爬取链家数据3

1、直接上代码： 

#coding:utf-8
import sys
reload(sys)
sys.setdefaultencoding("utf-8")
import pandas as pd
import urllib2
import urllib
import time
import re
from bs4 import BeautifulSoup

totalPrice=[]
houseinfo=[]
followinfo=[]
for i in range(1,3):
    #读取指定网页的内容
    myurl="http://hz.lianjia.com/ershoufang/pg"+str(i)
    req = urllib2.Request(myurl)
    myResponse = urllib2.urlopen(req)
    myPage = myResponse.read()
    unmyPage = myPage.decode('utf-8')

    #匹配房源的总价
    c1=re.findall('<div.*?class="totalPrice".*?><span>(.*?)</span>(.*?)</div>',unmyPage,re.S)
    for item in c1:
        newitem=item[0]+item[1]
        totalPrice.append(newitem)
        #print newitem

    #匹配房源信息
    c2=re.findall('data-el="region">(.*?)</div>',unmyPage,re.S)
    for item in c2:
        item=re.sub('</a>','',item)  #将</a>替换掉
        houseinfo.append(item)

    #匹配房源关注度
    c3=re.findall('<span.*?class="starIcon"></span>(.*?)</div>',unmyPage,re.S)
    for item in c3:
        followinfo.append(item)

house=pd.DataFrame({'totalprice':totalPrice,'houseinfo':houseinfo,
    'followinfo':followinfo})
print house,house.index
print house.head()

#使用pandas对数据进行清洗
houseinfo_split = pd.DataFrame((x.split('|') for x in house.houseinfo),index=house.index,
    columns=['小区','户型','面积','朝向','装修','电梯'])
print houseinfo_split

运行结果：

G:\python2.7\python.exe E:/python37/jiebacut_01/DateCrawler/lianjia/lianjia3.py