【爬虫】找呀找呀找房子

背景

特么的一个客厅的隔断要涨到2200！！！！！！

版本

python 2.7

前置条件

requests和beautifulsoup4的包包

代码

import types
import requests
from bs4 import BeautifulSoup
output = open('ganji.txt','w')
res = requests.get('http://bj.ganji.com/fang1/lishuiqiao/a1h3m1/')  #lishuiqiao
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')
for fangzi in soup.select('.f-list-item '):
    # title and url
    size = ''
    dd_title = fangzi.dl.find_all('dd',"dd-item title")
    if dd_title[0].a['href'][0:1] == '/':
        url = 'http://bj.ganji.com' + dd_title[0].a['href'].encode('utf8')
    else:
        url = dd_title[0].a['href'].encode('utf8')
    title = dd_title[0].text.strip().encode('utf8')

    # size
    dd_size = fangzi.dl.find_all('dd', "dd-item size")[0].contents
    for i in dd_size:
        if type(i) == type(fangzi):
            if len(i.text) > 0:
               size += i.text.encode('utf8') + ' '

    # price
    dd_price = fangzi.dl.find_all('dd',"dd-item info")
    price = dd_price[0].text.encode('utf8')

    # print title
    print title # debug
    output.write(title+'\r\n')  # write to file

    # print size
    print size
    output.write(size+'\r\n')  # write to file

    # print price
    print price
    output.write(price + '\r\n')  # write to file

    # print url
    print url
    print  '=========================================='
    output.write(url+'\r\n')  # write to file
    output.write( '==========================================\r\n')
output.close()

我这里是从赶集网上搞的，

res = requests.get('http://bj.ganji.com/fang1/lishuiqiao/a1h3m1/')  #lishuiqiao

第4行这段url可以把中间的lishuiqiao改成huoying（霍营）、xierqi（西二旗）等等（限北京，其他地区要把bj也改掉），亲测有效。

测试截图