Beautiful Soup的简单实例

简单记录一下，bs的使用

# -*- coding: utf-8 -*-
import requests
import bs4

goal_url = "https://baike.baidu.com/item/%E8%88%8C%E5%B0%96%E4%B8%8A%E7%9A%84%E4%B8%AD%E5%9B%BD/9081375"

def start_parse(url):
    print "开始获取(%s)内容" % url
    response = requests.get(url)
    print "获取网页内容完毕"
    soup = bs4.BeautifulSoup(response.content.decode("utf-8"),'lxml')
    # soup = bs4.BeautifulSoup(response.text);
    # 为了防止漏掉调用close方法，这里使用了with语句
    # 写入到文件中的编码为utf-8
    with open('archives.txt', 'w') as f:
        for archive in soup.select("dd"):
            f.write(archive.get_text().encode('utf-8'))
            print archive.get_text().encode('utf-8')

if __name__ == '__main__':
    start_parse(goal_url)