祝百岁之好——推荐爬虫上线

zhubaisuizhihao/crypt/__init__.py

@@ -0,0 +1 @@
+from .crypt import AESCipher

zhubaisuizhihao/crypt/crypt.py

@@ -0,0 +1,26 @@
+from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
+from cryptography.hazmat.backends import default_backend
+
+
+class AESCipher:
+    def __init__(self):
+        self.key = b'50102fa64073ad76'  # 用适当的方式转换或直接定义为字节串
+        self.iv = b'173d023138824bb0'  # 同上
+
+    def aes_encrypt(self, data):
+        cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
+        encryptor = cipher.encryptor()
+        ct = encryptor.update(self._pad(data).encode()) + encryptor.finalize()
+        return ct.hex().upper()
+
+    def aes_decrypt(self, data):
+        cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
+        decryptor = cipher.decryptor()
+        decrypted_data = decryptor.update(bytes.fromhex(data)) + decryptor.finalize()
+        return self._unpad(decrypted_data).decode()
+
+    def _pad(self, s):
+        return s + (16 - len(s) % 16) * chr(16 - len(s) % 16)
+
+    def _unpad(self, s):
+        return s[:-ord(s[len(s) - 1:])]

zhubaisuizhihao/zhubaishuizhihao_main/run_zbszh_recommend.py

@@ -0,0 +1,155 @@
+import argparse
+import time
+import random
+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 zhuwanwufusu.zhuwanwufusu_recommend import ZhuWanWuFuSuRecommend
+
+
+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="开始抓取祝万物复苏——推荐",
+                )
+                main_process = ZhuWanWuFuSuRecommend(
+                    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——祝万物复苏",
+                )
+                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,
+    )

zhubaisuizhihao/zhubaishuizhihao_recommend/__init__.py

@@ -0,0 +1 @@
+from .zbszh_recommend import ZhuBaiSuiZhiHaoRecommend

zhubaisuizhihao/zhubaishuizhihao_recommend/zbszh_recommend.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 ZhuBaiSuiZhiHaoRecommend(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/wx87c457cfb89f95ad/4/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": "wx87c457cfb89f95ad",
+                    "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/wx87c457cfb89f95ad/4/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/wx87c457cfb89f95ad/4/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/wx87c457cfb89f95ad/4/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": "wx87c457cfb89f95ad",
+                        "type": 2,
+                        "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