├── .gitattributes
├── douban_pic_download.py
└── douban_love_download.py


/.gitattributes:
--------------------------------------------------------------------------------
1 | # Auto detect text files and perform LF normalization
2 | * text=auto
3 | 


--------------------------------------------------------------------------------
/douban_pic_download.py:
--------------------------------------------------------------------------------
 1 | # coding:utf-8
 2 | # 下载豆瓣 王祖贤的海报
 3 | import requests
 4 | import json
 5 | 
 6 | query = '王祖贤'
 7 | ''' 下载图片 '''
 8 | def download(src, id):
 9 | 	dir = './' + str(id) + '.jpg'
10 | 	try:
11 | 		pic = requests.get(src, timeout=10)
12 | 	except requests.exceptions.ConnectionError:
13 | 		print('图片无法下载')
14 | 
15 | 	fp = open(dir, 'wb')
16 | 	fp.write(pic.content)
17 | 	fp.close()
18 | 
19 | ''' for循环 请求全部的url '''
20 | for i in range(0, 22471, 20):
21 | 	url = 'https://www.douban.com/j/search_photo?q='+query+'&limit=20&start='+str(i)
22 | 	html = requests.get(url).text    #得到返回结果
23 | 	response = json.loads(html,encoding='utf-8') #将JSON格式转换成Python对象
24 | 	for image in response['images']:
25 | 		print(image['src']) #查看当前下载的图片网址
26 | 		download(image['src'], image['id']) #下载一张图片
27 | 		
28 | 


--------------------------------------------------------------------------------
/douban_love_download.py:
--------------------------------------------------------------------------------
 1 | # coding:utf-8
 2 | # 下载豆瓣爱情的电影封面
 3 | import requests
 4 | import json
 5 | 
 6 | # 下载图片
 7 | def download(url, title):
 8 |     dir = './' + title + '.jpg'
 9 |     try:
10 |         pic = requests.get(url)
11 |         fp = open(dir, 'wb')
12 |         fp.write(pic.content)
13 |         fp.close()
14 |         print(title)
15 |     except requests.exceptions.ConnectionError:
16 |         print('图片无法下载')
17 | 
18 | 
19 | for num in range(0, 1000, 20):
20 |     # 构造url，翻页变换参数为start=, tag=电影, gender=爱情, 改变start=后面的数字，可以爬取不同的页
21 |     url = 'https://movie.douban.com/j/new_search_subjects?sort=U&range=0,10&tags=%E7%94%B5%E5%BD%B1&start='\
22 |           + str(num)+'&genres=%E7%88%B1%E6%83%85'
23 |     print(url)
24 |     html = requests.get(url).text
25 |     # 转为json格式
26 |     res = json.loads(html, encoding='utf-8')
27 |     for result in res['data']:
28 |         cover = result['cover']
29 |         title = result['title']
30 |         download(cover, title)


--------------------------------------------------------------------------------