python 相册_[Python]爬虫批量获取哔哩哔哩Coser的相册

最近老在弄硬件综合设计课程的实验，实现CPU，身心俱疲，所以上哔哩哔哩网站看了看发现个好东西...

哔哩哔哩网站顶部上有一个叫“画友”的功能，打开发现基本是一些 Coser 的照片，鉴于一篇篇的观赏过于麻烦，不如动手写个爬虫把妹子们放到磁盘里...

0x02 看看爬虫的效果：

0x03 直接放上源代码吧：

# -*- coding:utf-8 -*-

# @author: DYBOY

# @link: https://blog.dyboy.cn

import requests

import json

import os

import time

main_url = 'https://api.vc.bilibili.com/link_draw/v2/Photo/list?category=cos&type=hot&page_num='

req = requests.Session()

def get_html(page_num):

header= {

'Accept':'application/json, text/plain, */*',

'Accept-Encoding':'gzip, deflate, br',

'Accept-Language':'zh-CN,zh;q=0.9,en;q=0.8',

'Connection':'keep-alive',

'Cookie':' _dfcaptcha=2a3b6a18dc2f49833a6214509e784a6f; UM_distinctid=167c996fe832b-00aee39f185ce-3c604504-1fa400-167c996fe84325; CURRENT_QUALITY=16; fts=1545275440; bsource=seo_baidu'

,'Host':'api.vc.bilibili.com',

'Origin':'https://h.bilibili.com',

'Referer':'https://h.bilibili.com/eden/picture_area',

'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'

}

html = req.get(main_url+str(page_num))

html.encode = 'utf-8'

return html.text

def create_dic(dic_name):

curr_path = os.getcwd()

temPath = curr_path+os.path.sep+dic_name

if not os.path.exists(temPath):

os.makedirs(temPath)

else:

print('文件夹已存在')

return temPath

def save_pic(dic,imgsrc,name):

img = requests.get(imgsrc)

with open(dic+'/'+name,"wb") as f:

f.write(img.content)

return None

if __name__ == '__main__':

print ("开始时间："+time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))

for i in range(0,25):

album_list = json.loads(get_html(i))

print("第"+str(i)+"页")

for album in album_list['data']['items']:

username = album['user']['name']

userid = album['user']['uid']

userinfo = "用户名:"+username+" 用户id:"+str(userid)

doc_id = str(album['item']['doc_id'])

print("正在下载相册编号:"+doc_id)

try:

os.mkdir(doc_id)

except Exception as e:

print(e)

continue

with open(doc_id+"/info.txt","w",encoding='utf-8') as info:

info.write(userinfo)

pnum=0

for photo in album['item']['pictures']:

pnum+=1

save_pic(doc_id,photo['img_src'],str(pnum)+".jpg")

print(userinfo+" 》》》 下载"+str(pnum)+"张照片成功!\n")

print ("结束时间："+time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))