用python爬取指定用户的相册

最新推荐文章于 2024-07-31 15:55:27 发布

wsj537

最新推荐文章于 2024-07-31 15:55:27 发布

阅读量464

点赞数 1

文章标签： python 开发语言数据分析

本文链接：https://blog.csdn.net/wsj537/article/details/129870550

版权

import requests
import os

headers = {
    'User Agent': '''Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.54''',
    'cookie': '_s_tentry=weibo.com; Apache=7133306648074.258.1680155788157; SINAGLOBAL=7133306648074.258.1680155788157; ULV=1680155788162:1:1:1:7133306648074.258.1680155788157:; SUB=_2A25JIVSkDeRhGeFL71cZ9CfIyTWIHXVqV8FsrDV8PUNbmtANLVb9kW9NQh2ZlCk3EXOGfjQvtJHFoD_0-3dVJYmA; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WFAUgiyyOmJjpDT1RyxmxGg5JpX5KzhUgL.FoMfSh-RSh.Xeo.2dJLoIEXLxKMLBK-L1--LxK.L1hML12eLxKBLB.2L12eLxK.L1heL12-LxKBLBonLBont; ALF=1711691892; SSOLoginState=1680155892'}


def get_sinceid(url):
    resp_json = requests.get(url, params="html.parser", headers=headers).json()
    sinceid = resp_json['data']['since_id']
    return sinceid


def get_pids(url):
    resp_json = requests.get(url, params="html.parser", headers=headers).json()
    pids = []
    for d in resp_json['data']['list']:
        pids.append(d['pid'])
    return pids


def get_img(pids):
    img_base_urL = 'https://wx1.sinaimg.cn/large/{}.jpg'
    img_urls = []
    for pid in pids:
        img_url = img_base_urL.format(pid)
        img_urls.append(img_url)
    return img_urls


def download_img(img_urls):
    fp = 'c:/爬取的图片'
    if not os.path.exists(fp):
        os.makedirs(fp)
    for img_url in img_urls:
        data = requests.get(img_url, headers=headers).content
        with open(fp + "\\" + img_url.split("/")[-1], 'wb') as f:
            f.write(data)


print('输入爬取微博的uid')
a = input()
print('输入你想获得的页数，每页最多20张，如果没这么多页自动爬取全部图片')
b = input()
b = int(b)
sinceid = 0
base_url = f'https://weibo.com/ajax/profile/getImageWall?uid={a}&sinceid=0&has_album=true'

for i in range(b):
    pids = get_pids(base_url)
    sinceid = get_sinceid(base_url)
    if sinceid == 0:
        img_urls = get_img(pids)
        download_img(img_urls)
        print(f'第{i + 1}页下载完成')
        break
    base_url = f'https://weibo.com/ajax/profile/getImageWall?uid={a}&' + 'sinceid={}&has_album=true'.format(sinceid)
    img_urls = get_img(pids)
    download_img(img_urls)
    print(f'第{i + 1}页下载完成')
print('下载完毕，图片路径c:/爬取的图片')

需要安装request包，uid的获取方法微博查询他人uid方法 - 哔哩哔哩 (bilibili.com)