automatic_crawler/spider/crawler_online/zhuhaoshiduomo.py

import os
import json
import random
import sys
import time
import uuid
import requests
from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
from cryptography.hazmat.backends import default_backend

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

from application.items import VideoItem
from application.pipeline import PiaoQuanPipelineTest
from application.common.messageQueue import MQ
from application.common.proxies import tunnel_proxies


class AESCipher:
    def __init__(self):
        self.key = b'50102fa64073ad76'  # 用适当的方式转换或直接定义为字节串
        self.iv = b'173d023138824bb0'  # 同上

    def aes_encrypt(self, data):
        cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
        encryptor = cipher.encryptor()
        ct = encryptor.update(self._pad(data).encode()) + encryptor.finalize()
        return ct.hex().upper()

    def aes_decrypt(self, data):
        cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
        decryptor = cipher.decryptor()
        decrypted_data = decryptor.update(bytes.fromhex(data)) + decryptor.finalize()
        return self._unpad(decrypted_data).decode()

    def _pad(self, s):
        return s + (16 - len(s) % 16) * chr(16 - len(s) % 16)

    def _unpad(self, s):
        return s[:-ord(s[len(s) - 1:])]


class ZhuHaoShiDuoMoRecommend(object):
    """
    祝好事多磨小程序爬虫，测试版本
    """
    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.expire_flag = False
        self.cryptor = AESCipher()

    def get_recommend_list(self):
        """
        获取推荐流
        :return:
        """
        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/wx0afdc2669ed8df2f/3/page-frame.html',
            'accept-language': 'en-US,en;q=0.9'
        }
        page_index = 1
        total_page = 2
        while page_index <= total_page:
            query = {
                "pageNo": page_index,
                "pageSize": 10,
                "groupId": "1650323161797439489",  # 推荐流的 ID
                "vn": 1,
                "gx": 1,
                "appid": "wx0afdc2669ed8df2f",
                "type": 0
            }
            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))
            total_page = result['list']['pages']
            page_index = result['list']['current'] + 1
            for index, video_obj in enumerate(result['list']['records']):
                self.process_video_obj(video_obj)

    def process_video_obj(self, video_obj):
        """
        处理视频信息，清洗，规范化，发送至ETL
        :param video_obj: 视频信息
        :return: None
        """
        trace_id = self.platform + str(uuid.uuid1())
        play_cnt = int(video_obj['playnum'].replace("万+", "0000")) if "万+" in video_obj['playnum'] else int(
            video_obj['playnum'])
        item = VideoItem()
        user_dict = random.choice(self.user_list)
        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", user_dict['uid'])
        item.add_video_info("user_name", user_dict['link'])

        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():
            print(json.dumps(mq_obj, ensure_ascii=False, indent=4))
            self.download_cnt += 1
            print(self.download_cnt)

    def run(self):
        """
        执行函数
        """
        self.get_recommend_list()


if __name__ == '__main__':
    Z = ZhuHaoShiDuoMoRecommend(
        platform="zhuwanwufusu",
        mode="recommend",
        rule_dict={},
        user_dict={"uid": 123456, "nick_name": "luojunhuishuaige"},
        env="prod"
    )
    Z.get_recommend_list()