分析Ajax爬取今日头条街拍图片

最新推荐文章于 2022-11-21 19:03:57 发布

OnlyotDN

最新推荐文章于 2022-11-21 19:03:57 发布

阅读量249

点赞数 1

分类专栏： python3爬虫文章标签： Ajax python爬虫爬取头条图片

本文链接：https://blog.csdn.net/onlyot/article/details/99305438

版权

python3爬虫专栏收录该内容

1 篇文章 0 订阅

订阅专栏

# -*- coding:UTF-8 -*-
import requests
import time
import os
from hashlib import md5

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': 'synthesis',
        'timestamp': int(time.time() * 1000)
    }
    url = 'http://www.toutiao.com/search_content/?'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) Ap'
                      'pleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36',
        'referer': 'https://www.toutiao.com/search/?keyword=%E8%A1%97%E6%8B%8D',
        'x-requested-with': 'XMLHttpRequest'
    }
    try:
        response = requests.get(url=url, params=params, headers=headers)
        if response.status_code == 200:
            return response.json()
    except requests.ConnectionError:
        return None


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


def save_image(offset, item):
    if not os.path.exists('picture'+str(offset)):
        os.mkdir('picture'+str(offset))
    try:
        response = requests.get("http:" + item.get('image'))
        if response.status_code == 200:
            file_path = '{0}/{1}.{2}'.format('picture'+str(offset), 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')


if __name__ == '__main__':
    for offset in range(0, 120, 20):
        json = get_page(offset)
        for item in get_images(json):
            save_image(offset, item)