from bs4 import BeautifulSoup
import requests
import time
urls = []
def get_link_from(page_number):
for each_number in range(1,page_number):
list_view = 'http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(each_number)
wb_data = requests.get(list_view)
soup = BeautifulSoup(wb_data.text,'lxml')
for link in soup.select('div.result_btm_con.lodgeunitname'):
urls.append(link.get('detailurl'))
return urls
def print_gender(class_name):
if class_name == "member_girl_ico":
return "女"
if class_name == "member_girl_icol":
return "男"
def get_item_info(page_number):
urls = get_link_from(page_number)
for url in urls:
wb_data =requests.get(url)
soup = BeautifulSoup(wb_data.text,'lxml')
data = {
'title ': soup.select('div.pho_info > h4')[0].text,
'address' : soup.select('div.pho_info > p > span')[0].text.strip(' '),
'price' : soup.select('#pricePart > div.day_l > span')[0].text,
'pic' : soup.select('#curBigImage')[0].get('src'),
'host_name' : soup.select('div.w_240 > h6')[0].text,
'host_gender' : soup.select('div.w_240 > h6 > span')[0].get('class')[0],
}
print(data)
get_item_info(14)
