# -*- coding: utf-8 -*-
import bs4
import requests
def open_url(url):
# url = 'https://su.lianjia.com/chengjiao/gongyeyuan/pg1/'
hd = {}
hd['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
r = requests.get(url,headers=hd,timeout=10)
return r
host = 'https://su.lianjia.com/chengjiao/gongyeyuan/pg'
aa = []
bb = []
for i in range(1,3):
url = host + str(i)
r = open_url(url)
soup = bs4.BeautifulSoup(r.text,'html.parser')
whvj = []
targets = soup.find_all('a',class_="img")
for each in targets:
whvj.append(each['href'])
# print(url)
# print(whvj)
for i in whvj:
soup1 = bs4.BeautifulSoup(open_url(i).text,'html.parser')
djjx = soup1.find_all("p",class_="record_detail")
for each in djjx:
aa.append(each.text)
xbxi = soup1.find_all("div",class_="name")
for each in xbxi:
bb.append(each.text)
with open('top250.txt','w',encoding='utf-8') as f:
for each in bb:
f.write('\n')
f.write(each)
##
#open_url('https://su.lianjia.com/chengjiao/107100984444.html')
#soup1 = bs4.BeautifulSoup(open_url('https://su.lianjia.com/chengjiao/107100984444.html').text,'html.parser')
#djjx = soup1.find_all("p",class_="record_detail")
#
#
##print(djjx)
#aa = []
#for each in djjx:
# aa.append(each.text)
#
#print (aa[0])
##print('*********************')
#
#xbxi = soup1.find_all("div",class_="name")
##print(xbxi)
##print('*********************')
#bb = []
#for each in xbxi:
# bb.append(each.text)
#print(bb[6])
##
python爬虫——链家苏州成交房价
最新推荐文章于 2023-05-20 15:01:22 发布