基于Python實(shí)現(xiàn)最新房?jī)r(jià)信息的獲取

更新時(shí)間：2022年04月18日 08:20:42 作者：Python?集中營(yíng)

這篇文章主要為大家介紹了如何利用Python獲取房?jī)r(jià)信息（以北京為例），整個(gè)數(shù)據(jù)獲取的信息是通過(guò)房源平臺(tái)獲取的，通過(guò)下載網(wǎng)頁(yè)元素并進(jìn)行數(shù)據(jù)提取分析完成整個(gè)過(guò)程，需要的可以參考一下

整個(gè)數(shù)據(jù)獲取的信息是通過(guò)房源平臺(tái)獲取的，通過(guò)下載網(wǎng)頁(yè)元素并進(jìn)行數(shù)據(jù)提取分析完成整個(gè)過(guò)程

導(dǎo)入相關(guān)的網(wǎng)頁(yè)下載、數(shù)據(jù)解析、數(shù)據(jù)處理庫(kù)

from fake_useragent import UserAgent  # 身份信息生成庫(kù)

from bs4 import BeautifulSoup  # 網(wǎng)頁(yè)元素解析庫(kù)
import numpy as np  # 科學(xué)計(jì)算庫(kù)
import requests  # 網(wǎng)頁(yè)下載庫(kù)
from requests.exceptions import RequestException  # 網(wǎng)絡(luò)請(qǐng)求異常庫(kù)
import pandas as pd  # 數(shù)據(jù)處理庫(kù)

然后，在開(kāi)始之前初始化一個(gè)身份信息生成的對(duì)象，用于后面隨機(jī)生成網(wǎng)頁(yè)下載時(shí)的身份信息。

user_agent = UserAgent()

編寫一個(gè)網(wǎng)頁(yè)下載函數(shù)get_html_txt，從相應(yīng)的url地址下載網(wǎng)頁(yè)的html文本。

def get_html_txt(url, page_index):
    '''
    獲取網(wǎng)頁(yè)html文本信息
    :param url: 爬取地址
    :param page_index:當(dāng)前頁(yè)數(shù)
    :return:
    '''
    try:
        headers = {
            'user-agent': user_agent.random
        }
        response = requests.request("GET", url, headers=headers, timeout=10)
        html_txt = response.text
        return html_txt
    except RequestException as e:
        print('獲取第{0}頁(yè)網(wǎng)頁(yè)元素失??！'.format(page_index))
        return ''

編寫網(wǎng)頁(yè)元素處理函數(shù)catch_html_data，用于解析網(wǎng)頁(yè)元素，并將解析后的數(shù)據(jù)元素保存到csv文件中。

def catch_html_data(url, page_index):
    '''
    處理網(wǎng)頁(yè)元素?cái)?shù)據(jù)
    :param url: 爬蟲(chóng)地址
    :param page_index:
    :return:
    '''

    # 下載網(wǎng)頁(yè)元素
    html_txt = str(get_html_txt(url, page_index))

    if html_txt.strip() != '':

        # 初始化網(wǎng)頁(yè)元素對(duì)象
        beautifulSoup = BeautifulSoup(html_txt, 'lxml')

        # 解析房源列表
        h_list = beautifulSoup.select('.resblock-list-wrapper li')

        # 遍歷當(dāng)前房源的詳細(xì)信息
        for n in range(len(h_list)):
            h_detail = h_list[n]

            # 提取房源名稱
            h_detail_name = h_detail.select('.resblock-name a.name')
            h_detail_name = [m.get_text() for m in h_detail_name]
            h_detail_name = ' '.join(map(str, h_detail_name))

            # 提取房源類型
            h_detail_type = h_detail.select('.resblock-name span.resblock-type')
            h_detail_type = [m.get_text() for m in h_detail_type]
            h_detail_type = ' '.join(map(str, h_detail_type))

            # 提取房源銷售狀態(tài)
            h_detail_status = h_detail.select('.resblock-name span.sale-status')
            h_detail_status = [m.get_text() for m in h_detail_status]
            h_detail_status = ' '.join(map(str, h_detail_status))

            # 提取房源單價(jià)信息
            h_detail_price = h_detail.select('.resblock-price .main-price .number')
            h_detail_price = [m.get_text() for m in h_detail_price]
            h_detail_price = ' '.join(map(str, h_detail_price))

            # 提取房源總價(jià)信息
            h_detail_total_price = h_detail.select('.resblock-price .second')
            h_detail_total_price = [m.get_text() for m in h_detail_total_price]
            h_detail_total_price = ' '.join(map(str, h_detail_total_price))

            h_info = [h_detail_name, h_detail_type, h_detail_status, h_detail_price, h_detail_total_price]
            h_info = np.array(h_info)
            h_info = h_info.reshape(-1, 5)
            h_info = pd.DataFrame(h_info, columns=['房源名稱', '房源類型', '房源狀態(tài)', '房源均價(jià)', '房源總價(jià)'])
            h_info.to_csv('北京房源信息.csv', mode='a+', index=False, header=False)

        print('第{0}頁(yè)房源信息數(shù)據(jù)存儲(chǔ)成功！'.format(page_index))
    else:
        print('網(wǎng)頁(yè)元素解析失??！')

編寫多線程處理函數(shù)，初始化網(wǎng)絡(luò)網(wǎng)頁(yè)下載地址，并使用多線程啟動(dòng)調(diào)用業(yè)務(wù)處理函數(shù)catch_html_data，啟動(dòng)線程完成整個(gè)業(yè)務(wù)流程。

import threading  # 導(dǎo)入線程處理模塊


def thread_catch():
    '''
    線程處理函數(shù)
    :return:
    '''
    for num in range(1, 50, 3):
        url_pre = "https://bj.fang.lianjia.com/loupan/pg{0}/".format(str(num))
        url_cur = "https://bj.fang.lianjia.com/loupan/pg{0}/".format(str(num + 1))
        url_aft = "https://bj.fang.lianjia.com/loupan/pg{0}/".format(str(num + 2))

        thread_pre = threading.Thread(target=catch_html_data, args=(url_pre, num))
        thread_cur = threading.Thread(target=catch_html_data, args=(url_cur, num + 1))
        thread_aft = threading.Thread(target=catch_html_data, args=(url_aft, num + 2))
        thread_pre.start()
        thread_cur.start()
        thread_aft.start()


thread_catch()

數(shù)據(jù)存儲(chǔ)結(jié)果展示效果