数据挖掘--爬虫--Ajax数据爬取

发表于 | 更新于: | 分类于

Ajax

  Ajax，全程Asynchronous JavaScript and XML，即异步的JavaScript和XML，在保证页面不被刷新、页面链接不改变的情况下与服务器交换数据并更新部分网页的技术。

爬取今日头条街拍

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
80
81
82
83
84
85
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
""" 
@author zhangbohan.dell@gmail.com
@function:
@create 2019/2/25 11:12
"""
import os
from hashlib import md5
from multiprocessing.pool import Pool

import requests
from bs4 import BeautifulSoup
from urllib.parse import urlencode


def get_page(offset):
    params = {
        'aid': '24',
        'app_name': 'web_search',
        'offset': offset,
        'format': 'json',
        'keyword': '街拍',
        'autoload': 'true',
        'count': '20',
        'en_qc': '1',
        'cur_tab': '1',
        'from': 'search_tab',
        'pd': 'syntheis'
    }
    url = 'https://www.toutiao.com/api/search/content/?' + urlencode(params)
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.json()
    except requests.ConnectionError:
        return None


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


def save_image(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:
            file_path = '{0}/{1}.{2}'.format(item.get('title'), 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 Downloaded', file_path)
    except requests.ConnectionError:
        print('Failed to save Image')


def main(offset):
    json = get_page(offset)
    for item in get_image(json):
        print(item)
        save_image(item)


GROUP_START = 1
GROUP_END = 20

if __name__ == '__main__':
    pool = Pool()
    groups = ([x * 20 for x in range(GROUP_START, GROUP_END + 1)])
    pool.map(main, groups)
    pool.map(main, groups)
    pool.close()
    pool.join()

参考资料

崔庆才大佬的《python3网络爬虫开发实战》