python爬取链家二手房的数据

# 爬取的url,默认爬取的南京的链家房产信息
url = 'https://nj.lianjia.com/ershoufang/pg{}/'.format(page)
# 请求url
resp = requests.get(url, headers=headers, timeout=10)

soup = BeautifulSoup(resp.content, 'lxml')
# 筛选全部的li标签
sellListContent = soup.select('.sellListContent li.LOGCLICKDATA')
# 循环遍历
for sell in sellListContent:
    # 标题
    title = sell.select('div.title a')[0].string
    # 先抓取全部的div信息，再针对每一条进行提取
    houseInfo = list(sell.select('div.houseInfo')[0].stripped_strings)
    # 楼盘名字
    loupan = houseInfo[0]
    # 对楼盘的信息进行分割
    info = houseInfo[0].split('|')
    # 房子类型
    house_type = info[1].strip()
    # 面积大小
    area = info[2].strip()
    # 房间朝向
    toward = info[3].strip()
    # 装修类型
    renovation = info[4].strip()
    # 房屋地址
    positionInfo = ''.join(list(sell.select('div.positionInfo')[0].stripped_strings))
    # 房屋总价
    totalPrice = ''.join(list(sell.select('div.totalPrice')[0].stripped_strings))
    # 房屋单价
    unitPrice = list(sell.select('div.unitPrice')[0].stripped_strings)[0]