ZOL桌面壁纸的提取

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# author：albert time:2019/7/8
import  requests
from lxml import etree
from random import  randint


a = []

# 每个组图的url
def This_Mosaic_Url():
    req = requests.get('http://desk.zol.com.cn/1920x1200/').text
    html = etree.HTML(req)
    url = html.xpath("//div//li[@class='photo-list-padding']//a/@href")
    for i in url:
        url_list = 'http://desk.zol.com.cn' + i
        a.append(url_list)

def list_randan():
    it= iter(a)
    # print(next(it))
    return  next(it)

# 每个组图下的所有图片
def img_picture():
    # 第一个url===>"http://desk.zol.com.cn/bizhi/7590_94212_2.html"
    list = [a[0]]

    while True:
        url_1 = 'http://desk.zol.com.cn'
        req = requests.get(list[-1],timeout=3).text
        html = etree.HTML(req)

        url_detail = ''.join(html.xpath("//div[@class='photo-next prev-next']//a/@href"))
        if url_detail == 'javascript:;':
            try:
                for i in range(15):
                    href = list_randan()
                    list.append(href)
            except:
                pass
        else:
            url = url_1 + url_detail
            list.append(url)

    print(len(list))
    for x in list:
        print(x)

if __name__ == '__main__':
    This_Mosaic_Url()
    img_picture()