automatic_crawler/spider/crawler_online/jierizhufu.py

"""
@author luojunhui
节日祝福矩阵
节日祝福你祥贵
"""
import os
import sys
import time
import uuid
import random
import datetime
import requests

sys.path.append(os.getcwd())

from application.items import VideoItem
from application.pipeline import PiaoQuanPipeline
from application.common.messageQueue import MQ
from application.common.proxies import tunnel_proxies
from application.common.log import AliyunLogger


class JieRiZhuFu(object):
    """
    节日祝福矩阵——推荐爬虫
    """

    def __init__(self, platform, mode, rule_dict, user_list, env="prod"):
        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.expire_flag = False
        self.aliyun_log = AliyunLogger(platform=self.platform, mode=self.mode)

    def process_video_obj(self, video_obj):
        """
        处理每一个视频内容
        :return: None
        """
        trace_id = self.platform + str(uuid.uuid1())
        our_user = random.choice(self.user_list)
        publish_time_stamp = int(time.time())
        publish_time_str = datetime.datetime.fromtimestamp(publish_time_stamp).strftime(
            "%Y-%m-%d %H:%M:%S"
        )
        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"])
        item.add_video_info("publish_time_str", publish_time_str)
        item.add_video_info("publish_time_stamp", int(publish_time_stamp))
        item.add_video_info("video_url", video_obj["video_url"])
        item.add_video_info("cover_url", video_obj["video_cover"])
        item.add_video_info("out_video_id", video_obj["id"])
        item.add_video_info("play_cnt", video_obj['visited'])
        item.add_video_info("platform", self.platform)
        item.add_video_info("share_cnt", video_obj['shared'])
        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
            # print(json.dumps(mq_obj, ensure_ascii=False, indent=4))
            self.mq.send_msg(mq_obj)
            time.sleep(random.randint(1, 5))
            self.aliyun_log.logging(
                code="1002",
                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.expire_flag = True

    def get_recommend_list(self, page_index):
        """
        获取推荐页面的video_list
        :param page_index: 页码
        :return: None
        """
        if self.expire_flag:
            self.aliyun_log.logging(
                code="2000",
                message="本轮已经抓取到足够的数据，自动退出\t{}".format(self.download_cnt),
            )
            return
        url = "https://api.bestcaiwei.top/index.php"
        params = {
            "s": "mobile/Video/getList",
            "cid": 1,
            "page": page_index,
            "api_version": 4,
            "appid": "wx02bca7643610fee6",
            "version": "1.9.5",
            "env_version": "release",
            "scene": 1089
        }
        headers = {
            'Host': 'api.bestcaiwei.top',
            'ik': 'b326b5062b2f0e69046810717534cb09',
            '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/3.8.6(0x13080610) XWEB/1156',
            'token': 'eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpYXQiOjE3MTAzMDgxMDIsIm5iZiI6MTcxMDMwODEwMiwiZXhwIjoxNzEwMzExNzAyLCJkYXRhIjp7InVzZXJfaWQiOjQ0MTEzNTY2NH19.x6zQx2Ha_7C6g1UZKlxFPLU-JvJU4gaZ132_nzwLGEY',
            'Content-Type': 'application/json',
            'Accept': '*/*',
            'Sec-Fetch-Site': 'cross-site',
            'Sec-Fetch-Mode': 'cors',
            'Sec-Fetch-Dest': 'empty',
            'Referer': 'https://servicewechat.com/wx02bca7643610fee6/3/page-frame.html',
            'Accept-Language': 'en-US,en;q=0.9'
        }
        response = requests.request(
            "GET", url=url, headers=headers, params=params
        )
        data = response.json()
        for index, video_obj in enumerate(data["data"]["list"], 1):
            try:
                self.aliyun_log.logging(
                    code="1001",
                    message="扫描到一条视频",
                    data=video_obj,
                )
                self.process_video_obj(video_obj)
            except Exception as e:
                self.aliyun_log.logging(
                    code="3000",
                    message="抓取第{}条的时候出现问题， 报错信息是{}".format(index, e),
                )

    def run(self):
        """
        执行代码
        :return: None
        """
        for page in range(1, 10):
            if self.expire_flag:
                self.aliyun_log.logging(
                    code="2000",
                    message="本轮已经抓取到足够的数据，自动退出\t{}".format(self.download_cnt),
                )
                return
            else:
                # self.get_recommend_list(page_index=page)
                try:
                    self.get_recommend_list(page_index=page)
                except Exception as e:
                    self.aliyun_log.logging(
                        code="3000",
                        message="抓取第{}页时候出现错误， 报错信息是{}".format(page, e),
                    )