piaoquan_crawler/zhubaisuizhihao/zhubaisuizhihao_recommend/zbszh_recommend.py

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 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):
        """
        抓推荐流，只抓第一页
        """
        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'
        }
        query = {
            "pageNo": 1,
            "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))
        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
                )
                video_id = video_obj['id']
                self.get_detail_video_list(video_id)
            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)
                )

    def process_video_obj(self, video_obj):
        """
        process 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'])
        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 get_detail_video_list(self, video_id):
        """
        获取详情 id_list
        """
        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
        try:
            query = {
                "groupId": "1650323161797439489",
                "pageNo": 1,
                "pageSize": 10,
                "videoId": video_id,
                "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))
            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 __name__ == '__main__':
    pass