作业要求

我的代码

#-*- coding:utf-8 -*-
#本次作业完成完成爬取300个租房信息
#爬取网站为:http://bj.xiaozhu.com/search-duanzufang-p1-0/
#需要打开每一个租房图片的连接,打开新页面,在新页面获取租房信息

from bs4 import BeautifulSoup
import requests
import time

def _getSoup(url, headers):
    webSite = requests.get(url, headers)
    return BeautifulSoup(webSite.text, 'lxml') #注意第一个参数.text

def getProductUrl(url, headers):
    '''
    :param url: 搜索页的URL
    :param headers: 默认为本机的hearders,
    :return: list, 每一个元素为商品页的URL
    '''
    soup = _getSoup(url, headers)
    productsTemp = soup.select('a.resule_img_a') #获取搜索页中,房屋的链接位置
    products = [str(pro.get('href')) for pro in productsTemp] #获取链接

    return products

def getAttribute(url, headers):
    '''
    :param url: 商品页的URL
    :param headers: 用户的headers
    :return: 一个包含商品信息的dict
    '''
    time.sleep(2)
    soup = _getSoup(url, headers)
    title = soup.select('div.pho_info > h4 > em')
    address = soup.select('div.pho_info > p > span')
    image = soup.select('#curBigImage')
    price = soup.select('div.day_l > span')
    rentingType = soup.select('#introduce > li.border_none > h6')
    roomInfo = soup.select('#introduce > li.border_none > p')
    bedNum = soup.select('#introduce > li:nth-of-type(3) > h6')
    bedInfo = soup.select('#introduce > li:nth-of-type(3) > p')
    lorderName = soup.select('a.lorder_name')
    lorderGender = soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > div')
    lorderCredit = soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > p')

    genderLabel = lorderGender[0].get('class')[0] #.get返回的是一个list
    if genderLabel == 'member_ico':
        gender = 'male'
    elif genderLabel == 'member_ico1':
        gender = 'female'
    else:
        gender = 'unknown'

    creditLabel = lorderCredit[0].find_all('span', class_ = 'zm_ico')
    if len(creditLabel) != 0:
        credit = creditLabel[0].get_text()
    else:
        credit = 'unknown'

    attribute = {
        'title' : title[0].get_text(),
        'address' : address[0].get_text().strip(), #将地址后面的空格和换行符号去除
        'image' : image[0].get('src'),
        'price' : int(price[0].get_text()), #日租金应该是整型
        'rentingType' : rentingType[0].get_text(), #租房类型:单间?整套?...
        'area' : float(list(roomInfo[0].stripped_strings)[0].split('：')[1][:-2]), #房屋面积
        'apartment' : list(roomInfo[0].stripped_strings)[1][5:], #房屋户型
        'bedNum' : int(bedNum[0].get_text()[1:][:-1]), #床的数量,整型
        'bedInfo' : list(bedInfo[0].stripped_strings), #床的信息
        'lorderName' : lorderName[0].get_text(), #用户姓名
        'lorderGender': gender, #用户性别
        'lorderCredit' : credit #用户的芝麻信用值

    }

    return attribute

def main():
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/51.0.2704.106 Safari/537.36 Name'
    }
    pageNum = 1  # 开始的搜索页的页码
    roomNum = 0  # 已经完成的房间数
    while roomNum <= 300:

        print('page', str(pageNum))  # 当前搜索页的页码
        url = 'http://bj.xiaozhu.com/search-duanzufang-p{}/'.format(str(pageNum))  # 当前搜索页的URL
        products = getProductUrl(url, headers=headers)  # 获取当前搜索页的房源链接list
        print(products)
        roomsCurrentPage = [getAttribute(url, headers) for url in products]
        # 将房源信息写入rooms.txt中
        with open('/Users/xyh/Documents/python/python3/Week1/1_3/rooms.txt', 'a') as text:
            for room in roomsCurrentPage:
                text.write(str(room))
                text.write('\n')
                roomNum += 1

        pageNum += 1

    print('已搞定!')

if __name__ == '__main__':
    main()