代码如下：
from bs4 import BeautifulSoup
from urllib import request
import time
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36'
}
def judgment_sex(class_name):
if class_name == ['member_ico1']:
return '女'
else:
return '男'
def get_links(url):
req = request.Request(url,headers=headers)
response = request.urlopen(req)
web_data = response.read()
soup = BeautifulSoup(web_data,'lxml')
links = soup.select("#page_list>ul>li>a")
for link in links:
href = link.get("href")
get_info(href)
def get_info(url):
req = request.Request(url, headers=headers)
response = request.urlopen(req)
web_data = response.read()
soup = BeautifulSoup(web_data,"lxml")
tittles = soup.select('div.pho_info>h4')
addresses = soup.select('span.pr5')
prices = soup.select('#pricePart>div.day_l>span')
imgs = soup.select('#floatRightBox>div.js_box.clearfix>div.member_pic>a>img')
names = soup.select('#floatRightBox>div.js_box.clearfix>div.w_240>h6>a')
sexs = soup.select('#floatRightBox>div.js_box.clearfix>div.member_pic>div')
for tittle,address,price,img,name,sex in zip(tittles,addresses,prices,imgs,names,sexs):
data = {
'tittle':tittle.get_text().strip(),
'address':address.get_text().strip(),
'img':img.get("src"),
'name':name.get_text(),
'sex':judgment_sex(sex.get("class"))
}
print(data)
if __name__== '_main_':
urls = ['http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(number)for number in
range(1,14)]
for single_url in urls:
get_links(single_url)
time.sleep(2)
如果不是程序的问题，是不是因为运行结果已经被保存在某个不知道的角落？还请大佬指点。
添加回答
举报
0/150
提交
取消