crawl_house/beike/phone.py

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
'''
@Contact :   liuyuqi.gov@msn.cn
@Time    :   2023/05/29 19:20:39
@License :   Copyright © 2017-2022 liuyuqi. All Rights Reserved.
@Desc    :   手机接口 
'''
import hashlib
import base64,json,random,time
import requests

class KePhone(object):
    ''' 调用app接口 '''
    
    def __init__(self):
        pass


    # 获取挂牌信息-贝壳网信息
    def get_guapai_data(self, xiaoqu_id):
        guapai_url = 'https://app.api.ke.com/house/ershoufang/searchv5'
        guapai_data = {
            'fullFilters': '1',
            'containerType': '2',
            'limitCount': '20',
            'condition': xiaoqu_id,
            'cityId': '**********',
            'limitOffset': '0'
        }
        # header抓一下复制进来
        headers = {
            "x-req-id": "**********",
            "Page-Schema": "ershou%2Flist",
            "Referer": "ershoulistsearch",
            "Cookie": "lianjia_udid=********;"
                      "lianjia_ssid=**********;"
                      "lianjia_uuid=**********",
            "Lianjia-City-Id": "**********",
            "User-Agent": "Beike2.31.0;Android MuMu; Android 6.0.1",
            "Lianjia-Channel": "**********",
            "Lianjia-Device-Id": "**********",
            "Lianjia-Version": "2.31.0",
            "Lianjia-Im-Version": "2.34.0",
            "Lianjia-Recommend-Allowable": "1",
            "Authorization": self.generateAuthorization(guapai_url, guapai_data),
            "ip": "**********",
            "wifi_name": "**********",
            "lat": "**********",
            "lng": "**********",
            "Host": "app.api.ke.com",
            "Connection": "Keep-Alive",
            "Accept-Encoding": "gzip"
        }
        guapai_res = requests.get(guapai_url, headers=headers, params=guapai_data)
        # 获取小区的挂牌信息列表
        guapai_json = json.loads(guapai_res.text)
        if guapai_json['errno'] == 0:
            guapai_info = guapai_json['data']['list']
            for i in guapai_info:
                # 插入数据库的信息列表
                sql_data = []
                if 'houseCode' in i:
                    # house_code
                    house_code = i['houseCode']
                    sql_data.append(house_code)
                    # 标题
                    resblock_name = i['title']
                    sql_data.append(resblock_name)
                    # 描述
                    resblock_desc = i['desc']
                    sql_data.append(resblock_desc)
                    # 总价
                    total_p = i['priceStr']
                    total_p = self.return_no(total_p)
                    sql_data.append(total_p)
                    # 小区
                    communityName = i['communityName']
                    sql_data.append(communityName)
                    # basicList处理
                    for basic_info in i['basicList']:
                        # pass
                        sql_data.append(basic_info['value'])
                    # infoList处理
                    for infoList_info in i['infoList']:
                        infoList_data = infoList_info['value']
                        if infoList_info['name'] == '单价：':
                            # 返回数字
                            infoList_data = self.return_no(infoList_data)
                        sql_data.append(infoList_data)
                    # 构造URL，用于微信推送
                    url = 'https://m.ke.com/tj/ershoufang/' + house_code + '.html'
                    sql_data.append(url)
                    # 数据插入数据库
                    self.insert_guapai(sql_data)
            # 休眠
            sleeptime = random.randint(2, 10)
            time.sleep(sleeptime)



    # 获取Authorization
    # 来源https://github.com/ShiJianYingxiang/origin/blob/master/fang_beike/fang_beike/spiders/ershou_viewer.py
    # url没用
    def generateAuthorization(self, url, url_parm):
        secret_key = "d5e343d453aecca8b14b2dc687c381ca"
        secret_id = "20180111_android"
        # 提取URL内参数
        # url_parm = {i.split("=")[0]: i.split("=")[1] for i in url.split("?")[1].split("&")}
        # 参数排序
        url_parm_sort = sorted(url_parm.items(), key=lambda x: x[0], reverse=False)
        p2 = secret_key + "".join([i[0] + "=" + i[1] for i in url_parm_sort])
        v3 = hashlib.sha1(p2.encode('utf-8')).hexdigest()
        v4 = secret_id + ":" + v3
        v5 = base64.b64encode(v4.encode("utf-8"))
        return v5.decode()


if __name__ == "__main__":
    pass