レジストリデータ2
1808 ワード
#coding:utf-8
import sys
reload(sys)
sys.setdefaultencoding("utf-8") # 。 , pandas DataFrame
import pandas as pd
import urllib2
import urllib
import time
import re
from bs4 import BeautifulSoup
#
myurl="http://hz.lianjia.com/ershoufang/pg"+str(1)
req = urllib2.Request(myurl)
myResponse = urllib2.urlopen(req)
myPage = myResponse.read()
unmyPage = myPage.decode('utf-8') # Unicode
#
c1=re.findall('(.*?)(.*?)
',unmyPage,re.S)totalPrice=[]
for item in c1:
newitem=item[0]+item[1]
newitem=str(newitem)
totalPrice.append(newitem)
#ルームソース情報の照合
c2=re.findall('data-el="region">(.*?)',unmyPage,re.S)
houseinfo=[]
for item in c2:
#item=item.encode('utf-8')
#print isinstance(item,str)
houseinfo.append(item)
#部屋の注目度と一致する
c3=re.findall('(.*?)',unmyPage,re.S)
followinfo=[]
for item in c3:
followinfo.append(item)
house=pd.DataFrame({'totalprice':totalPrice,'houseinfo':houseinfo,
'followinfo':followinfo})
print type(house['totalprice'][0]) #str
print type(house['houseinfo'][0]) #unicode
print type(house['followinfo'][0]) #unicode
print house.head()
2、運行結果:
G:\python2.7\python.exe E:/python37/jiebacut_01/DateCrawler/lianjia/lianjia2.py
followinfo ... totalprice
0 173 / 58 / 3 ... 950
1 238 / 33 / 6 ... 480
2 164 / 19 / 3 ... 270
3 156 / 11 / 11 ... 585
4 70 / 26 / 3 ... 250
[5 rows x 3 columns]
Process finished with exit code 0