Python-爬取今日头条美图_import requests from urllib.parse import urlencode

import requests
from urllib.parse import urlencode
import os
from hashlib import md5
from multiprocessing.pool import Pool

def get_page(offset):
    params = {
        'aid': '24',
        'app_name': 'web_search',
        'offset': offset,
        'format': 'json',
        'keyword': '街拍',
        'autoload': 'true',
        'count': '20',
        'cur_tab': '3'
    }

    url = 'https://www.toutiao.com/api/search/content/?' + urlencode(params)
    header={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'}
    try:
        response = requests.get(url,headers=header)
        if response.status_code == 200:
            #print('连接成功')
            return response.json()
    except requests.ConnectionError:
        print("连接失败")
        return None

def get_images(json):
    #print(json)
    if json.get('data'):
        
        for item in json.get('data'):
            title = item.get('title')
            images = item.get('image_list')
            if images:
                for image in images:
                    yield{
                        'image': image.get('url'),
                        'title': title
                    }


def save_images(item):
    if not os.path.exists(item.get('title')):
        os.mkdir(item.get('title'))
    try:
        response = requests.get(item.get('image'))
        if response.status_code == 200:
            # 这里使用 将图片的unicode 
            file_path = '{0}/{1}.{2}'.format(item.get('title').replace(' ',''), md5(response.content).hexdigest(), 'jpg')
            if not os.path.exists(file_path):
                with open(file_path,'wb') as f:
                    f.write(response.content)
            else:
                print('Already Download', file_path)
    except requests.ConnectionError:
        print('Failed to Save Image')


def main(offset):
    json = get_page(offset)
    for item in get_images(json):
        #print(item)
        save_images(item)

GROUP_START = 1
GROUP_END = 1

if __name__ == '__main__':
    os.chdir('jiepai')     # 打开文件夹，在该文件夹下产生文件
    pool = Pool()    #  Pool 多进程下载
    groups = ([x*20 for x in range(GROUP_START, GROUP_END + 1)])
    pool.map(main, groups)
    pool.close()
    pool.join()


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79