python3 爬取豆瓣电影TOP250，漂亮表格彩色显示

傷城~ 2022-05-10 04:46 139阅读 0赞

#coding=utf-8  
    import requests
    import re
    from bs4 import BeautifulSoup
    from prettytable import PrettyTable
    from colorama import Fore,Style
     
    
    def getHtml(url):  
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:56.0) Gecko/20100101 Firefox/56.0'}  
        page = requests.get(url,headers = headers)
        html =page.text
        return html
    
    if __name__=='__main__':
        table = PrettyTable(['NO.','movie','year','star','vote'])
        movies = []
        years = []
        stars = []
        votes = []
        for page in range(0,250,25):
            url = 'https://movie.douban.com/top250?start={0}&filter='.format(page)
            Html = getHtml(url)
            Soup = BeautifulSoup(Html,'html.parser')
            names = Soup.find_all('div',class_ = 'info')
            
            for name in names:
                movie = name.find_all('span',class_ = 'title')
                movies.append(movie[0].text)
            tags = Soup.find_all('p',class_ = '')
            for tag in tags:
                tag = tag.text
                reg = r'\d+'
                tag = re.findall(reg,tag)
                years.append(tag[0])
    
            tags = Soup.find_all('div',class_ = 'star')
            for tag in tags:
                star = tag.find_all('span')
                stars.append(star[1].text)
                reg = r'\d+'
                vote = re.findall(reg,star[3].text)
                votes.append(vote[0])
        for i in range(0,250):
            table.add_row([Fore.RED + str(i+1),Style.BRIGHT + Fore.GREEN + movies[i],Fore.YELLOW +years[i],Fore.BLUE +stars[i],Fore.CYAN +votes[i]])
        print (table)

效果图如下：

![70][]

[70]: /images/20220510/667f708f830b4ef19ddedb495cfe0d7b.png