鏈家的房租網(wǎng)站
兩個導(dǎo)入的包
1.requests 用來過去網(wǎng)頁內(nèi)容 
2.BeautifulSoup
import time
import pymssql
import requests
from bs4 import BeautifulSoup
#  https://wh.lianjia.com/zufang/
#獲取url中下面的內(nèi)容
def get_page(url):
  responce = requests.get(url)
  soup = BeautifulSoup(responce.text,'lxml')
  return soup
#封裝成函數(shù)，作用是獲取列表下的所有租房頁面的鏈接，返回一個鏈接列表
def get_links(url):
  responce = requests.get(url)
  soup = BeautifulSoup(responce.text,'lxml')
  link_div = soup.find_all('div',class_ = 'pic-panel')
  links = [div.a.get('href') for div in link_div]
  return links
#收集一個房子的信息
def get_house_info(house_url):
  soup = get_page(house_url)
  price = soup.find('span',class_='total').text
  unit = soup.find('span',class_= 'unit').text[1:-1]
  area = soup.find('p', class_ = 'lf').text
  house_info= soup.find_all('p',class_ = 'lf')
  area = house_info[0].text[3:] #字符串切片工具
  layout = house_info[1].text[5:]
  info={
    '價格':price,
    '單位':unit,
    '面積':area,
    '戶型':layout
    }
  return info
#鏈接數(shù)據(jù)庫
server="192.168.xx.xx"  #換成自己的服務(wù)器信息
user="liujiepeng"
password="xxxxx"    #自己的數(shù)據(jù)庫用戶名和密碼
conn=pymssql.connect(server,user,password,database="house")
def insert(conn,house):
  #sql_values = values.format(house['價格'],house['單位'],house['面積'],
                #house['戶型'])
  sql = "insert into [house].dbo.lianjia(price,unit,area,layout)values('%s','%s','%s','%s')"%(house["價格"],house["單位"],house["面積"],house["戶型"])
  print(sql)
  cursor = conn.cursor() #游標(biāo)，開拓新的窗口
  #cursor1 = conn.cursor()
  cursor.execute(sql) #執(zhí)行sql語句
  conn.commit() #提交 ，更新sql 語句
links = get_links('https://wh.lianjia.com/zufang/')
count = 1
for link in links:
  #time.sleep(2)
  print('獲取一個數(shù)據(jù)成功')
  house = get_house_info(link)
  insert(conn,house)
  print("第%s個數(shù)據(jù)，存入數(shù)據(jù)庫成功！"%(count))
  count = count+1
  #print(house["價格"],end='\r')