python爬虫学习之爬取超清唯美壁纸

  1 '''
  2 在学习过程中有什么不懂得可以加我的
  3 python学习交流扣扣qun，934109170
  4 群里有不错的学习教程、开发工具与电子书籍。
  5 与你分享python企业当下人才需求及怎么从零基础学习好python，和学习什么内容。
  6 '''
  7 # -*- coding:utf-8 -*-
  8  
  9 from requests import get
 10 from filetype import guess
 11 from os import rename
 12 from os import makedirs
 13 from os.path import exists
 14 from json import loads
 15 from contextlib import closing
 16  
 17  
 18 # 文件下载器
 19 def Down_load(file_url, file_full_name, now_photo_count, all_photo_count):
 20     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"}
 21  
 22     # 开始下载图片
 23     with closing(get(file_url, headers=headers, stream=True)) as response:
 24         chunk_size = 1024  # 单次请求最大值
 25         content_size = int(response.headers['content-length'])  # 文件总大小
 26         data_count = 0 # 当前已传输的大小
 27         with open(file_full_name, "wb") as file:
 28             for data in response.iter_content(chunk_size=chunk_size):
 29                 file.write(data)
 30                 done_block = int((data_count / content_size) * 50)
 31                 data_count = data_count + len(data)
 32                 now_jd = (data_count / content_size) * 100
 33                 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=" ")
 34  
 35     # 下载完图片后获取图片扩展名，并为其增加扩展名
 36     file_type = guess(file_full_name)
 37     rename(file_full_name, file_full_name + '.' + file_type.extension)
 38  
 39  
 40  
 41 # 爬取不同类型图片
 42 def crawler_photo(type_id, photo_count):
 43  
 44     # 最新 1, 最热 2, 女生 3, 星空 4
 45     if(type_id == 1):
 46         url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c68ffb9463b7fbfe72b0db0?page=1&per_page=' + str(photo_count)
 47     elif(type_id == 2):
 48         url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c69251c9b1c011c41bb97be?page=1&per_page=' + str(photo_count)
 49     elif(type_id == 3):
 50         url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c81087e6aee28c541eefc26?page=1&per_page=' + str(photo_count)
 51     elif(type_id == 4):
 52         url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c81f64c96fad8fe211f5367?page=1&per_page=' + str(photo_count)
 53  
 54     # 获取图片列表数据
 55     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"}
 56     respond = get(url, headers=headers)
 57     photo_data = loads(respond.content)
 58  
 59     # 已经下载的图片张数
 60     now_photo_count = 1
 61  
 62     # 所有图片张数
 63     all_photo_count = len(photo_data)
 64  
 65     # 开始下载并保存5K分辨率壁纸
 66     for photo in photo_data:
 67  
 68         # 创建一个文件夹存放我们下载的图片
 69         if not exists('./' + str(type_id)):
 70             makedirs('./' + str(type_id))
 71  
 72         # 准备下载的图片链接
 73         file_url = photo['urls']['raw']
 74  
 75         # 准备下载的图片名称,不包含扩展名
 76         file_name_only = file_url.split('/')
 77         file_name_only = file_name_only[len(file_name_only) -1]
 78  
 79         # 准备保存到本地的完整路径
 80         file_full_name = './' + str(type_id) + '/' + file_name_only
 81  
 82         # 开始下载图片
 83         Down_load(file_url, file_full_name, now_photo_count, all_photo_count)
 84         now_photo_count = now_photo_count + 1
 85  
 86  
 87  
 88 if __name__ == '__main__':
 89  
 90     # 最新 1, 最热 2, 女生 3, 星空 4
 91     # 爬取类型为3的图片(女生),一共准备爬取20000张
 92     wall_paper_id = 1
 93     wall_paper_count = 10
 94     while(True):
 95  
 96         # 换行符
 97         print('\n\n')
 98  
 99         # 选择壁纸类型
100         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：")
101         # 判断输入是否正确
102         while(wall_paper_id  != str(1) and wall_paper_id  != str(2) and wall_paper_id  != str(3) and wall_paper_id  != str(4)):
103             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：")
104  
105  
106         # 选择要下载的壁纸数量
107         wall_paper_count = input("请输入要下载的5K超清壁纸的数量：")
108         # 判断输入是否正确
109         while(int(wall_paper_count) <= 0):
110             wall_paper_count = input("请输入要下载的5K超清壁纸的数量：")
111  
112  
113         # 开始爬取5K高清壁纸
114         print("正在下载5K超清壁纸，请稍等……")
115         crawler_photo(int(wall_paper_id), int(wall_paper_count))
116         print('\n下载5K高清壁纸成功!')