python简单爬虫实例4之猫眼网top100抓取特定内容（100个电影）

在实例三的基础上进行加强，当一个网页抓取好后，抓取全部网页也就非常容易了。

from bs4 import BeautifulSoup
from urllib.request import urlopen

def get_one_page(x):
    #字符串的格式化处理： {}占位符表示未知的参数，后面会补上
    url = 'https://maoyan.com/board/4?offset={}'.format(x*10)
    #第二种方法：url = 'https://maoyan.com/board/4?offset=%d'%(x*10)
    response = urlopen(url)
    return (response.read().decode())

def get_film(html):
    ls = []
    #html = get_one_page(x)
    soup = BeautifulSoup(html,'html.parser')
    class_name = soup.select('.name')
    class_star = soup.select('.star')
    class_releasetime = soup.select('.releasetime')
    class_integer = soup.select('.integer')
    class_fraction = soup.select('.fraction')
    #print(class_name,class_star,class_releasetime,class_integer,class_fraction)
    for a,b,c,d,e in zip(class_name,class_star,class_releasetime,class_integer,class_fraction):
        '''print(a.get_text())
        print(b.get_text().strip())
        print(c.get_text())
        print(d.get_text(),end='')
        print(e.get_text().strip())
        print()'''
        movie={}
        movie['name']=a.get_text()
        movie['star'] = b.get_text().strip()
        movie['releasetime'] = c.get_text()
        #movie['releasetime'] = d.get_text()
        #movie['fraction'] = e.get_text()
        #评分合成
        f=d.get_text()+e.get_text()
        movie['score']=f
        ls.append(movie)

    return ls


if __name__ == '__main__':

    movie_list = []

    for index in range(0, 10):
        html = get_one_page(index)
        movie_list += get_film(html)

    # 所有抓取内容
    print((movie_list))

将每次提取的内容放到movie字典中，存到movie_list列表中，最终的movie_list列表就包含了所有的电影信息。