爬虫实战第三天

任务

爬取小猪短租北京地区（http://bj.xiaozhu.com/）租房信息（前三页）。

成果

将爬取的信息写入到了MongoDB中，并且查询了价格大于等于500/晚的租房信息。

源码

from bs4 import BeautifulSoup
from pymongo import MongoClient
import requests

pages = ['http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(str(i)) for i in range(1, 4)]
info = []
client = MongoClient('localhost', 27017)
xiao_zhu = client['xiao_zhu']
xiao_zhu_sheet = xiao_zhu['xiao_zhu_sheet']


def get_info(url):
    wb_data = requests.get(url)
    soup = BeautifulSoup(wb_data.text, 'lxml')
    data = {
        'title': soup.select('div.pho_info > h4 > em')[0].get_text(),
        'address': soup.select('div.pho_info > p > span')[0].get_text().strip(' ').strip('\n'),
        'price': int(soup.select('#pricePart > div.day_l > span')[0].get_text()),
        # 图片链接在chrome中不是直接打开而是下载，在IE中可以直接打开
        'house_image': soup.select('#curBigImage')[0]['src'],
        'master_name': soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > a')[0]['title'],
        'master_sex': soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > span')[0]['class'][0].split('_')[1],
        'master_image': soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > a > img')[0]['src']
    }
    xiao_zhu_sheet.insert_one(data)


def get_url(start_url):
    wb_data = requests.get(start_url)
    soup = BeautifulSoup(wb_data.text, 'lxml')
    urls = soup.select('#page_list > ul > li > a')
    return urls

for page in pages:
    urls = get_url(page)
    for url in urls:
        try:
            get_info(url['href'])
        except Exception as e:
            pass

'''
'price'关键字的属性类型必须为数值型，这样才能比较大小
$lt/$lte/$gt/$gte/$ne （l == less g == greater e == equal n == not）
使用print(type(xiao_zhu_sheet.find({'price': {'$gte': 500}})[0]))发现每个item实际上是一个dict
'''
for item in xiao_zhu_sheet.find({'price': {'$gte': 500}}):
    print(item)