from bs4 import BeautifulSoup
import requests
import time

list_url = ['http://bj.xiaozhu.com/zhengzu-duanzufang-{}/' .format(str(i)) for i in range(1,5,1)]
page_url = []

#性别验证
def get_sex(class_name):
    if class_name == ['member_ico']:
        return '男'
    else:
        return '女'

#获取详情页地址
def get_page_url(url):
    web_data = requests.get(url)
    time.sleep(1)
    soup = BeautifulSoup(web_data.text, 'lxml')
    links = soup.select('ul.pic_list > li > a[target="_blank"]')

    for link in links:
       href = link.get('href')
       get_content(href)

#获取详情页信息
def get_content(url) :
    page_data = requests.get(url)
    time.sleep(1)
    data = BeautifulSoup(page_data.text, 'lxml')

    titles = data.select('div.pho_info > h4 > em')
    addresses = data.select('span[class="pr5"]')
    fees = data.select('div.day_l > span')
    images = data.select('img[id="curBigImage"]')
    avatars = data.select('div.member_pic > a > img')
    sexs = data.select('div.member_pic > div')
    names = data.select('a[class="lorder_name"]')

    for title, address, fee, image, avatar, sex, name in zip (titles, addresses, fees, images, avatars,sexs, names):
        data = {
            'title' : title.get_text(),
            'address' : address.get_text(),
            'fee' : fee.get_text(),
            'image' : image.get('src'),
            'avatar' : avatar.get('src'),
            'sex' : get_sex(sex.get('class')),
            'name' : name.get_text(),
        }
        print(data)

#爬取开始
for list in list_url:
    get_page_url(list)