Python爬虫实例一

实例要求：
爬取小猪短租的房源链接以及每条房源链接的详情
详情爬取信息要求如下图：

爬取代码如下：

from bs4 import BeautifulSoup
import requests
import time
urls = ['http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(str(i)) for i in range(1,14,1)]

def get_info(concrete_url):
    wb_data = requests.get(concrete_url)
    soup = BeautifulSoup(wb_data.text)
    first_imgs = soup.select('div.pho_show_big > div[valign="middle"] > img')
    titles = soup.select('div.pho_info > h4')
    addresses = soup.select('span.pr5')
    daymoneys = soup.select('div.day_l > span')
    hostimgs = soup.select('div.member_pic > a[target="_blank"] > img')
    sexes = soup.select('div.member_pic > div')
    hostnames=soup.select('a.lorder_name')
    for first_img, title, address, daymoney, hostimg, hostsex, hostname in zip(first_imgs,titles,addresses,daymoneys,hostimgs,sexes,hostnames):
        if hostsex.get('class')[0]=='member_ico1':
            hostsexone = '男'
        if hostsex.get('class')[0]=='member_ico':
            hostsexone = '女'
        if hostsex.get('class')[0]=='':
            hostsexone = ' 暂无'
        concreteinfo={
            '房源图片':first_img.get('src'),
            '房屋标题': title.get_text(),
            '地址':address.get_text().strip(),
            '日租金':daymoney.get_text(),
            '房东照片':hostimg.get('src'),
            '房东性别':hostsexone,
            '房东名字':hostname.get_text()
        }
        print(concreteinfo)


def get_urllist(url):
    wb_data = requests.get(url)
    soup = BeautifulSoup(wb_data.text)
    url_fangzis = soup.select('a.resule_img_a')
    for url_fangzi in url_fangzis:
        data={
            'url':url_fangzi.get('href')
        }
        get_info(data.get('url'))
    time.sleep(4)



for url_one in urls:
    get_urllist(url_one)

爬取结果如下：