piaoquan_crawler/shanhuzhufu/shanhuzhufu_recommend/shanhuzhufu_recommend_scheduling.py

import os
import json
import random
import sys
import time
import uuid

import requests
import datetime

sys.path.append(os.getcwd())
from common.video_item import VideoItem
from common import PiaoQuanPipeline, AliyunLogger, tunnel_proxies
from common.mq import MQ
from shanhuzhufu.crypt.decrypt import ShanHuZhuFuAes as AES


class ShanHuZhuFuRecommend(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_video_list(self):
        base_url = "https://shanhu.nnapi.cn/videos/api.videos/getItem"
        headers = {
            'Host': 'shanhu.nnapi.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/json',
          'accept': '*/*',
          'sec-fetch-site': 'cross-site',
          'sec-fetch-mode': 'cors',
          'sec-fetch-dest': 'empty',
          'referer': 'https://servicewechat.com/wxc2088c70f666b45e/2/page-frame.html',
          'accept-language': 'en-US,en;q=0.9',
          'Cookie': 'PHPSESSID=562dc39e8e68ad3e76c237f687bd049b; lang=zh-cn'
        }
        for i in range(100):
            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 = {
                        "mark": "",
                        "page": i + 1
                    }
                    response = requests.get(url=base_url, headers=headers, params=params, proxies=tunnel_proxies())
                    encrypted_info = response.json()['data']
                    decrypted_info = json.loads(self.cryptor.decrypt(data=encrypted_info))
                    video_list = decrypted_info['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,
                                message="抓取第{}条的时候出现问题， 报错信息是{}".format(index, e)
                            )
            except Exception as e:
                AliyunLogger.logging(
                    code="3000",
                    platform=self.platform,
                    mode=self.mode,
                    env=self.env,
                    message="抓取第{}页时候出现错误， 报错信息是{}".format(i + 1, e)
                )

    def process_video_obj(self, video_obj):
        trace_id = self.platform + str(uuid.uuid1())
        our_user = random.choice(self.user_list)
        publish_time_stamp = datetime.datetime.strptime(video_obj['create_at'], "%Y-%m-%d %H:%M:%S").timestamp()
        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['name'])
        item.add_video_info("publish_time_str", video_obj['create_at'])
        item.add_video_info("publish_time_stamp", int(publish_time_stamp))
        item.add_video_info("video_url", video_obj['cover'])
        item.add_video_info("cover_url", video_obj['cover'] + '&vframe/png/offset/1/w/200')
        item.add_video_info("like_cnt", video_obj['num_like'])
        item.add_video_info("play_cnt", video_obj['num_read'])
        item.add_video_info("comment_cnt", video_obj['num_comment'])
        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)
            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