上线退休大本营爬虫

tuixiudabenying/tuixiudabenying_main/run_txdby_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 tuixiudabenying.tuixiudabenying_recommend import TuiXiuDaBenYingRecommend
+
+
+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="开始抓取退休大本营——推荐",
+                )
+                main_process = TuiXiuDaBenYingRecommend(
+                    platform=crawler,
+                    mode=log_type,
+                    rule_dict=rule_dict,
+                    user_list=user_list,
+                    env=env
+                )
+                main_process.get_video_list()
+                AliyunLogger.logging(
+                    code="1000",
+                    platform=crawler,
+                    mode=log_type,
+                    env=env,
+                    message="完成抓取——退休大本营",
+                )
+                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,
+    )

tuixiudabenying/tuixiudabenying_recommend/__init__.py

@@ -0,0 +1 @@
+from .tuixiudabenying_recommend import TuiXiuDaBenYingRecommend

tuixiudabenying/tuixiudabenying_recommend/functions.py

@@ -0,0 +1,62 @@
+import json
+import time
+import random
+import requests
+
+
+def get_tencent_video_url(video_id):
+    url = "https://h5vv.video.qq.com/getinfo?vid={}&platform=101001&charge=0&otype=json&defn=shd".format(
+        video_id
+    )
+    headers = {
+        "Host": "h5vv.video.qq.com",
+        "xweb_xhr": "1",
+        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF XWEB/30817",
+        "Content-Type": "application/x-www-form-urlencoded",
+        "Accept": "*/*",
+        "Sec-Fetch-Site": "cross-site",
+        "Sec-Fetch-Mode": "cors",
+        "Sec-Fetch-Dest": "empty",
+        "Referer": "https://servicewechat.com/wx5fcd817f3f80aece/3/page-frame.html",
+        "Accept-Language": "en",
+    }
+    response = requests.get(url, headers=headers)
+    result = json.loads(response.text.replace("QZOutputJson=", "")[:-1])
+    vl = result["vl"]["vi"][0]
+    key = vl["fvkey"]
+    name = vl["fn"]
+    folder = vl["ul"]["ui"][0]["url"]
+    video_url = folder + name + "?vkey=" + key
+    time.sleep(random.randint(1, 5))
+    return video_url
+
+
+def get_video_list():
+    url = "https://txdby.leyoukge.com/api/getVideoListByPagination"
+    params = {
+        "i": 1,
+        "v": "1.0.0",
+        "class_id": 6,
+        "page": 1
+    }
+    headers = {
+        'Host': 'txdby.leyoukge.com',
+        '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',
+        'Content-Type': 'application/x-www-form-urlencoded',
+        'Accept': '*/*',
+        'Referer': 'https://servicewechat.com/wx6665a673af83c3e8/3/page-frame.html',
+        'Accept-Language': 'en-US,en;q=0.9'
+    }
+    response = requests.request("GET", url, headers=headers, params=params)
+    # print(json.dumps(response.json(), indent=4, ensure_ascii=False))
+    return response.json()
+
+
+# result = get_video_list()
+# print(json.dumps(result, ensure_ascii=False, indent=4))
+for video_obj in get_video_list()['extra']:
+    vid = video_obj['vid']
+    print(video_obj['title'])
+    url = get_tencent_video_url(vid)
+    print(url)

tuixiudabenying/tuixiudabenying_recommend/tuixiudabenying_recommend.py

@@ -0,0 +1,175 @@
+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
+
+
+def get_tencent_video_url(video_id):
+    url = "https://h5vv.video.qq.com/getinfo?vid={}&platform=101001&charge=0&otype=json&defn=shd".format(
+        video_id
+    )
+    headers = {
+        "Host": "h5vv.video.qq.com",
+        "xweb_xhr": "1",
+        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF XWEB/30817",
+        "Content-Type": "application/x-www-form-urlencoded",
+        "Accept": "*/*",
+        "Sec-Fetch-Site": "cross-site",
+        "Sec-Fetch-Mode": "cors",
+        "Sec-Fetch-Dest": "empty",
+        "Referer": "https://servicewechat.com/wx5fcd817f3f80aece/3/page-frame.html",
+        "Accept-Language": "en",
+    }
+    response = requests.get(url, headers=headers)
+    result = json.loads(response.text.replace("QZOutputJson=", "")[:-1])
+    vl = result["vl"]["vi"][0]
+    key = vl["fvkey"]
+    name = vl["fn"]
+    folder = vl["ul"]["ui"][0]["url"]
+    video_url = folder + name + "?vkey=" + key
+    time.sleep(random.randint(1, 5))
+    return video_url
+
+
+class TuiXiuDaBenYingRecommend(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
+
+    def get_video_list(self):
+        """
+        推荐流并没有页数，每次请求数据不同，设置每天的抓取视频数量为100-200条
+        """
+        base_url = "https://txdby.leyoukge.com/api/getVideoListByPagination"
+        headers = {
+            'Host': 'txdby.leyoukge.com',
+            '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',
+            'Content-Type': 'application/x-www-form-urlencoded',
+            'Accept': '*/*',
+            'Referer': 'https://servicewechat.com/wx6665a673af83c3e8/3/page-frame.html',
+            'Accept-Language': 'en-US,en;q=0.9'
+        }
+        for i in range(1, 9):
+            time.sleep(random.randint(1, 10))
+            try:
+                if self.limit_flag:
+                    AliyunLogger.logging(
+                        code="2000",
+                        platform=self.platform,
+                        mode=self.mode,
+                        env=self.env,
+                        message="本轮已经抓取到足够的数据，自动退出\t{}".format(self.download_cnt),
+                    )
+                    return
+                else:
+                    params = {
+                        "i": 1,
+                        "v": "1.0.0",
+                        "class_id": 6,
+                        "page": i
+                    }
+                    response = requests.get(
+                        url=base_url,
+                        headers=headers,
+                        params=params,
+                        proxies=tunnel_proxies(),
+                    )
+                    video_list = response.json()['extra']
+                    if video_list:
+                        for index, video_obj in enumerate(video_list, 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,
+                                    data=video_obj,
+                                    message="抓取第{}条的时候出现问题， 报错信息是{}".format(index, e),
+                                )
+                    else:
+                        AliyunLogger.logging(
+                            code="2000",
+                            platform=self.platform,
+                            mode=self.mode,
+                            env=self.env,
+                            message="已经抓完了，自动退出"
+                        )
+                        return
+            except Exception as e:
+                AliyunLogger.logging(
+                    code="3000",
+                    platform=self.platform,
+                    mode=self.mode,
+                    env=self.env,
+                    message="抓取推荐页的时候出现错误， 报错信息是{}".format(e),
+                )
+
+    def process_video_obj(self, video_obj):
+        trace_id = self.platform + str(uuid.uuid1())
+        our_user = random.choice(self.user_list)
+        item = VideoItem()
+        item.add_video_info("user_id", our_user["uid"])
+        item.add_video_info("user_name", our_user["nick_name"])
+        item.add_video_info("video_id", video_obj["id"])
+        item.add_video_info("video_title", video_obj["title"])
+        vid = video_obj['vid']
+        video_url = get_tencent_video_url(video_id=vid)
+        item.add_video_info("video_url", video_url)
+        item.add_video_info("cover_url", video_obj['cover_url'])
+        item.add_video_info("play_cnt", video_obj['play'])
+        item.add_video_info("share_cnt", video_obj['forward'])
+        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())))
+        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)
+            # print(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

tuixiudabenying/tuixiudabenying_recommend/tuixiudabenying_recommend_dev.py

@@ -0,0 +1,149 @@
+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 tunnel_proxies
+from common.pipeline import PiaoQuanPipelineTest
+from common.mq import MQ
+
+
+def get_tencent_video_url(video_id):
+    url = "https://h5vv.video.qq.com/getinfo?vid={}&platform=101001&charge=0&otype=json&defn=shd".format(
+        video_id
+    )
+    headers = {
+        "Host": "h5vv.video.qq.com",
+        "xweb_xhr": "1",
+        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF XWEB/30817",
+        "Content-Type": "application/x-www-form-urlencoded",
+        "Accept": "*/*",
+        "Sec-Fetch-Site": "cross-site",
+        "Sec-Fetch-Mode": "cors",
+        "Sec-Fetch-Dest": "empty",
+        "Referer": "https://servicewechat.com/wx5fcd817f3f80aece/3/page-frame.html",
+        "Accept-Language": "en",
+    }
+    response = requests.get(url, headers=headers)
+    result = json.loads(response.text.replace("QZOutputJson=", "")[:-1])
+    vl = result["vl"]["vi"][0]
+    key = vl["fvkey"]
+    name = vl["fn"]
+    folder = vl["ul"]["ui"][0]["url"]
+    video_url = folder + name + "?vkey=" + key
+    time.sleep(random.randint(1, 5))
+    return video_url
+
+
+class TuiXiuDaBenYingRecommend(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
+
+    def get_video_list(self):
+        """
+        推荐流并没有页数，每次请求数据不同，设置每天的抓取视频数量为100-200条
+        """
+        base_url = "https://txdby.leyoukge.com/api/getVideoListByPagination"
+        headers = {
+            'Host': 'txdby.leyoukge.com',
+            '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',
+            'Content-Type': 'application/x-www-form-urlencoded',
+            'Accept': '*/*',
+            'Referer': 'https://servicewechat.com/wx6665a673af83c3e8/3/page-frame.html',
+            'Accept-Language': 'en-US,en;q=0.9'
+        }
+        for i in range(1, 9):
+            time.sleep(random.randint(1, 10))
+            try:
+                if self.limit_flag:
+                    message = "本轮已经抓取到足够的数据，自动退出\t{}".format(self.download_cnt)
+                    print(message)
+                    return
+                else:
+                    params = {
+                        "i": 1,
+                        "v": "1.0.0",
+                        "class_id": 6,
+                        "page": i
+                    }
+                    response = requests.get(
+                        url=base_url,
+                        headers=headers,
+                        params=params,
+                        proxies=tunnel_proxies(),
+                    )
+                    video_list = response.json()['extra']
+                    if video_list:
+                        for index, video_obj in enumerate(video_list, 1):
+                            try:
+                                print("扫描到一条视频")
+                                self.process_video_obj(video_obj)
+                            except Exception as e:
+                                print("抓取第{}条的时候出现问题， 报错信息是{}".format(index, e))
+                    else:
+                        print("已经抓完了，自动退出")
+                        return
+            except Exception as e:
+                print("抓取推荐页的时候出现错误， 报错信息是{}".format(e))
+
+    def process_video_obj(self, video_obj):
+        trace_id = self.platform + str(uuid.uuid1())
+        our_user = random.choice(self.user_list)
+        item = VideoItem()
+        item.add_video_info("user_id", our_user["uid"])
+        item.add_video_info("user_name", our_user["nick_name"])
+        item.add_video_info("video_id", video_obj["id"])
+        item.add_video_info("video_title", video_obj["title"])
+        vid = video_obj['vid']
+        video_url = get_tencent_video_url(video_id=vid)
+        item.add_video_info("video_url", video_url)
+        item.add_video_info("cover_url", video_obj['cover_url'])
+        item.add_video_info("play_cnt", video_obj['play'])
+        item.add_video_info("share_cnt", video_obj['forward'])
+        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())))
+        mq_obj = item.produce_item()
+        pipeline = PiaoQuanPipelineTest(
+            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)
+            print(json.dumps(mq_obj, ensure_ascii=False, indent=4))
+            print("成功发送至 ETL")
+            if self.download_cnt >= int(
+                    self.rule_dict.get("videos_cnt", {}).get("min", 200)
+            ):
+                self.limit_flag = True
+
+
+if __name__ == '__main__':
+    S = TuiXiuDaBenYingRecommend(
+        platform="tuixiudabenying",
+        mode="recommend",
+        env="dev",
+        rule_dict={},
+        user_list=[{'nick_name': "Ivring", 'uid': "1997"}, {'nick_name': "paul", 'uid': "1998"}]
+    )
+    S.get_video_list()