import requests
from bs4 import BeautifulSoup
def getpage(url):
responce = requests.get(url)
soup = BeautifulSoup(responce.text,'lxml')
return soup
def getlinks(link_url):
responce = requests.get(link_url)
format_list = BeautifulSoup(responce.text,'lxml')
link_div = format_list.find_all('div',class_='pic-panel')
links = [div.a.get('href') for div in link_div]
return links
url = 'https://bj.lianjia.com/zufang/'
house_url = 'https://bj.lianjia.com/zufang/101102926709.html'
def get_house_info(house_url):
# li = getlinks(url)
# print(li)
soup = getpage(house_url)
prince = soup.find('span',class_='total').text
unit = soup.find('span',class_='unit').text.strip()
house_info = soup.find_all('p')
area = house_info[0].text[3:]
layout = house_info[1].text[5:]
floor = house_info[2].text[3:]
direction = house_info[3].text[5:]
location = house_info[4].text[3:]
xiaoqu_location = house_info[5].text[3:7]
create_time = house_info[6].text[3:]
info ={'面积':area,
'分布':layout,
'楼层':floor,
'方向':direction,
'价格':prince,
'单价':unit,
'地铁':location,
'小区':xiaoqu_location,
'时间':create_time
}
return info
house = get_house_info(house_url)
for k,v in house.items():
print('{}:{}'.format(k,v))
网页题目:python爬取相关网站一些信息
当前URL:
http://bjjierui.cn/article/jhgcjh.html