千图网图片下载

最新推荐文章于 2024-06-14 09:50:01 发布

funcdefmain

最新推荐文章于 2024-06-14 09:50:01 发布

阅读量132

点赞数 1

分类专栏：爬虫文章标签： python

本文链接：https://blog.csdn.net/qq_45444679/article/details/132587372

版权

爬虫专栏收录该内容

12 篇文章 1 订阅

订阅专栏

千图网图片下载

只能下载部分图片

import os.path

import requests
from spider import Spider


def parse_real_url(src_url):
    base_url = 'http://apifont.58pic.com/index.php?c=Download&a=downPng&im=//58pic'
    download_url = base_url + src_url.split('58pic')[-1].split('!')[0]
    return download_url


def run(keyword_pinyin, category):
    url = 'https://www.58pic.com/tupian/{}-852-0-default-0-0-0-0_2_0_0_0_0_0-0-0-0-0-0-0-0-0-0-0-0-{}.html?is_ajax=1&is_new=1'
    for page in range(1, 130):
        print(f'下载第{page}页数据')
        page_url = url.format(keyword_pinyin, page)
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 5.1; rv:5.0) Gecko/20100101 Firefox/6.1856'
        }
        print(page_url)
        resp = requests.get(url=page_url, headers=headers)
        print(resp.text)
        pic_list = resp.json()['data']['pics']
        task_list = []
        for pic in pic_list:
            pid = pic['id']
            title = pic['title']
            pic_url = pic['picurl']
            if 'freepik' in pic_url:
                continue
            save_name = title[:10] + '_' + str(pid) + '.jpg'
            save_dir = fr'./{category}'
            save_path = os.path.join(save_dir, save_name)
            download_url = parse_real_url(pic['picurl'])
            print('下载地址:', download_url)
            task_list.append((download_url, save_path))
        Spider(task_list=task_list, thread_num=3).run()


if __name__ == '__main__':
    keyword_pinyin = 'shanmai'
    run(
        keyword_pinyin=keyword_pinyin,
        category="山脉"
    )