Python爬虫之爬取我爱我家二手房数据-巨人网络通讯

Python爬虫之爬取我爱我家二手房数据

一、问题说明

首先，运行下述代码，复现问题：

# -*-coding:utf-8-*-
import re
import requests
from bs4 import BeautifulSoup


cookie = 'PHPSESSID=aivms4ufg15sbrj0qgboo3c6gj; HMF_CI=4d8ff20092e9832daed8fe5eb0475663812603504e007aca93e6630c00b84dc207; _ga=GA1.2.556271139.1620784679; gr_user_id=4c878c8f-406b-46a0-86ee-a9baf2267477; _dx_uzZo5y=68b673b0aaec1f296c34e36c9e9d378bdb2050ab4638a066872a36f781c888efa97af3b5; smidV2=20210512095758ff7656962db3adf41fa8fdc8ddc02ecb00bac57209becfaa0; yfx_c_g_u_id_10000001=_ck21051209583410015104784406594; __TD_deviceId=41HK9PMCSF7GOT8G; zufang_cookiekey=["%7B%22url%22%3A%22%2Fzufang%2F_%25E9%2595%25BF%25E6%2598%25A5%25E6%25A1%25A5%3Fzn%3D%25E9%2595%25BF%25E6%2598%25A5%25E6%25A1%25A5%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E9%95%BF%E6%98%A5%E6%A1%A5%22%2C%22total%22%3A%220%22%7D","%7B%22url%22%3A%22%2Fzufang%2F_%25E8%258B%258F%25E5%25B7%259E%25E8%25A1%2597%3Fzn%3D%25E8%258B%258F%25E5%25B7%259E%25E8%25A1%2597%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E8%8B%8F%E5%B7%9E%E8%A1%97%22%2C%22total%22%3A%220%22%7D","%7B%22url%22%3A%22%2Fzufang%2F_%25E8%258B%258F%25E5%25B7%259E%25E6%25A1%25A5%3Fzn%3D%25E8%258B%258F%25E5%25B7%259E%25E6%25A1%25A5%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E8%8B%8F%E5%B7%9E%E6%A1%A5%22%2C%22total%22%3A%220%22%7D"]; ershoufang_cookiekey=["%7B%22url%22%3A%22%2Fzufang%2F_%25E9%2595%25BF%25E6%2598%25A5%25E6%25A1%25A5%3Fzn%3D%25E9%2595%25BF%25E6%2598%25A5%25E6%25A1%25A5%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E9%95%BF%E6%98%A5%E6%A1%A5%22%2C%22total%22%3A%220%22%7D","%7B%22url%22%3A%22%2Fershoufang%2F_%25E8%258B%258F%25E5%25B7%259E%25E6%25A1%25A5%3Fzn%3D%25E8%258B%258F%25E5%25B7%259E%25E6%25A1%25A5%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E8%8B%8F%E5%B7%9E%E6%A1%A5%22%2C%22total%22%3A%220%22%7D"]; zufang_BROWSES=501465046,501446051,90241951,90178388,90056278,90187979,501390110,90164392,90168076,501472221,501434480,501480593,501438374,501456072,90194547,90223523,501476326,90245144; historyCity=["\u5317\u4eac"]; _gid=GA1.2.23153704.1621410645; Hm_lvt_94ed3d23572054a86ed341d64b267ec6=1620784715,1621410646; _Jo0OQK=4958FA78A5CC420C425C480565EB46670E81832D8173C5B3CFE61303A51DE43E320422D6C7A15892C5B8B66971ED1B97A7334F0B591B193EBECAAB0E446D805316B26107A0B847CA53375B268E06EC955BB75B268E06EC955BB9D992FB153179892GJ1Z1OA==; ershoufang_BROWSES=501129552; domain=bj; 8fcfcf2bd7c58141_gr_session_id=61676ce2-ea23-4f77-8165-12edcc9ed902; 8fcfcf2bd7c58141_gr_session_id_61676ce2-ea23-4f77-8165-12edcc9ed902=true; yfx_f_l_v_t_10000001=f_t_1620784714003__r_t_1621471673953__v_t_1621474304616__r_c_2; Hm_lpvt_94ed3d23572054a86ed341d64b267ec6=1621475617'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36',
    'Cookie': cookie.encode("utf-8").decode("latin1")
}


def run():
    base_url = 'https://bj.5i5j.com/ershoufang/xichengqu/n%d/'
    for page in range(1, 11):
        url = base_url % page
        print(url)
        html = requests.get(url, headers=headers).text
        soup = BeautifulSoup(html, 'lxml')
        try:
            for li in soup.find('div', class_='list-con-box').find('ul', class_='pList').find_all('li'):
                title = li.find('h3', class_='listTit').get_text()  # 名称
                # print(title)
        except Exception as e:
            print(e)
            print(html)
            break


if __name__ == '__main__':
    run()

运行后会发现，在抓取https://bj.5i5j.com/ershoufang/xichengqu/n1/(也可能是其他页码)时，会报错：'NoneType' object has no attribute 'find'，观察输出的html信息，可以发现html内容为：HTML>HEAD>script>window.location.href="https://bj.5i5j.com/ershoufang/xichengqu/n1/?wscckey=0f36b400da92f41d_1621823822" rel="external nofollow" ;/script>/HEAD>BODY>，但此链接在浏览器访问是可以看到数据的，但链接会被重定向，重定向后的url即为上面这个html的href内容。因此，可以合理的推断，针对部分页码链接，我爱我家不会直接返回数据，但会返回带有正确链接的信息，通过正则表达式获取该链接即可正确抓取数据。

二、解决方法

在下面的完整代码中，采取的解决方法是：

1.首先判断当前html是否含有数据

2.若无数据，则通过正则表达式获取正确链接

3.重新获取html数据

if 'HTML>HEAD>script>window.location.href=' in html:
	url = re.search(r'.*?href="(.+)" rel="external nofollow"  rel="external nofollow" .*?', html).group(1)
	html = requests.get(url, headers=headers).text

三、完整代码

# -*-coding:utf-8-*-
import os
import re
import requests
import csv
import time
from bs4 import BeautifulSoup

folder_path = os.path.split(os.path.abspath(__file__))[0] + os.sep  # 获取当前文件所在目录
cookie = 'PHPSESSID=aivms4ufg15sbrj0qgboo3c6gj; HMF_CI=4d8ff20092e9832daed8fe5eb0475663812603504e007aca93e6630c00b84dc207; _ga=GA1.2.556271139.1620784679; gr_user_id=4c878c8f-406b-46a0-86ee-a9baf2267477; _dx_uzZo5y=68b673b0aaec1f296c34e36c9e9d378bdb2050ab4638a066872a36f781c888efa97af3b5; smidV2=20210512095758ff7656962db3adf41fa8fdc8ddc02ecb00bac57209becfaa0; yfx_c_g_u_id_10000001=_ck21051209583410015104784406594; __TD_deviceId=41HK9PMCSF7GOT8G; zufang_cookiekey=["%7B%22url%22%3A%22%2Fzufang%2F_%25E9%2595%25BF%25E6%2598%25A5%25E6%25A1%25A5%3Fzn%3D%25E9%2595%25BF%25E6%2598%25A5%25E6%25A1%25A5%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E9%95%BF%E6%98%A5%E6%A1%A5%22%2C%22total%22%3A%220%22%7D","%7B%22url%22%3A%22%2Fzufang%2F_%25E8%258B%258F%25E5%25B7%259E%25E8%25A1%2597%3Fzn%3D%25E8%258B%258F%25E5%25B7%259E%25E8%25A1%2597%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E8%8B%8F%E5%B7%9E%E8%A1%97%22%2C%22total%22%3A%220%22%7D","%7B%22url%22%3A%22%2Fzufang%2F_%25E8%258B%258F%25E5%25B7%259E%25E6%25A1%25A5%3Fzn%3D%25E8%258B%258F%25E5%25B7%259E%25E6%25A1%25A5%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E8%8B%8F%E5%B7%9E%E6%A1%A5%22%2C%22total%22%3A%220%22%7D"]; ershoufang_cookiekey=["%7B%22url%22%3A%22%2Fzufang%2F_%25E9%2595%25BF%25E6%2598%25A5%25E6%25A1%25A5%3Fzn%3D%25E9%2595%25BF%25E6%2598%25A5%25E6%25A1%25A5%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E9%95%BF%E6%98%A5%E6%A1%A5%22%2C%22total%22%3A%220%22%7D","%7B%22url%22%3A%22%2Fershoufang%2F_%25E8%258B%258F%25E5%25B7%259E%25E6%25A1%25A5%3Fzn%3D%25E8%258B%258F%25E5%25B7%259E%25E6%25A1%25A5%22%2C%22x%22%3A%220%22%2C%22y%22%3A%220%22%2C%22name%22%3A%22%E8%8B%8F%E5%B7%9E%E6%A1%A5%22%2C%22total%22%3A%220%22%7D"]; zufang_BROWSES=501465046,501446051,90241951,90178388,90056278,90187979,501390110,90164392,90168076,501472221,501434480,501480593,501438374,501456072,90194547,90223523,501476326,90245144; historyCity=["\u5317\u4eac"]; _gid=GA1.2.23153704.1621410645; Hm_lvt_94ed3d23572054a86ed341d64b267ec6=1620784715,1621410646; _Jo0OQK=4958FA78A5CC420C425C480565EB46670E81832D8173C5B3CFE61303A51DE43E320422D6C7A15892C5B8B66971ED1B97A7334F0B591B193EBECAAB0E446D805316B26107A0B847CA53375B268E06EC955BB75B268E06EC955BB9D992FB153179892GJ1Z1OA==; ershoufang_BROWSES=501129552; domain=bj; 8fcfcf2bd7c58141_gr_session_id=61676ce2-ea23-4f77-8165-12edcc9ed902; 8fcfcf2bd7c58141_gr_session_id_61676ce2-ea23-4f77-8165-12edcc9ed902=true; yfx_f_l_v_t_10000001=f_t_1620784714003__r_t_1621471673953__v_t_1621474304616__r_c_2; Hm_lpvt_94ed3d23572054a86ed341d64b267ec6=1621475617'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36',
    'Cookie': cookie.encode("utf-8").decode("latin1")
}


def get_page(url):
    """获取网页原始数据"""
    global headers
    html = requests.get(url, headers=headers).text
    return html


def extract_info(html):
    """解析网页数据，抽取出房源相关信息"""
    host = 'https://bj.5i5j.com'
    soup = BeautifulSoup(html, 'lxml')
    data = []
    for li in soup.find('div', class_='list-con-box').find('ul', class_='pList').find_all('li'):
        try:
            title = li.find('h3', class_='listTit').get_text()  # 名称
            url = host + li.find('h3', class_='listTit').a['href']  # 链接
            info_li = li.find('div', class_='listX')  # 每个房源核心信息都在这里
            p1 = info_li.find_all('p')[0].get_text()  # 获取第一段
            info1 = [i.strip() for i in p1.split('  ·  ')]
            # 户型、面积、朝向、楼层、装修、建成时间
            house_type, area, direction, floor, decoration, build_year = info1
            p2 = info_li.find_all('p')[1].get_text()  # 获取第二段
            info2 = [i.replace(' ', '') for i in p2.split('·')]
            # 小区、位于几环、交通信息
            if len(info2) == 2:
                residence, ring = info2
                transport = ''  # 部分房源无交通信息
            elif len(info2) == 3:
                residence, ring, transport = info2
            else:
                residence, ring, transport = ['', '', '']
            p3 = info_li.find_all('p')[2].get_text()  # 获取第三段
            info3 = [i.replace(' ', '') for i in p3.split('·')]
            # 关注人数、带看次数、发布时间
            try:
                watch, arrive, release_year = info3
            except Exception as e:
                print(info2, '获取带看、发布日期信息出错')
                watch, arrive, release_year = ['', '', '']
            total_price = li.find('p', class_='redC').get_text().strip()  # 房源总价
            univalence = li.find('div', class_='jia').find_all('p')[1].get_text().replace('单价', '')  # 房源单价
            else_info = li.find('div', class_='listTag').get_text()
            data.append([title, url, house_type, area, direction, floor, decoration, residence, ring,
                         transport, total_price, univalence, build_year, release_year, watch, arrive, else_info])
        except Exception as e:
            print('extract_info: ', e)
    return data


def crawl():
    esf_url = 'https://bj.5i5j.com/ershoufang/'  # 主页网址
    fields = ['城区', '名称', '链接', '户型', '面积', '朝向', '楼层', '装修', '小区', '环', '交通情况', '总价', '单价',
              '建成时间', '发布时间', '关注', '带看', '其他信息']
    f = open(folder_path + 'data' + os.sep + '北京二手房-我爱我家.csv', 'w', newline='', encoding='gb18030')
    writer = csv.writer(f, delimiter=',')  # 以逗号分割
    writer.writerow(fields)
    page = 1
    regex = re.compile(r'.*?href="(.+)" rel="external nofollow"  rel="external nofollow" .*?')
    while True:
        url = esf_url + 'n%s/' % page  # 构造页面链接
        if page == 1:
            url = esf_url
        html = get_page(url)
        # 部分页面链接无法获取数据，需进行判断，并从返回html内容中获取正确链接，重新获取html
        if 'HTML>HEAD>script>window.location.href=' in html:
            url = regex.search(html).group(1)
            html = requests.get(url, headers=headers).text
        print(url)
        data = extract_info(html)
        if data:
            writer.writerows(data)
        page += 1
    f.close()


if __name__ == '__main__':
    crawl()  # 启动爬虫