python爬取百度图库

python爬取百度图库

import requests
import os
import urllib
import random

class Spider_baidu_image():
    def __init__(self):
        self.url = 'http://image.baidu.com/search/acjson?'
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.\
            3497.81 Safari/537.36'}
        self.headers_image = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.\
            3497.81 Safari/537.36',
            'Referer': 'http://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1557124645631_R&pv=&ic=&nc=1&z=&hd=1&latest=0&copyright=0&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&sid=&word=%E8%83%A1%E6%AD%8C'}
        self.keyword = input("请输入搜索图片关键字:")
        self.paginator = int(input("请输入搜索页数，每页30张图片："))

    def get_param(self):
        keyword = urllib.parse.quote(self.keyword)
        params = []
        for i in range(1, self.paginator + 1):
            params.append(
                'tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord={}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=&hd=1&latest=0&copyright=0&word={}&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&cg=star&pn={}&rn=30&gsm=78&1557125391211='.format(
                    keyword, keyword, 30 * i))
        return params

    def get_urls(self, params):
        urls = []
        for i in params:
            urls.append(self.url + i)
        return urls

    def get_image_url(self, urls):
        image_url = []
        for url in urls:
            json_data = requests.get(url, headers=self.headers).json()
            json_data = json_data.get('data')
            for i in json_data:
                if i:
                    image_url.append(i.get('thumbURL'))
        return image_url

    def get_image(self, image_url):
        path = r'输入保存地址'
        for index, url in enumerate(image_url, start=1):
            with open(path +'/'+self.keyword+str(random.random()) +'.{}.jpg'.format(index-1), 'wb') as f:
                f.write(requests.get(url, headers=self.headers_image).content)
            if index != 0 and index % 30 == 0:
                print('{}第{}页下载完成'.format(self.keyword, index / 30))

    def __call__(self, *args, **kwargs):
        params = self.get_param()
        urls = self.get_urls(params)
        image_url = self.get_image_url(urls)
        self.get_image(image_url)


if __name__ == '__main__':
    spider = Spider_baidu_image()
    spider()


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