python电影系统管理-Python 爬取电影网站的信息【如有重复请管理删帖】

[Python] 纯文本查看 复制代码#!/usr/bin/env python

# -*- coding: utf-8 -*-

# [url=home.php?mod=space&uid=686237]@date[/url] : 2018-07-30 17:14:11

# [url=home.php?mod=space&uid=686208]@AuThor[/url] : --Eruy-- ([url=mailto:yl8923@qq.com]yl8923@qq.com[/url])

# @Version : $Id$

#请求库

import requests

#解析库 bs4 css pyquery json xpath re

from lxml import etree

# 类

class MiNiMp4(object):

"""docstring for GetMovies"""

def GetMovies(self, page):

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

html = requests.get(url)

htmll = etree.HTML(html.text) #初始化xml

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

# print(hrefs)

for url in hrefs:

html = requests.get(url)

dat = etree.HTML(html.text)

movieName = dat.xpath("//div[@class="movie-meta"]/h1/text()")

print(movieName)

self.saveMovies(movieName)

# return url

#

@staticmethod

def saveMovies(data):

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

fp.write(data[0]+" ")

if __name__ == "__main__":

minimp4 = MiNiMp4()

for n in range(10):

minimp4.GetMovies(n)