exception import MQExceptionBase
+
+sys.path.append(os.getcwd())
+from common.public import task_fun_mq, get_consumer, ack_message
+from common.scheduling_db import MysqlHelper
+from common import AliyunLogger
+from kaixinkuailechangxiangban.kaixinkuailechangxiangban_recommend import KXKLCXBRecommend
+
+
+def main(log_type, crawler, topic_name, group_id, env):
+    consumer = get_consumer(topic_name, group_id)
+    # 长轮询表示如果Topic没有消息，则客户端请求会在服务端挂起3秒，3秒内如果有消息可以消费则立即返回响应。
+    # 长轮询时间3秒（最多可设置为30秒）。
+    wait_seconds = 30
+    # 一次最多消费3条（最多可设置为16条）。
+    batch = 1
+    AliyunLogger.logging(
+        code="1000",
+        platform=crawler,
+        mode=log_type,
+        env=env,
+        message=f'{10 * "="}Consume And Ack Message From Topic{10 * "="}\n'
+        f"WaitSeconds:{wait_seconds}\n"
+        f"TopicName:{topic_name}\n"
+        f"MQConsumer:{group_id}",
+    )
+    while True:
+        try:
+            # 长轮询消费消息。
+            recv_msgs = consumer.consume_message(batch, wait_seconds)
+            for msg in recv_msgs:
+                AliyunLogger.logging(
+                    code="1000",
+                    platform=crawler,
+                    mode=log_type,
+                    env=env,
+                    message=f"Receive\n"
+                    f"MessageId:{msg.message_id}\n"
+                    f"MessageBodyMD5:{msg.message_body_md5}\n"
+                    f"MessageTag:{msg.message_tag}\n"
+                    f"ConsumedTimes:{msg.consumed_times}\n"
+                    f"PublishTime:{msg.publish_time}\n"
+                    f"Body:{msg.message_body}\n"
+                    f"NextConsumeTime:{msg.next_consume_time}\n"
+                    f"ReceiptHandle:{msg.receipt_handle}\n"
+                    f"Properties:{msg.properties}",
+                )
+                # ack_mq_message
+                ack_message(
+                    log_type=log_type,
+                    crawler=crawler,
+                    recv_msgs=recv_msgs,
+                    consumer=consumer,
+                )
+                # 解析 task_dict
+                task_dict = task_fun_mq(msg.message_body)["task_dict"]
+                AliyunLogger.logging(
+                    code="1000",
+                    platform=crawler,
+                    mode=log_type,
+                    env=env,
+                    message="f调度任务:{task_dict}",
+                )
+                # 解析 rule_dict
+                rule_dict = task_fun_mq(msg.message_body)["rule_dict"]
+                AliyunLogger.logging(
+                    code="1000",
+                    platform=crawler,
+                    mode=log_type,
+                    env=env,
+                    message=f"抓取规则:{rule_dict}\n",
+                )
+                # 解析 user_list
+                task_id = task_dict["id"]
+                select_user_sql = (
+                    f"""select * from crawler_user_v3 where task_id={task_id}"""
+                )
+                user_list = MysqlHelper.get_values(
+                    log_type, crawler, select_user_sql, env, action=""
+                )
+                AliyunLogger.logging(
+                    code="1003",
+                    platform=crawler,
+                    mode=log_type,
+                    env=env,
+                    message="开始抓取"
+                )
+                AliyunLogger.logging(
+                    code="1000",
+                    platform=crawler,
+                    mode=log_type,
+                    env=env,
+                    message="开始抓取开心快乐常相伴——推荐",
+                )
+                main_process = KXKLCXBRecommend(
+                    platform=crawler,
+                    mode=log_type,
+                    rule_dict=rule_dict,
+                    user_list=user_list,
+                    env=env
+                )
+                main_process.schedule()
+                AliyunLogger.logging(
+                    code="1000",
+                    platform=crawler,
+                    mode=log_type,
+                    env=env,
+                    message="完成抓取——开心快乐常相伴",
+                )
+                AliyunLogger.logging(
+                    code="1004", platform=crawler, mode=log_type, env=env,message="结束一轮抓取"
+                )
+
+        except MQExceptionBase as err:
+            # Topic中没有消息可消费。
+            if err.type == "MessageNotExist":
+                AliyunLogger.logging(
+                    code="2000",
+                    platform=crawler,
+                    mode=log_type,
+                    env=env,
+                    message=f"No new message! RequestId:{err.req_id}\n",
+                )
+                continue
+            AliyunLogger.logging(
+                code="2000",
+                platform=crawler,
+                mode=log_type,
+                env=env,
+                message=f"Consume Message Fail! Exception:{err}\n",
+            )
+            time.sleep(2)
+            continue
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()  ## 新建参数解释器对象
+    parser.add_argument("--log_type", type=str)  ## 添加参数,注明参数类型
+    parser.add_argument("--crawler")  ## 添加参数
+    parser.add_argument("--topic_name")  ## 添加参数
+    parser.add_argument("--group_id")  ## 添加参数
+    parser.add_argument("--env")  ## 添加参数
+    args = parser.parse_args()  ### 参数赋值，也可以通过终端赋值
+    main(
+        log_type=args.log_type,
+        crawler=args.crawler,
+        topic_name=args.topic_name,
+        group_id=args.group_id,
+        env=args.env,
+    )

kaixinkuailechangxiangban/kaixinkuailechangxiangban_recommend/__init__.py

@@ -0,0 +1 @@
+from .kaixinkuailechangxiangban_recommend_2 import KXKLCXBRecommend

kaixinkuailechangxiangban/kaixinkuailechangxiangban_recommend/huanhuanxixizhufudao_recommend.py

@@ -0,0 +1,310 @@
+# -*- coding: utf-8 -*-
+# @Author: wang
+# @Time: 2023/9/6
+import json
+import os
+import random
+import sys
+import time
+from hashlib import md5
+
+from appium import webdriver
+from appium.webdriver.common.touch_action import TouchAction
+from appium.webdriver.extensions.android.nativekey import AndroidKey
+from appium.webdriver.webdriver import WebDriver
+from bs4 import BeautifulSoup
+from selenium.common import NoSuchElementException
+from selenium.webdriver.common.by import By
+
+sys.path.append(os.getcwd())
+from common.common import Common
+from common.mq import MQ
+from common.public import download_rule, get_config_from_mysql
+from common.scheduling_db import MysqlHelper
+
+
+class HhxxzfdRecommend:
+    platform = "欢欢喜喜祝福到"
+    download_cnt = 0
+    element_list = []
+    i = 0
+
+    @classmethod
+    def start_wechat(cls, log_type, crawler, env, rule_dict, our_uid):
+        if env == "dev":
+            chromedriverExecutable = "/Users/piaoquan/Downloads/chromedriver"
+        else:
+            chromedriverExecutable = "/Users/piaoquan/Downloads/chromedriver"
+
+        Common.logger(log_type, crawler).info("启动微信")
+        Common.logging(log_type, crawler, env, '启动微信')
+        caps = {
+            "platformName": "Android",
+            "devicesName": "Android",
+            # "platformVersion": "11",
+            # "udid": "emulator-5554",
+            "appPackage": "com.tencent.mm",
+            "appActivity": ".ui.LauncherUI",
+            "autoGrantPermissions": "true",
+            "noReset": True,
+            "resetkeyboard": True,
+            "unicodekeyboard": True,
+            "showChromedriverLog": True,
+            "printPageSourceOnFailure": True,
+            "recreateChromeDriverSessions": True,
+            "enableWebviewDetailsCollection": True,
+            "setWebContentsDebuggingEnabled": True,
+            "newCommandTimeout": 6000,
+            "automationName": "UiAutomator2",
+            "chromedriverExecutable": chromedriverExecutable,
+            "chromeOptions": {"androidProcess": "com.tencent.mm:appbrand0"},
+        }
+        driver = webdriver.Remote("http://localhost:4723/wd/hub", caps)
+        driver.implicitly_wait(30)
+
+        for i in range(120):
+            try:
+                if driver.find_elements(By.ID, 'com.tencent.mm:id/f2s'):
+                    Common.logger(log_type, crawler).info("微信启动成功")
+                    Common.logging(log_type, crawler, env, '微信启动成功')
+                    break
+                elif driver.find_element(By.ID, "com.android.systemui:id/dismiss_view"):
+                    Common.logger(log_type, crawler).info("发现并关闭系统下拉菜单")
+                    Common.logging(log_type, crawler, env, '发现并关闭系统下拉菜单')
+                    driver.find_element(By.ID, "com.android.system:id/dismiss_view").click()
+                else:
+                    pass
+            except NoSuchElementException:
+                time.sleep(1)
+
+        Common.logger(log_type, crawler).info("下滑，展示小程序选择面板")
+        Common.logging(log_type, crawler, env, '下滑，展示小程序选择面板')
+        size = driver.get_window_size()
+        driver.swipe(int(size['width'] * 0.5), int(size['height'] * 0.2),
+                     int(size['width'] * 0.5), int(size['height'] * 0.8), 200)
+        time.sleep(1)
+        Common.logger(log_type, crawler).info('打开小程序"欢欢喜喜祝福到"')
+        Common.logging(log_type, crawler, env, '打开小程序"欢欢喜喜祝福到"')
+        driver.find_elements(By.XPATH, '//*[@text="欢欢喜喜祝福到"]')[-1].click()
+        time.sleep(5)
+
+        cls.get_videoList(log_type, crawler, driver, env, rule_dict, our_uid)
+
+        time.sleep(1)
+        driver.quit()
+
+    @classmethod
+    def search_elements(cls, driver: WebDriver, xpath):
+        time.sleep(1)
+        windowHandles = driver.window_handles
+        for handle in windowHandles:
+            driver.switch_to.window(handle)
+            time.sleep(1)
+            try:
+                elements = driver.find_elements(By.XPATH, xpath)
+                if elements:
+                    return elements
+            except NoSuchElementException:
+                pass
+
+    @classmethod
+    def check_to_applet(cls, log_type, crawler, env, driver: WebDriver):
+        time.sleep(1)
+        webViews = driver.contexts
+        Common.logger(log_type, crawler).info(f"webViews:{webViews}")
+        Common.logging(log_type, crawler, env, f"webViews:{webViews}")
+        driver.switch_to.context(webViews[1])
+        windowHandles = driver.window_handles
+        for handle in windowHandles:
+            driver.switch_to.window(handle)
+            time.sleep(1)
+            try:
+                driver.find_element(By.XPATH, '//*[@class="nav_item active"]')
+                Common.logger(log_type, crawler).info("切换到小程序成功\n")
+                Common.logging(log_type, crawler, env, '切换到小程序成功\n')
+                return
+            except NoSuchElementException:
+                time.sleep(1)
+
+    @classmethod
+    def repeat_video(cls, log_type, crawler, video_id, env):
+        sql = f""" select * from crawler_video where platform in ("{crawler}","{cls.platform}") and out_video_id="{video_id}"; """
+
+        repeat_video = MysqlHelper.get_values(log_type, crawler, sql, env)
+        return len(repeat_video)
+
+    @classmethod
+    def swipe_up(cls, driver: WebDriver):
+        cls.search_elements(driver, '//*[@class="videoplay"]')
+        size = driver.get_window_size()
+        driver.swipe(int(size["width"] * 0.7), int(size["height"] * 0.8),
+                     int(size["width"] * 0.7), int(size["height"] * 0.4), 200)
+
+    @classmethod
+    def get_video_url(cls, log_type, crawler, driver: WebDriver, video_title_element):
+        for i in range(3):
+            cls.search_elements(driver, '//*[@class="videoplay"]')
+            Common.logger(log_type, crawler).info(f"video_title_element:{video_title_element[0]}")
+            time.sleep(1)
+            Common.logger(log_type, crawler).info("滑动标题至可见状态")
+            driver.execute_script("arguments[0].scrollIntoView({block:'center',inline:'center'});", video_title_element[0])
+            time.sleep(3)
+            Common.logger(log_type, crawler).info("点击标题")
+            video_title_element[0].click()
+            # driver.execute_script("arguments[0].click();", video_title_element[0])
+            Common.logger(log_type, crawler).info("点击标题完成")
+            time.sleep(1)
+            video_url_elements = cls.search_elements(driver, "//wx-video[@id='video0']")
+            if video_url_elements:
+                return video_url_elements[0].get_attribute("src")
+
+    @classmethod
+    def get_videoList(cls, log_type, crawler, driver: WebDriver, env, rule_dict, our_uid):
+        mq = MQ(topic_name="topic_crawler_etl_" + env)
+        driver.implicitly_wait(20)
+        # 鼠标左键点击， 1为x坐标， 2为y坐标
+        cls.check_to_applet(log_type=log_type, crawler=crawler, env=env, driver=driver)
+        time.sleep(1)
+
+        page = 0
+        while True:
+            if cls.search_elements(driver, '//*[@class="videoplay"]') is None:
+                Common.logger(log_type, crawler).info("窗口已销毁\n")
+                Common.logging(log_type, crawler, env, '窗口已销毁\n')
+                cls.i = 0
+                cls.download_cnt = 0
+                cls.element_list = []
+                return
+
+            cls.swipe_up(driver)
+
+            page_source = driver.page_source
+            soup = BeautifulSoup(page_source, 'html.parser')
+            soup.prettify()
+
+            video_list_elements = soup.findAll("wx-view", class_="video_item_ob")
+            # video_list_elements 有，cls.element_list 中没有的元素
+            video_list_elements = list(set(video_list_elements).difference(set(cls.element_list)))
+            # video_list_elements 与 cls.element_list 的并集
+            cls.element_list = list(set(video_list_elements) | set(cls.element_list))
+            Common.logger(log_type, crawler).info(f"正在抓取第{page + 1}页，共:{len(video_list_elements)}条视频")
+            Common.logging(log_type, crawler, env, f"正在抓取第{page + 1}页，共:{len(video_list_elements)}条视频")
+
+            if len(video_list_elements) == 0:
+                for i in range(10):
+                    Common.logger(log_type, crawler).info(f"向上滑动第{i + 1}次")
+                    cls.swipe_up(driver)
+                    time.sleep(0.5)
+                continue
+
+            for i, video_element in enumerate(video_list_elements):
+                try:
+
+                    Common.logger(log_type, crawler).info(f"本轮已抓取{cls.download_cnt}条视频\n")
+                    Common.logging(log_type, crawler, env, f"本轮已抓取{cls.download_cnt}条视频\n")
+                    if cls.download_cnt >= int(rule_dict.get("videos_cnt", {}).get("min", 10)):
+                        cls.i = 0
+                        cls.download_cnt = 0
+                        cls.element_list = []
+                        return
+                    cls.i += 1
+                    Common.logger(log_type, crawler).info(f"第{cls.i}条视频")
+                    Common.logging(log_type, crawler, env, f"第{cls.i}条视频")
+
+                    video_title = video_element.find("wx-view", class_="video_title").text
+                    cover_url = video_element.find("wx-image", class_="video_bg")["src"]
+                    user_name = video_element.find("wx-text", class_="text-group_2").select_one("span:nth-of-type(2)").text.strip()
+                    out_video_id = video_element.get("id")
+
+                    video_dict = {
+                        "video_title": video_title,
+                        "video_id": out_video_id,
+                        "duration": 0,
+                        "play_str": 0,
+                        "play_cnt": 0,
+                        "like_cnt": 0,
+                        "share_cnt": 0,
+                        "user_name": user_name,
+                        "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": cover_url,
+                        "cover_url": cover_url,
+                        "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}")
+                    # Common.logger(log_type, crawler).info(f"==========分割线==========\n")
+
+                    if video_title is None or cover_url is None:
+                        Common.logger(log_type, crawler).info("无效视频\n")
+                        Common.logging(log_type, crawler, env, '无效视频\n')
+                        cls.swipe_up(driver)
+                        time.sleep(0.5)
+                    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")
+                        cls.swipe_up(driver)
+                        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=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')
+                        cls.swipe_up(driver)
+                        time.sleep(0.5)
+                    elif cls.repeat_video(log_type, crawler, out_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')
+                        cls.swipe_up(driver)
+                        time.sleep(5)
+                    else:
+                        video_title_element = cls.search_elements(driver, f'//*[contains(text(), "{video_title}")]')
+                        if video_title_element is None:
+                            Common.logger(log_type, crawler).warning(f"未找到该视频标题的element:{video_title_element}")
+                            Common.logging(log_type, crawler, env, f"未找到该视频标题的element:{video_title_element}")
+                            continue
+                        Common.logger(log_type, crawler).info("点击标题，进入视频详情页")
+                        Common.logging(log_type, crawler, env, "点击标题，进入视频详情页")
+                        video_url = cls.get_video_url(log_type, crawler, driver, video_title_element)
+                        if video_url is None:
+                            Common.logger(log_type, crawler).info("未获取到视频播放地址\n")
+                            driver.press_keycode(AndroidKey.BACK)
+                            time.sleep(5)
+                            continue
+                        video_dict['video_url'] = video_url
+                        Common.logger(log_type, crawler).info(f"video_url:{video_url}")
+
+                        video_dict["platform"] = crawler
+                        video_dict["strategy"] = log_type
+                        video_dict["out_video_id"] = video_dict["video_id"]
+                        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)
+                        cls.download_cnt += 1
+                        driver.press_keycode(AndroidKey.BACK)
+                        time.sleep(5)
+                        cls.swipe_up(driver)
+                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")
+            Common.logger(log_type, crawler).info("已抓取完一组，休眠 5 秒\n")
+            Common.logging(log_type, crawler, env, "已抓取完一组，休眠 5 秒\n")
+            time.sleep(5)
+            page += 1
+
+
+
+if __name__ == "__main__":
+    rule_dict1 = {"period": {"min": 0, "max": 365},
+                  "duration": {"min": 0, "max": 1800},
+                  "favorite_cnt": {"min": 0, "max": 0},
+                  "videos_cnt": {"min": 10, "max": 20},
+                  "share_cnt": {"min": 0, "max": 0}}
+    HhxxzfdRecommend.start_wechat("recommend", "huanhuanxixizhufudao", "dev", rule_dict1, 6267141)

kaixinkuailechangxiangban/kaixinkuailechangxiangban_recommend/kaixinkuailechangxiangban_recommend_2.py

@@ -0,0 +1,373 @@
+import os
+import json
+import random
+import sys
+import time
+import uuid
+
+import requests
+
+sys.path.append(os.getcwd())
+from common.video_item import VideoItem
+from common import PiaoQuanPipeline, AliyunLogger, tunnel_proxies
+from common.mq import MQ
+from common.db import MysqlHelper
+from zhuwanwufusu.crypt import AESCipher as AES
+
+
+class KXKLCXBRecommend(object):
+    def __init__(self, platform, mode, rule_dict, user_list, env):
+        self.platform = platform
+        self.mode = mode
+        self.rule_dict = rule_dict
+        self.user_list = user_list
+        self.env = env
+        self.download_cnt = 0
+        self.mq = MQ(topic_name="topic_crawler_etl_" + self.env)
+        self.limit_flag = False
+        self.cryptor = AES()
+
+    def get_recommend_list(self):
+        url = "https://api.lidongze.cn/jeecg-boot/ugc/getVideoListsEn2"
+        headers = {
+            'Host': 'api.lidongze.cn',
+            'xweb_xhr': '1',
+            'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF MacWechat/3.8.4(0x13080410)XWEB/31009',
+            'token': '',
+            'content-type': 'application/json',
+            'accept': '*/*',
+            'referer': 'https://servicewechat.com/wx05c1e3981d52164e/2/page-frame.html',
+            'accept-language': 'en-US,en;q=0.9'
+        }
+        page_index = 1
+        total_page = 2
+        while page_index <= total_page:
+            try:
+                query = {
+                    "pageNo": page_index,
+                    "pageSize": 10,
+                    "groupId": "1650323161797439489",  # 推荐流的 ID
+                    "vn": 1,
+                    "gx": 1,
+                    "appid": "wx05c1e3981d52164e",
+                    "type": 2
+                }
+                params = {
+                    "v": self.cryptor.aes_encrypt(data=json.dumps(query))
+                }
+                response = requests.request("GET", url, headers=headers, params=params, proxies=tunnel_proxies())
+                result = json.loads(self.cryptor.aes_decrypt(response.text))
+                total_page = result['list']['pages']
+                page_index = result['list']['current'] + 1
+                for index, video_obj in enumerate(result['list']['records'], 1):
+                    try:
+                        AliyunLogger.logging(
+                            code="1001",
+                            platform=self.platform,
+                            mode=self.mode,
+                            env=self.env,
+                            message="扫描到一条视频",
+                            data=video_obj
+                        )
+                        self.process_video_obj(video_obj)
+                    except Exception as e:
+                        AliyunLogger.logging(
+                            code="3000",
+                            platform=self.platform,
+                            mode=self.mode,
+                            env=self.env,
+                            message="抓取单条视频失败, 该视频位于第{}页第{}条报错原因是{}".format(page_index, index, e)
+                        )
+            except Exception as e:
+                AliyunLogger.logging(
+                    code="3000",
+                    platform=self.platform,
+                    mode=self.mode,
+                    env=self.env,
+                    message="抓取第{}页的时候失败, 报错原因是{}".format(page_index, e)
+                )
+            time.sleep(random.randint(5, 10))
+
+    def get_user_videos(self, user_id):
+        """
+        在抓取完推荐页之后，去抓每一个用户的主页视频
+        """
+        url = "https://api.lidongze.cn/jeecg-boot/ugc/getAuthVideoList"
+        headers = {
+            'Host': 'api.lidongze.cn',
+            'xweb_xhr': '1',
+            'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF MacWechat/3.8.4(0x13080410)XWEB/31009',
+            'token': '',
+            'content-type': 'application/json',
+            'accept': '*/*',
+            'referer': 'https://servicewechat.com/wx05c1e3981d52164e/2/page-frame.html',
+            'accept-language': 'en-US,en;q=0.9'
+        }
+        page_index = 1
+        total_page = 1
+        while page_index <= total_page:
+            query = {
+                "pageNo": page_index,
+                "pageSize": 10,
+                "authid": user_id
+            }
+            params = {
+                "v": self.cryptor.aes_encrypt(data=json.dumps(query))
+            }
+            response = requests.request("GET", url, headers=headers, params=params, proxies=tunnel_proxies())
+            result = json.loads(self.cryptor.aes_decrypt(response.text))
+            total_page = result['list']['pages']
+            page_index = result['list']['current'] + 1
+            for index, video_temp in enumerate(result['list']['records']):
+                video_id = video_temp['id']
+                detail_query = {
+                    "videoId": video_id
+                }
+                detail_params = {
+                    "v": self.cryptor.aes_encrypt(data=json.dumps(detail_query))
+                }
+                url = "https://api.lidongze.cn/jeecg-boot/ugc/getVideosDataEn"
+                headers = {
+                    'Host': 'api.lidongze.cn',
+                    'xweb_xhr': '1',
+                    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF MacWechat/3.8.4(0x13080410)XWEB/31009',
+                    'token': '',
+                    'content-type': 'application/json',
+                    'accept': '*/*',
+                    'referer': 'https://servicewechat.com/wx05c1e3981d52164e/2/page-frame.html',
+                    'accept-language': 'en-US,en;q=0.9'
+                }
+                detail_response = requests.request("GET", url, headers=headers, params=detail_params,
+                                                   proxies=tunnel_proxies())
+                detail_video = json.loads(self.cryptor.aes_decrypt(detail_response.text))
+                if detail_video['success']:
+                    try:
+                        AliyunLogger.logging(
+                            code="1001",
+                            platform=self.platform,
+                            mode=self.mode,
+                            env=self.env,
+                            message="扫描到一条视频",
+                            data=detail_video['data']
+                        )
+                        self.process_video_obj(detail_video['data'])
+                    except Exception as e:
+                        AliyunLogger.logging(
+                            code="3000",
+                            platform=self.platform,
+                            mode=self.mode,
+                            env=self.env,
+                            message="抓取单条视频失败, 该视频位于第{}条报错原因是{}".format(index, e)
+                        )
+
+    def process_video_obj(self, video_obj):
+        time.sleep(random.randint(3, 8))
+        trace_id = self.platform + str(uuid.uuid1())
+        if video_obj.get("playnum"):
+            play_cnt = int(video_obj['playnum'].replace("万+", "0000")) if "万+" in video_obj['playnum'] else int(
+                video_obj['playnum'])
+        else:
+            play_cnt = 0
+        our_user = random.choice(self.user_list)
+        item = VideoItem()
+        item.add_video_info("video_id", video_obj['id'])
+        item.add_video_info("video_title", video_obj['vname'])
+        item.add_video_info("play_cnt", play_cnt)
+        item.add_video_info("publish_time_stamp", int(time.time()))
+        item.add_video_info("out_user_id", video_obj['authid'])
+        item.add_video_info("cover_url", video_obj['shareimg'])
+        item.add_video_info("like_cnt", int(video_obj['likenum']))
+        item.add_video_info("video_url", video_obj['videoaddr'])
+        item.add_video_info("out_video_id", video_obj['id'])
+        item.add_video_info("platform", self.platform)
+        item.add_video_info("strategy", self.mode)
+        item.add_video_info("session", "{}-{}".format(self.platform, int(time.time())))
+        item.add_video_info("user_id", our_user['uid'])
+        item.add_video_info("user_name", our_user['nick_name'])
+        # 把扫描到的账号存到 accounts 表中
+        self.manage_auth_id(out_user_id=video_obj['authid'], out_user_name=video_obj['authname'])
+        mq_obj = item.produce_item()
+        pipeline = PiaoQuanPipeline(
+            platform=self.platform,
+            mode=self.mode,
+            rule_dict=self.rule_dict,
+            env=self.env,
+            item=mq_obj,
+            trace_id=trace_id,
+        )
+        if pipeline.process_item():
+            self.download_cnt += 1
+            self.mq.send_msg(mq_obj)
+            AliyunLogger.logging(
+                code="1002",
+                platform=self.platform,
+                mode=self.mode,
+                env=self.env,
+                message="成功发送至 ETL",
+                data=mq_obj
+            )
+            if self.download_cnt >= int(self.rule_dict.get("videos_cnt", {}).get("min", 200)):
+                self.limit_flag = True
+
+    def manage_auth_id(self, out_user_id, out_user_name):
+        """
+        out_user_id: 外站视频的用户 id
+        out_user_name: 外站视频用户名字
+        逻辑： 对新扫描到的视频的用户 id 进行判断，若用户 id 不存在，则把视频 id 存到表中,
+              如果用户 id 存在，则判断用户是否修改名字，若名字修改则更新名字
+        """
+        select_user_sql = f"""select name, name_id from accounts where name_id = "{out_user_id}" and platform = "{self.platform}" and useful = 1 limit 1"""
+        out_user_info = MysqlHelper.get_values(
+            log_type=self.mode,
+            crawler=self.platform,
+            sql=select_user_sql,
+            env=self.env,
+            machine="",
+        )
+        if out_user_info:
+            name, name_id = out_user_info[0]
+            if name == out_user_name:
+                return
+            else:
+                update_sql = f"""update accounts set name = "{out_user_name}" where name_id = "{out_user_id}";"""
+                MysqlHelper.update_values(
+                    log_type=self.mode,
+                    crawler=self.platform,
+                    sql=update_sql,
+                    env=self.env,
+                    machine=""
+                )
+        else:
+            insert_sql = f"""INSERT INTO accounts (name, name_id, platform, useful) values ("{out_user_name}", "{out_user_id}", "{self.platform}", 1 )"""
+            MysqlHelper.update_values(
+                log_type=self.mode,
+                crawler=self.platform,
+                sql=insert_sql,
+                env=self.env,
+                machine="",
+            )
+
+    def get_user_list(self):
+        select_user_sql = f"""select name_id from accounts where platform = "{self.platform}" and useful = 1"""
+        out_user_info = MysqlHelper.get_values(
+            log_type=self.mode,
+            crawler=self.platform,
+            sql=select_user_sql,
+            env=self.env,
+            machine="",
+        )
+        if out_user_info:
+            result = []
+            for i in out_user_info:
+                result.append(i[0])
+            return result
+        else:
+            return []
+
+    def get_detail_video_list(self):
+        url = "https://api.lidongze.cn/jeecg-boot/ugc/getDetailVideoListsEn2"
+        headers = {
+            'Host': 'api.lidongze.cn',
+            'xweb_xhr': '1',
+            'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF MacWechat/3.8.5(0x13080510)XWEB/1100',
+            'token': '',
+            'referer': 'https://servicewechat.com/wx05c1e3981d52164e/2/page-frame.html',
+            'accept-language': 'en-US,en;q=0.9'
+        }
+        page_index = 1
+        total_page = 2
+        while page_index <= total_page:
+            try:
+                if self.limit_flag:
+                    AliyunLogger.logging(
+                        code="2000",
+                        platform=self.platform,
+                        mode=self.mode,
+                        env=self.env,
+                        message="本轮已经抓取足够数量的视频"
+                    )
+                    return
+                else:
+                    query = {
+                        "groupId": "1650323161797439489",
+                        "pageNo": page_index,
+                        "pageSize": 10,
+                        "appid": "wx05c1e3981d52164e",
+                        "type": 3,
+                        "hxid": "1556555457243828666"
+                    }
+                    params = {
+                        "v": self.cryptor.aes_encrypt(data=json.dumps(query))
+                    }
+                    response = requests.request("GET", url, headers=headers, params=params)
+                    result = json.loads(self.cryptor.aes_decrypt(response.text))
+                    total_page = result['list']['pages']
+                    page_index = result['list']['current'] + 1
+                    for index, video_obj in enumerate(result['list']['records'], 1):
+                        try:
+                            AliyunLogger.logging(
+                                code="1001",
+                                platform=self.platform,
+                                mode=self.mode,
+                                env=self.env,
+                                message="扫描到一条视频",
+                                data=video_obj
+                            )
+                            self.process_video_obj(video_obj)
+                        except Exception as e:
+                            AliyunLogger.logging(
+                                code="3000",
+                                platform=self.platform,
+                                mode=self.mode,
+                                env=self.env,
+                                message="抓取单条视频失败, 该视频位于第{}页第{}条报错原因是{}".format(page_index, index, e)
+                            )
+            except Exception as e:
+                AliyunLogger.logging(
+                    code="3000",
+                    platform=self.platform,
+                    mode=self.mode,
+                    env=self.env,
+                    message="抓取第{}页的时候失败, 报错原因是{}".format(page_index, e)
+                )
+            time.sleep(random.randint(5, 10))
+
+    def schedule(self):
+        """
+        先抓取推荐列表的视频， 等待 2 分钟后抓取 detail 页面，等待 5 分钟后，抓取账号视频
+        """
+        self.get_recommend_list()
+        if self.limit_flag:
+            return
+        time.sleep(2 * 60)
+        self.get_detail_video_list()
+        if self.limit_flag:
+            return
+        time.sleep(5 * 60)
+        self.mode = "author"
+        user_list = self.get_user_list()
+        if user_list:
+            for index, user_id in enumerate(user_list):
+                try:
+                    if self.limit_flag:
+                        AliyunLogger.logging(
+                            code="2000",
+                            platform=self.platform,
+                            mode=self.mode,
+                            env=self.env,
+                            message="本轮已经抓取足够数量的视频"
+                        )
+                        return
+                    self.get_user_videos(user_id=user_id)
+                except Exception as e:
+                    AliyunLogger.logging(
+                        code="3000",
+                        platform=self.platform,
+                        mode=self.mode,
+                        env=self.env,
+                        message="抓取账号视频出现异常，账号 id 是{}, 报错原因是{}".format(user_id, e)
+                    )
+
+
+if __name__ == '__main__':
+    pass