python BeautifulSoup 获取豆瓣当前热映电影以及评分

今天药忘吃喽~ 2022-05-30 03:14 174阅读 0赞

> 使用urllib + Bs4

#!/usr/bin/env python
    # _*_ coding:utf-8 _*_
    import urllib2
    from bs4 import BeautifulSoup
    
    
    def agent():
        # 构造http 请求头
        headers = {
            'HOST': 'movie.douban.com',
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; rv:45.0) Gecko/20100101 Firefox/45.0',
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
            'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
            'Accept-Encoding': 'gzip, deflate, br',
            'DNT': '1',
            'Referer': 'https://movie.douban.com/',
            'Connection': 'keep-alive',
        }
        return headers
    
    
    def get_html(url):
        try:
            # 发送请求
            req = urllib2.Request(url)
            # 使用urllib2获取到页面源码
            html = urllib2.urlopen(req).read()
            # print html
        except urllib2.HTTPError:
            return 1
        else:
            return html
    
    
    def filter_html(url):
        # 解析html 页面
        html = get_html(url)
        # BS不能直接处理url,因此从urllib2那里获取到页面源码，再由BS解析
        s = BeautifulSoup(html)
        movie_dict = {}
        # 获取到页面的div id=screening这个属性的div里面就有当前热门电影,因此我们就获取这整个div
        for i in s.find_all('div', id="screening"):
            # ul标签就是html列表,这个div里面的ul就是电影列表
            li = i.find_all('ul')
            # print i.attrs
            for j in li:
                # print j
                # text是获取列表里面的字符
                content = j.text.encode('UTF-8')
                # 获取到的字符里面包含大量的空格因此需要处理
                name = content.strip().replace(' ', '').split()[0]
                score = content.strip().replace(' ', '').split()[1]
                # 将其加入字典电影名称作为键,分数作为值,这样做还有一个原因是获取的结果有重复的话,存到字典里面可以去重
                movie_dict[name] = score
                # print '%s  评分:%s' % (name, score)
        for k, v in movie_dict.items():
            print k, v
    if __name__ == "__main__":
        link = 'https://movie.douban.com/'
        filter_html(link)

> github 代码地址

[https://github.com/pythondever/douban][https_github.com_pythondever_douban]

[https_github.com_pythondever_douban]: https://github.com/pythondever/douban