爬虫11-途牛网

最新推荐文章于 2024-08-15 07:10:10 发布

原创

最新推荐文章于 2024-08-15 07:10:10 发布 · 1k 阅读

4 ·

CC 4.0 BY-SA版权

import requests
from bs4 import BeautifulSoup


def got_html(url):
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) '
                             'Chrome/69.0.3497.100 Safari/537.36'}
    # url = 'http://s.tuniu.com/search_complex/whole-nj-0-%E6%B3%B0%E5%9B%BD/'
    response = requests.get(url, headers=headers)
    html = response.content.decode()
    # print(html)
    return html


def parse_html(html):
    soup = BeautifulSoup(html, 'lxml')
    item_list = soup.select('ul[class="thebox clearfix"] li')
    print(len(item_list))
    for item in item_list:
        # 名称
        name = item.select('div > a > dl > dt > p.title > span')[0].get_text().strip()
        # 价格
        price = item.select('div > a > div.priceinfo > div.tnPrice > em')[0].get_text().strip()
        # 满意度
        dos = item.select('div > a > div.priceinfo > div.comment-sat.clearfix >