Python爬虫教程-爬取5K分辨率超清唯美壁纸源码

  1 # -*- coding:utf-8 -*-
  2 
  3 from requests import get
  4 from filetype import guess
  5 from os import rename
  6 from os import makedirs
  7 from os.path import exists
  8 from json import loads
  9 from contextlib import closing
 10 
 11 
 12 # 文件下载器
 13 def Down_load(file_url, file_full_name, now_photo_count, all_photo_count):
 14     headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
 15 
 16     # 开始下载图片
 17     with closing(get(file_url, headers=headers, stream=True)) as response:
 18         chunk_size = 1024  # 单次请求最大值
 19         content_size = int(response.headers[‘content-length‘])  # 文件总大小
 20         data_count = 0 # 当前已传输的大小
 21         with open(file_full_name, "wb") as file:
 22             for data in response.iter_content(chunk_size=chunk_size):
 23                 file.write(data)
 24                 done_block = int((data_count / content_size) * 50)
 25                 data_count = data_count + len(data)
 26                 now_jd = (data_count / content_size) * 100
 27                 print("\r %s：[%s%s] %d%% %d/%d" % (file_full_name, done_block * ‘█‘, ‘ ‘ * (50 - 1 - done_block), now_jd, now_photo_count, all_photo_count), end=" ")
 28 
 29     # 下载完图片后获取图片扩展名，并为其增加扩展名
 30     file_type = guess(file_full_name)
 31     rename(file_full_name, file_full_name + ‘.‘ + file_type.extension)
 32 
 33 
 34 
 35 # 爬取不同类型图片
 36 def crawler_photo(type_id, photo_count):
 37 
 38     # 最新 1, 最热 2, 女生 3, 星空 4
 39     if(type_id == 1):
 40         url = ‘https://service.paper.meiyuan.in/api/v2/columns/flow/5c68ffb9463b7fbfe72b0db0?page=1&per_page=‘ + str(photo_count)
 41     elif(type_id == 2):
 42         url = ‘https://service.paper.meiyuan.in/api/v2/columns/flow/5c69251c9b1c011c41bb97be?page=1&per_page=‘ + str(photo_count)
 43     elif(type_id == 3):
 44         url = ‘https://service.paper.meiyuan.in/api/v2/columns/flow/5c81087e6aee28c541eefc26?page=1&per_page=‘ + str(photo_count)
 45     elif(type_id == 4):
 46         url = ‘https://service.paper.meiyuan.in/api/v2/columns/flow/5c81f64c96fad8fe211f5367?page=1&per_page=‘ + str(photo_count)
 47 
 48     # 获取图片列表数据
 49     headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
 50     respond = get(url, headers=headers)
 51     photo_data = loads(respond.content)
 52 
 53     # 已经下载的图片张数
 54     now_photo_count = 1
 55 
 56     # 所有图片张数
 57     all_photo_count = len(photo_data)
 58 
 59     # 开始下载并保存5K分辨率壁纸
 60     for photo in photo_data:
 61 
 62         # 创建一个文件夹存放我们下载的图片
 63         if not exists(‘./‘ + str(type_id)):
 64             makedirs(‘./‘ + str(type_id))
 65 
 66         # 准备下载的图片链接
 67         file_url = photo[‘urls‘][‘raw‘]
 68 
 69         # 准备下载的图片名称,不包含扩展名
 70         file_name_only = file_url.split(‘/‘)
 71         file_name_only = file_name_only[len(file_name_only) -1]
 72 
 73         # 准备保存到本地的完整路径
 74         file_full_name = ‘./‘ + str(type_id) + ‘/‘ + file_name_only
 75 
 76         # 开始下载图片
 77         Down_load(file_url, file_full_name, now_photo_count, all_photo_count)
 78         now_photo_count = now_photo_count + 1
 79 
 80 
 81 
 82 if __name__ == ‘__main__‘:
 83 
 84     # 最新 1, 最热 2, 女生 3, 星空 4
 85     # 爬取类型为3的图片(女生),一共准备爬取20000张
 86     wall_paper_id = 1
 87     wall_paper_count = 10
 88     while(True):
 89 
 90         # 换行符
 91         print(‘\n\n‘)
 92 
 93         # 选择壁纸类型
 94         wall_paper_id = input("壁纸类型：最新壁纸 1, 最热壁纸 2, 女生壁纸 3, 星空壁纸 4\n请输入编号以便选择5K超清壁纸类型：")
 95         # 判断输入是否正确
 96         while(wall_paper_id  != str(1) and wall_paper_id  != str(2) and wall_paper_id  != str(3) and wall_paper_id  != str(4)):
 97             wall_paper_id = input("壁纸类型：最新壁纸 1, 最热壁纸 2, 女生壁纸 3, 星空壁纸 4\n请输入编号以便选择5K超清壁纸类型：")
 98 
 99 
100         # 选择要下载的壁纸数量
101         wall_paper_count = input("请输入要下载的5K超清壁纸的数量：")
102         # 判断输入是否正确
103         while(int(wall_paper_count) <= 0):
104             wall_paper_count = input("请输入要下载的5K超清壁纸的数量：")
105 
106 
107         # 开始爬取5K高清壁纸
108         print("正在下载5K超清壁纸，请稍等……")
109         crawler_photo(int(wall_paper_id), int(wall_paper_count))
110         print(‘\n下载5K高清壁纸成功!‘)