Python实战：抓取小猪短租租房信息

最终成果：

我的代码：

from bs4 import BeautifulSoup
import requests
url = 'http://bj.xiaozhu.com/'
urls = ['http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(str(i)) for i in range(1, 14)]
urls.insert(0, url)   # 得到13个网页的网址

info = []            # 保存得到的信息
def print_gender(class_name):      # 得到房主的性别
    if class_name == 'member_ico1':
        return '女'
    if class_name == 'member_ico':
        return '男'

def get_attractions(url):        #得到单个租房网址上的信息
    wb_data = requests.get(url)
    soup = BeautifulSoup(wb_data.text, 'lxml')
    title = soup.select('div.pho_info > h4')[0].text.strip()
    addr  = soup.select('div.pho_info > p')[0].get('title')
    price = soup.select('div.day_l > span')[0].text
    house_pic1 = soup.select('div.pho_show_big > div > img')[0].get('src')
    host_pic = soup.select('div.member_pic > a > img')[0].get('src')
    host_name = soup.select('div.w_240 > h6 > a')[0].text
    host_gender = soup.select('div.member_pic > div')[0].get('class')[0]

    data = {
        'title':title,
        'addr':addr,
        'price':price,
        'house_pic1':house_pic1,
        'host_pic' :host_pic,
        'host_name':host_name,
        'host_gender':print_gender(host_gender),
    }
    info.append(data)
    print(data)

links = []
def get_link(urls):         #得到所要抓取网页的链接
    for url in urls:
        wb_data = requests.get(url)
        soup = BeautifulSoup(wb_data.text, 'lxml')
        link = soup.select('ul > li > a.resule_img_a')

        for i in range(len(link)):
            links.append(link[i].get('href'))

get_link(urls)
for url in links:             #循环得到每个网页上所有链接网页上的信息
    get_attractions(url)

总结：

1. 获取标签信息的路径的方法，查看单个标签的唯一性路径

2.利用字符串的strip函数，去除字符串两边的空格，回车和Tab键

3.利用函数使代码清晰化