Python 爬取电影网站的信息
本帖最后由 艾鱼 于 2018-10-30 09:19 编辑自学Python一段时间了，写的代码比较紊乱，也不多，大佬勿喷。
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date : 2018-07-30 17:14:11
# @Author: --Eruy-- (yl8923@qq.com)
# @Link : http://www.leybc.com/
# @Version : $Id$
#请求库
import requests
#解析库 bs4css 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+'\n')
if __name__ == "__main__":
minimp4 = MiNiMp4()
for n in range(10):
minimp4.GetMovies(n)
页:
[1]