爬取迷你mp4各个电影信息

网站：www.minimp4.com

# coding=utf-8

import requests

from lxml import etree

class Minimpe_moves(object):

    def Getmovies(self,page):

        url = 'http://www.minimp4.com/movie/?page={}'.format(page)

        html = requests.get(url)

        htmml = etree.HTML(html.text)#解析网页

        href = htmml.xpath('//div[@class="meta"]/h1/a/@href')

        for url_moves in href:

            html1 = requests.get(url_moves)

            htmml1 = etree.HTML(html1.text)

            movie_name = htmml1.xpath('//div[@class="movie-meta"]/h1/text()')#提取电影名字

            #movie_actor =htmml1.xpath('//div[@class="movie-meta"]/p[@id="casts"]/a/text()')#爬取主演名字

            print (movie_name)

            Minimpe_moves.saveMovies(movie_name)

#语法糖　装饰器　静态方法

    @staticmethod

    def saveMovies(data):

        with open('movies.txt','a',encoding = 'utf-8') as f:

            f.write(data[0]+'\n')

#内置属性，别的文件引入这个文件时，无法执行下面代码

if __name__ == "__main__":

    minimp4 = Minimpe_moves ()

    for n in range(11):#爬取1到10页

        minimp4.Getmovies(n)

上图是各个电影主演，基本上每部电影的各个信息都能爬取下来，只需修改对应的xpath即可．