Python 1-3

注意事项

• Beautiful Soup 反馈结果的类型
• strip() 函数如何去空格、回车等待
• str.format()函数 格式化字符串

from bs4 import BeautifulSoup
import requests

# 创建函数获取性别
# 通过host_sex.get("class")返回的是列表,判断条件需要 "==列表"
def get_host_sex(class_name):
    if class_name == ['member_girl_ico']:
        return '女'
    else:
        return '男'

def get_urls_list(url):
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text, 'lxml')
    links = soup.select('#page_list > ul > li > a')
    for link in links:
        get_item(link.get('href'))

def get_item(url):
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text, 'lxml')

    title = soup.select('div.pho_info > h4 > em')
    address = soup.select('div.pho_info > p > span.pr5')
    price = soup.select('div.day_l > span')
    img = soup.select('div.pho_show_l > div > div:nth-of-type(2) > img')
    host_name = soup.select('div.w_240 > h6 > a')
    host_img = soup.select('div.member_pic > a > img')
    host_sex = soup.select('div.w_240 > h6 > span')

    for title, address, price, img, host_name, host_img, host_sex in zip(title, address, price, img, host_name, host_img, host_sex ):
        data = {
            'title':title.get_text(),
            # 地址结果中存在空格和换行,通过strip()函数去除
            'address':address.get_text().strip(),
            'price':price.get_text(),
            'img':img.get("src"),
            'host_name':host_name.get_text(),
            'host_img':host_img.get("src"),
            'host_sex':get_host_sex(host_sex.get("class"))
        }
        print(data)

# 获取url列表,其中页面数通过格式化字符串的函数str.format()获取
page_urls = ['http://hz.xiaozhu.com/search-duanzufang-p{}-0/'.format(str(i)) for i in range(1,2)]
for page_url in page_urls:
    get_urls_list(page_url)