python实战计划第二周第一次：筛选房源

分成两部分，存储到mongodb和查找，较快完成，不过select的查找过长，下次争取用较短的元素定位。

我的成果

屏幕快照 2016-09-01 下午2.28.01.jpg

我的代码

from bs4 import BeautifulSoup
import requests
from pymongo import MongoClient

client=MongoClient('localhost',27017)
xiaozhu=client['xiaozhu']
page_list=xiaozhu['page_list']
apartment=xiaozhu['apartment']

def get_links():
    urls=['http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(i) for i in range(1,4)]
    for url in urls:
        wb_data=requests.get(url)
        soup=BeautifulSoup(wb_data.text,'lxml')
        links=soup.select('#page_list > ul > li > div.result_btm_con.lodgeunitname')
        for link in links:
            page_list.insert_one({'url':link.get('detailurl')})

def get_info(url):
    wb_data = requests.get(url)
    soup = BeautifulSoup(wb_data.text, 'lxml')
    title = soup.select('body > div.wrap.clearfix.con_bg > div.con_l > div.pho_info > h4 > em')
    area = soup.select('body > div.wrap.clearfix.con_bg > div.con_l > div.pho_info > p > span')
    price = soup.select('#pricePart > div.day_l > span')
    data = {
        'title': title[0].get_text(),
        'area': area[0].get_text() if soup.find_all('span','pr5') else None,
        'price': price[0].get_text(),
    }
    apartment.insert_one(data)
    print('done')

# get_links()
# for i in page_list.find():
#     get_info(i['url'])
for item in apartment.find():
    if int(item['price']) >=500:
        print(item['title'],item['area'])

总结

• 存储价格的时候是字符型了，所以查找的时候需要转化
• 简化定位元素