每天送祝福——爬虫上线

jingdianfuqiwang/jingdianfuqiwang_recommend/jingdianfuqiwang_dev.py

@@ -1,9 +1,9 @@
 import json
 import requests
-from urllib.parse import urlencode
+from common import tunnel_proxies
 
 url = "https://jdfqw.wentingyou.cn/index.php/v111/index/index"
-obj = {"cid":"","page":60,"is_ads":1}
+obj = {"cid":"","page":1,"is_ads":1}
 w = json.dumps(obj)
 # params = {}
 headers = {
@@ -20,7 +20,7 @@ headers = {
 }
 
 
-response = requests.request("GET", url, headers=headers, params={"parameter": w})
+response = requests.request("GET", url, headers=headers, params={"parameter": w}, proxies=tunnel_proxies())
 print(response.url)
 
 print(json.dumps(response.json(), ensure_ascii=False, indent=4))

jingdianfuqiwang/jingdianfuqiwang_recommend/test3.py

@@ -0,0 +1,25 @@
+import requests
+
+url = "https://music-video-bos.cdn.bcebos.com/4d78865df946c655b74dfa71bb09f265/65683a1a/video/20230816/a8b22de9c0d2332fde0dae480780f426_1.mp4"
+
+payload = {}
+headers = {
+  'Host': 'music-video-bos.cdn.bcebos.com',
+  'sec-ch-ua': '"Google Chrome";v="119", "Chromium";v="119", "Not?A_Brand";v="24"',
+  'sec-ch-ua-mobile': '?0',
+  'sec-ch-ua-platform': '"macOS"',
+  'upgrade-insecure-requests': '1',
+  'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36',
+  'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+  'sec-fetch-site': 'none',
+  'sec-fetch-mode': 'navigate',
+  'sec-fetch-user': '?1',
+  'sec-fetch-dest': 'document',
+'referer': 'https://servicewechat.com/',
+  'accept-language': 'en,zh-CN;q=0.9,zh;q=0.8',
+}
+
+response = requests.request("GET", url, headers=headers, data=payload)
+
+print(response.text)
+

meitiansongnizhufu/meitiansongzhufu_recommend/__init__.py

@@ -0,0 +1 @@
+from .meitiansongzhufu_recommend import SongZhuFuRecommend

meitiansongnizhufu/meitiansongzhufu_recommend/main_request.py

@@ -0,0 +1,70 @@
+import json
+
+import requests
+
+
+def get_video_detail(vid, userad, cate):
+    # URL and payload
+    url = "https://gkvxwq2023.we-media.cn/app/index.php"
+    payload = {
+        "i": "1",
+        "t": "0",
+        "m": "jyt_txvideo",
+        "v": "1.0.0",
+        "from": "wxapp",
+        "c": "entry",
+        "a": "wxapp",
+        "do": "videodetail",
+        "vid": vid,
+        "userad": userad,
+        "cate": cate,
+    }
+    headers = {
+        "Host": "gkvxwq2023.we-media.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",
+        "content-type": "application/x-www-form-urlencoded",
+        "accept": "*/*",
+        "referer": "https://servicewechat.com/wx49f06df06becc7fa/2/page-frame.html",
+        "accept-language": "en-US,en;q=0.9",
+    }
+    response = requests.request("POST", url, headers=headers, data=payload)
+    print(json.dumps(response.json(), ensure_ascii=False, indent=4))
+
+
+def get_video_list():
+    url = "https://gkvxwq2023.we-media.cn/app/index.php"
+    payload = {
+        "i": "1",
+        "t": "0",
+        "m": "jyt_txvideo",
+        "v": "1.0.0",
+        "from": "wxapp",
+        "c": "entry",
+        "a": "wxapp",
+        "do": "videotui",
+        "city": "",
+        "category": "494",
+    }
+    headers = {
+        "Host": "gkvxwq2023.we-media.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",
+        "content-type": "application/x-www-form-urlencoded",
+        "accept": "*/*",
+        "referer": "https://servicewechat.com/wx49f06df06becc7fa/2/page-frame.html",
+        "accept-language": "en-US,en;q=0.9",
+    }
+    response = requests.post(url, data=payload, headers=headers)
+    return response.json()
+
+
+
+if __name__ == "__main__":
+    result = get_video_list()
+    # print(json.dumps(result, ensure_ascii=False, indent=4))
+    for video_obj in result["data"]:
+        vid = video_obj['vid']
+        cate = video_obj['category']
+        userad = ''
+        get_video_detail(vid=vid, userad=userad, cate=cate)

meitiansongnizhufu/meitiansongzhufu_recommend/meitiansongzhufu_dev.py

@@ -0,0 +1,158 @@
+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
+
+
+def get_video_detail(vid, userad, cate):
+    time.sleep(random.randint(5, 25))
+    url = "https://gkvxwq2023.we-media.cn/app/index.php"
+    payload = {
+        "i": "1",
+        "t": "0",
+        "m": "jyt_txvideo",
+        "v": "1.0.0",
+        "from": "wxapp",
+        "c": "entry",
+        "a": "wxapp",
+        "do": "videodetail",
+        "vid": vid,
+        "userad": userad,
+        "cate": cate,
+    }
+    headers = {
+        "Host": "gkvxwq2023.we-media.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",
+        "content-type": "application/x-www-form-urlencoded",
+        "accept": "*/*",
+        "referer": "https://servicewechat.com/wx49f06df06becc7fa/2/page-frame.html",
+        "accept-language": "en-US,en;q=0.9",
+    }
+    response = requests.request("POST", url, headers=headers, data=payload)
+    return response.json()
+
+
+class SongZhuFuRecommend(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.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://gkvxwq2023.we-media.cn/app/index.php"
+        headers = {
+            "Host": "gkvxwq2023.we-media.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",
+            "content-type": "application/x-www-form-urlencoded",
+            "accept": "*/*",
+            "referer": "https://servicewechat.com/wx49f06df06becc7fa/2/page-frame.html",
+            "accept-language": "en-US,en;q=0.9",
+        }
+        params = {
+            "i": "1",
+            "t": "0",
+            "m": "jyt_txvideo",
+            "v": "1.0.0",
+            "from": "wxapp",
+            "c": "entry",
+            "a": "wxapp",
+            "do": "videotui",
+            "city": "",
+            "category": "494",
+        }
+        while True:
+            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:
+                    response = requests.get(
+                        url=base_url,
+                        headers=headers,
+                        params=params,
+                        proxies=tunnel_proxies(),
+                    )
+                    video_list = response.json()['data']
+                    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["vtitle"])
+        item.add_video_info("publish_time_stamp", int(video_obj['create_time']))
+        vid = video_obj['vid']
+        userad = ""
+        cate = video_obj['category']
+        detail_obj = get_video_detail(vid=vid, userad=userad, cate=cate)['data']
+        item.add_video_info("video_url", detail_obj['vid'])
+        item.add_video_info("cover_url", detail_obj["poster"])
+        item.add_video_info("duration", detail_obj['vtime'])
+        item.add_video_info("play_cnt", detail_obj['realview'])
+        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(mq_obj)
+            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 = SongZhuFuRecommend(
+        platform="meitiansongzhufu",
+        mode="recommend",
+        env="dev",
+        rule_dict={},
+        user_list=[{'nick_name': "Ivring", 'uid': "1997"}, {'nick_name': "paul", 'uid': "1998"}]
+    )
+    S.get_video_list()

meitiansongnizhufu/meitiansongzhufu_recommend/meitiansongzhufu_recommend.py

@@ -0,0 +1,190 @@
+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_video_detail(vid, userad, cate):
+    time.sleep(random.randint(5, 25))
+    url = "https://gkvxwq2023.we-media.cn/app/index.php"
+    payload = {
+        "i": "1",
+        "t": "0",
+        "m": "jyt_txvideo",
+        "v": "1.0.0",
+        "from": "wxapp",
+        "c": "entry",
+        "a": "wxapp",
+        "do": "videodetail",
+        "vid": vid,
+        "userad": userad,
+        "cate": cate,
+    }
+    headers = {
+        "Host": "gkvxwq2023.we-media.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",
+        "content-type": "application/x-www-form-urlencoded",
+        "accept": "*/*",
+        "referer": "https://servicewechat.com/wx49f06df06becc7fa/2/page-frame.html",
+        "accept-language": "en-US,en;q=0.9",
+    }
+    response = requests.request("POST", url, headers=headers, data=payload)
+    return response.json()
+
+
+class SongZhuFuRecommend(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://gkvxwq2023.we-media.cn/app/index.php"
+        headers = {
+            "Host": "gkvxwq2023.we-media.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",
+            "content-type": "application/x-www-form-urlencoded",
+            "accept": "*/*",
+            "referer": "https://servicewechat.com/wx49f06df06becc7fa/2/page-frame.html",
+            "accept-language": "en-US,en;q=0.9",
+        }
+        params = {
+            "i": "1",
+            "t": "0",
+            "m": "jyt_txvideo",
+            "v": "1.0.0",
+            "from": "wxapp",
+            "c": "entry",
+            "a": "wxapp",
+            "do": "videotui",
+            "city": "",
+            "category": "494",
+        }
+        while True:
+            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:
+                    response = requests.get(
+                        url=base_url,
+                        headers=headers,
+                        params=params,
+                        proxies=tunnel_proxies(),
+                    )
+                    video_list = response.json()['data']
+                    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["vtitle"])
+        item.add_video_info("publish_time_stamp", int(video_obj['create_time']))
+        vid = video_obj['vid']
+        if vid.startswith("new"):
+            userad = ""
+            cate = video_obj['category']
+        else:
+            return
+        detail_obj = get_video_detail(vid=vid, userad=userad, cate=cate)['data']
+        item.add_video_info("video_url", detail_obj['vid'])
+        item.add_video_info("cover_url", detail_obj["poster"])
+        item.add_video_info("duration", detail_obj['vtime'])
+        item.add_video_info("play_cnt", detail_obj['realview'])
+        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
+

meitiansongnizhufu/meitiansonhzhufu_main/run_mtszf_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 meitiansongnizhufu.meitiansongzhufu_recommend import SongZhuFuRecommend
+
+
+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="开始抓取每天送祝福——推荐",
+                )
+                main_process = SongZhuFuRecommend(
+                    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——每天送祝福",
+                )
+                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,
+    )