#!/usr/bin/env python

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

# @Time    : 2017/12/1 15:55

# @Author  : gj

# @Site    :

# @File    : test_class.py

# @Software: PyCharm

import urllib2,re,threading

'''

伪造头信息

'''

def Get_header():

    headers = {

        'USER_AGENT': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.54 Safari/536.5'

    }

    return headers

'''

获取页面内容

'''

def Spider(url,header):

    req = urllib2.Request(url=url,headers=header)

    html = urllib2.urlopen(req)

    info = html.read()

    return info

def Analyse(infos):

    pattern = re.compile('<ol class="grid_view">(.*?)</ol>',re.S)

    info = pattern.findall(infos)

    pattern = re.compile("<li>(.*?)</li>",re.S)

    movie_infos = pattern.findall(info[0])

    movie=[]

    for movie_info in movie_infos:

        movie_temp=[]

        url = ""

        title=""

        director=""

        score=""

        peoples=""

        inq=""

        #获取链接地址

        pattern_url = re.compile('<a href="(.*?)" class="">')

        movie_urls = pattern.findall(movie_info)

        for movie_url in movie_urls:

            url = url+movie_url

        movie_temp.append(url)

        # 获取视频名称

        pattern_title = re.compile('<span class="title">(.*?)</span>')

        movie_titles = pattern_title.findall(movie_info)

        for movie_title in movie_titles:

            title = title+movie_title

        movie_temp.append(title)

        # 获取视频演员表

        pattern_director = re.compile('<p class="">(.*?)<br>',re.S)

        movie_directors = pattern_director.findall(movie_info)

        for movie_director in movie_directors:

            director = director+movie_director

        movie_temp.append(director)

        #获取视频评分

        pattern_score = re.compile('<div class="star">.*?<span class="rating_num" property="v:average">(.*?)</span>.*?<span>(.*?)</span>.*?</div>',re.S)

        movie_scores = pattern_score.findall(movie_info)

        for movie_score in movie_scores:

            score = movie_score[0]

            peoples = movie_score[1]

            break

        movie_temp.append(score)

        movie_temp.append(peoples)

        # 获取视频简介

        pattern_inq = re.compile('<p class="quote">.*?<span class="inq">(.*?)</span>.*?</p>',re.S)

        movie_inqs = pattern_inq.findall(movie_info)

        if len(movie_inqs)>0:

            inq = movie_inqs[0]

        else:

            inq ='该视频无简介'

        movie_temp.append(inq)

        movie.append(movie_temp)

    return movie

'''

将返回内容写入文件

'''

def write_file(infos):

    #防止多个线程写文件造成数据错乱

    mutex.acquire()

    with open("./movie.txt","ab") as f:

        for info in infos:

            write_info = ""

            for i in range(0,len(info)):

                info[i] = info[i].replace("\n","")

                write_info = write_info+info[i]+"   "

            write_info= write_info+"\n"

            f.write(write_info)

    mutex.release()

def start(i):

    url = "https://movie.douban.com/top250?start=%d&filter="%(i*25)

    headers = Get_header()

    infos= Spider(url,headers)

    movie_infos = Analyse(infos)

    write_file(movie_infos)

def main():

    #创建多线程

    Thread = []

    for i in range(0,10):

        t=threading.Thread(target=start,args=(i,))

        Thread.append(t)

    for i in range(0,10):

        Thread[i].start()

    for i in range(0,10):

        Thread[i].join()

if __name__ == "__main__":

    #加锁

    mutex = threading.Lock()

    main()