爬取小豬短租上300條租房信息霜浴，包括標(biāo)題、地址蓝纲、日租金阴孟、房東、房東性別税迷、房東頭像永丝、房屋圖片等，如下圖所示：
1.png
最終程序運行截圖：
2.png
完整代碼：
from bs4 import BeautifulSoup
import requests
import time
def get_detail_info(url, data=None):
# 爬取單條租房信息（標(biāo)題箭养，圖片慕嚷，房東，日租金毕泌，房東性別喝检，房東頭像）
wb_data = requests.get(url)
soup = BeautifulSoup(wb_data.text, 'lxml')
time.sleep(2)
title = soup.select('h4 > em')[0].get_text()
address = soup.select('span.pr5')[0].get_text()
rent = soup.select('div.day_l > span')[0].get_text()
image = soup.select('#curBigImage')[0].get('src')
lorder_pic = soup.select('div.member_pic > a > img')[0].get('src')
lorder_name = soup.select('a.lorder_name')[0].get_text()
lorder_sex = soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > span')[0].get('class')
def get_gender(class_name):
if class_name == "member_boy_ico":
return "男"
else:
return "女"
data = {
'標(biāo)題': title,
'地址': address,
'日租金': rent,
'圖片': image,
'房東頭像': lorder_pic,
'房東姓名': lorder_name,
'房東性別': get_gender(lorder_sex)
}
print(data)
def get_links(url):
# 獲取詳情頁鏈接
wb_data = requests.get(url)
soup = BeautifulSoup(wb_data.text, 'lxml')
links = soup.select('#page_list > ul > li > a')
for link in links:
href = link.get('href')
get_detail_info(href)
urls = ['http://su.xiaozhu.com/search-duanzufang-p{}-0/'.format(str(i) for i in range(1,10))]
# 獲取9頁的租房信息
for url in urls:
get_links(url)
總結(jié)：
用requests庫打開網(wǎng)頁（get, post等方法）
