Ajax爬取今日头条街拍

最新推荐文章于 2024-04-07 14:00:00 发布

臣序源

最新推荐文章于 2024-04-07 14:00:00 发布

阅读量322

点赞数

分类专栏：学习记录 python 文章标签：爬虫初学

本文链接：https://blog.csdn.net/weixin_42112678/article/details/82936490

版权

学习记录同时被 2 个专栏收录

5 篇文章 2 订阅

订阅专栏

python

3 篇文章 0 订阅

订阅专栏

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

def get_page(offset):
    params = {
        'offset': offset,
        'format': 'json',
        'keyword': '街拍',
        'autoload': 'true',
        'count': '20',
        'cur_tab': '1',
        'from': 'search_tab'
    }
    url = 'https://www.toutiao.com/search_content/?' + urlencode(params)

    try:
        response = requests.get(url)
        if codes.ok == response.status_code:
            return response.json()
    except requests.ConnectionError:
        return None
    
def get_images(json):
    if json.get('data'):
        for item in json.get('data'):
            if item.get('cell_type') is not None:
                continue
            title = item.get('title')
            images = item.get('image_list')
            for image in images:
                yield {
                    'image': image.get('url'),
                    'title': title
                }

def save_image(item):
    file_path = 'image' + os.path.sep + item.get('title')
    if not os.path.exists(file_path):
        os.makedirs(file_path)
    try:
        save_nrl = 'http:' + item.get('image')
        rep = requests.get(save_nrl)
        if codes.ok == rep.status_code:
            image_path = file_path + os.path.sep + '{}.{}'.format(md5(rep.content).hexdigest(),'jpg')
            if not os.path.exists(image_path):
                with open(image_path, 'wb')as f:
                    f.write(rep.content)
                print('当前下载路径:%s' % image_path)
            else:
                print('未找到目标路径')
    except requests.ConnectionError:
        print('下载失败')

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

GROUP_START = 1
GROUP_END = 10

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