介绍NET牛人网站

脚本服务 (netnr.com)

提供大量的脚本服务1607224173238.png

练习破解 NET牛人的图片网站

最新壁纸 在线壁纸 NET牛人 (netnr.com)

1607224445189.png
url地址：

  1. https://ss.netnr.com/wallpaper

1.分析

打开一个页面，进行下拉，发现页面使用的是懒加载，发现了他的url

1607224556553.png
1607224645705.png

页面请求的地址为：

  1. https://bird.ioliu.cn/v2?url=http%3A%2F%2Fwallpaper.apc.360.cn%2Findex.php%3Fc%3DWallPaper%26start%3D25%26count%3D12%26from%3D360chrome%26a%3DgetAppsByCategory%26cid%3D36

解码后：

  1. https://bird.ioliu.cn/v2?url=http://wallpaper.apc.360.cn/index.php?c=WallPaper&start=25&count=12&from=360chrome&a=getAppsByCategory&cid=36

参数解析

  1. url=http://wallpaper.apc.360.cn/index.php
  2. c=WallPaper
  3. start=25
  4. count=12
  5. from=360chrome
  6. a=getAppsByCategory
  7. cid=36

重要的参数：

  • start 请求的图片从第几张开始
  • count 需要返回多少组图片
  • cid id

问题：

  • cid如何获取

解决：

此页面访问地址：

  1. https://ss.netnr.com/wallpaper#36

发现36就是我们的cid

但是我们从哪里拿这个cid呢？

做过web开发的同学就会知道这样的id一定放在导航栏中的，方便页面的跳转

1607225020451.png

查看源码：

1607225034640.png

果然在这里

2.编写代码

2.1获取cid列表

  1. def getCidList():
  2.     url = 'https://ss.netnr.com/wallpaper'
  3.     html = requests.get(url=url, headers=headers).text
  4.     tree = etree.HTML(html)
  5.     name_list = tree.xpath('/html/body/div[2]/div[1]/div/div/a/text()')
  6.     cid_list = tree.xpath('/html/body/div[2]/div[1]/div/div/a/@href')
  7.     dic = dict(zip(name_list, cid_list))
  8.     # 本地存储
  9.     with open(path + '/cid.json', 'w', encoding='utf-8') as fp:
  10.         json.dump(dic, fp=fp, ensure_ascii=False)

2.2获取cid列表

拿到json数据

  1.     params = {
  2.         'url': 'http://wallpaper.apc.360.cn/index.php',
  3.         'c': 'WallPaper',
  4.         'start': start,
  5.         'count': count,
  6.         'from': '360chrome',
  7.         'a': 'getAppsByCategory',
  8.         'cid': cid
  9.     }
  11.     url = 'https://bird.ioliu.cn/v2'
  12.     data = requests.get(url=url, params=params, headers=headers).json()
  13.     data_list = data['data']

json

  1. {
  2. "id": "2037036",
  3. "class_id": "6",
  4. "resolution": "1920x1200",
  5. "url_mobile": "",
  6. "url": "http://p4.qhimg.com/bdr/__85/t019f2bf1d6ea85a7d6.jpg",
  7. "url_thumb": "http://p4.qhimg.com/bdr/__85/t019f2bf1d6ea85a7d6.jpg",
  8. "url_mid": "http://p4.qhimg.com/bdr/__85/t019f2bf1d6ea85a7d6.jpg",
  9. "download_times": "0",
  10. "imgcut": "0",
  11. "tag": "_全部_ _category_清纯_ _category_美肩_ _category_马尾_ _category_吊带_ _category_阳光_ _category_美女模特_",
  12. "create_time": "2020-12-02 20:14:58",
  13. "update_time": "2020-12-02 20:16:05",
  14. "ad_id": "",
  15. "ad_img": "",
  16. "ad_pos": "",
  17. "ad_url": "",
  18. "ext_1": "",
  19. "ext_2": "",
  20. "utag": "清纯 美肩 马尾 吊带 阳光",
  21. "tempdata": "",
  22. "rdata": [],
  23. "img_1600_900": "http://p4.qhimg.com/bdm/1600_900_85/t019f2bf1d6ea85a7d6.jpg",
  24. "img_1440_900": "http://p4.qhimg.com/bdm/1440_900_85/t019f2bf1d6ea85a7d6.jpg",
  25. "img_1366_768": "http://p4.qhimg.com/bdm/1366_768_85/t019f2bf1d6ea85a7d6.jpg",
  26. "img_1280_800": "http://p4.qhimg.com/bdm/1280_800_85/t019f2bf1d6ea85a7d6.jpg",
  27. "img_1280_1024": "http://p4.qhimg.com/bdm/1280_1024_85/t019f2bf1d6ea85a7d6.jpg",
  28. "img_1024_768": "http://p4.qhimg.com/bdm/1024_768_85/t019f2bf1d6ea85a7d6.jpg"
  29. }

完整代码

  1. import json
  2. import time
  3. import requests
  4. import os
  5. from lxml import etree
  6. from tqdm import tqdm
  8. headers = {
  9.     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36 Edg/87.0.664.52'
  10. }
  11. # 保存位置
  12. path = './NET牛人图片'
  13. # 分辨率（默认最高）
  14. resolution = 'img_1600_900'
  17. def main():
  18.     # 每次循环增加20
  19.     # 1-20  i-(i+20)-1
  20.     # 2
  21.     j = 1
  22.     for i in range(1, 4):
  23.         print('爬取第%d张到第%d张的图片' % (j, (j + 20) - 1))
  24.         download(6, '美女', j, (j + 20) - 1, resolution)
  25.         j += 20
  26.         print('线程睡眠1S')
  27.         time.sleep(1)
  30. # cid_dic = readCidList()
  33. def download(cid, kind, start, count, resolution):
  34.     if not os.path.exists(path + '/' + kind):
  35.         os.mkdir(path + '/' + kind)
  37.     params = {
  38.         'url': 'http://wallpaper.apc.360.cn/index.php',
  39.         'c': 'WallPaper',
  40.         'start': start,
  41.         'count': count,
  42.         'from': '360chrome',
  43.         'a': 'getAppsByCategory',
  44.         'cid': cid
  45.     }
  47.     url = 'https://bird.ioliu.cn/v2'
  48.     data = requests.get(url=url, params=params, headers=headers).json()
  49.     data_list = data['data']
  50.     for item in tqdm(data_list):
  51.         img_url = item[resolution]
  52.         # img_name = str(item["utag"]).replace(' ','')
  53.         # img_suffix = str(img_url).split('.')[-1]
  54.         # file_name = img_name + '.' + img_suffix
  55.         file_name = str(img_url).split('/')[-1]
  56.         img_data = requests.get(img_url).content
  57.         with open(path + '/' + kind + '/' + file_name, 'wb') as fp:
  58.             fp.write(img_data)
  61. def readCidList():
  62.     with open(path + '/cid.json', 'r', encoding='utf-8') as fp:
  63.         data = json.load(fp)
  64.         print(type(data))
  65.     return data
  68. def getCidList():
  69.     url = 'https://ss.netnr.com/wallpaper'
  70.     html = requests.get(url=url, headers=headers).text
  71.     tree = etree.HTML(html)
  72.     name_list = tree.xpath('/html/body/div[2]/div[1]/div/div/a/text()')
  73.     cid_list = tree.xpath('/html/body/div[2]/div[1]/div/div/a/@href')
  74.     dic = dict(zip(name_list, cid_list))
  75.     # 本地存储
  76.     with open(path + '/cid.json', 'w', encoding='utf-8') as fp:
  77.         json.dump(dic, fp=fp, ensure_ascii=False)
  80. # 创建文件夹
  81. def my_mkdir():
  82.     if not os.path.exists(path):
  83.         os.mkdir(path)
  86. if __name__ == '__main__':
  87.     main()