#!/user/bin/python
# -*- coding:utf-8 -*-
# __author__:yanglong
# __data__:2019.4.23

import requests
from lxml import etree

class phto():
    def __init__(self):
        self.url="https://www.soogif.com"
        self.header={
            "User - Agent": "Mozilla / 5.0(Windows NT 10.0;WOW64) AppleWebKit / 537.36(KHTML, likeGecko)"
                            " Chrome / 73.0.3683.103Safari / 537.36"
        }

    def send_requests(self,url):
        response=requests.get(url,headers=self.header)
        return response.content

    def save_data(self,img_data,img_name):
        data=self.send_requests(img_data)
        name="./img/"+img_name+".mp4"
        print '正在保存图片：%s'%img_name.encode("utf-8")
        with open(name,"wb") as f:
            f.write(data)

    def get_data(self,data,rel):
        elment=etree.HTML(data)
        html_xpath=elment.xpath(rel)
        return html_xpath

    def get_all_url(self):
        all_path="/html/body/div[10]/div/div[1]/div[2]/a/@href"
        response=self.send_requests(self.url+'/sort/147')
        all_url=self.get_data(response,all_path)
        for i in range(len(all_url)):
            all_url[i]=self.url+all_url[i]
        #print all_url
        return all_url

    def run(self):
        all_url=self.get_all_url()
        for each_pege in all_url:
            main_url_list=[each_pege+"?pageSize=28&pageNumber={}".format(i) for i in range(1,10)]
            for main_url in main_url_list:
                response_data=self.send_requests(main_url)
                img_url_path="//div[@class='up clearfix']/a/figure/div/video/@src"
                img_name_path="//div[@class='up clearfix']/a/figure/div/video/@alt"

                img_url_list=self.get_data(response_data,img_url_path)
                img_name_list=self.get_data(response_data,img_name_path)

                for src,name in zip(img_url_list,img_name_list):
                    self.save_data(src,name)

if __name__ == '__main__':
    test=phto()
    test.run()