Python爬取bilibili的cos福利

最新推荐文章于 2024-09-27 22:51:18 发布

萌新开车了

最新推荐文章于 2024-09-27 22:51:18 发布

阅读量5.3k

点赞数

文章标签： Pyhton 爬虫 bilibili

本文链接：https://blog.csdn.net/qq_43539477/article/details/85224164

版权

从别的地方找到个好玩的网址，链接https://api.vc.bilibili.com/link_draw/v2/Photo/list？category=cos&type=hot&page_num=1。页面比较简单，但是内容十分的非常的特别丰富。于是心生歹念进行了爬取。做的比较简陋。见笑了。为了方便没有py环境的大佬们运行，末尾进行了打包。（有啥写的不好的地方请指出）

import re
import requests
import os
import json


class BiliBili(object,):
    def __init__(self,page_num,dir_name,file_name):
        self.base_url = "https://api.vc.bilibili.com/link_draw/v2/Photo/list?category=cos&type=hot&page_num={}".format(page_num)
        self.headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"}
        self.count = file_name
        self.dir_name = dir_name
	
	#发送请求
    def send_request(self, url):
        resopnse = requests.get(url, headers=self.headers)
        data = resopnse.content.decode()
        json_data = json.loads(data)['data']['items']
        str_data = json.dumps(json_data)
        return str_data
	
	#发送图片链接请求
    def secend_request(self, url):
        resopnse = requests.get(url, headers=self.headers)
        data = resopnse.content
        return data
	
	#对基本url进行解析
    def analysis_url(self, data):
        pattern = re.compile('c": "(.*?)", "i')
        url = re.findall(pattern, data)
        return url
	
	#保存图片信息
    def save_file(self,dir_name,names,data,):
        with open( "{}/".format(dir_name)+ str(names) + '.jpg', 'wb') as f:
            f.write(data)
	#启动
    def run(self):
        try:
            os.mkdir(self.dir_name)
        except:
            pass
       
        data = self.send_request(self.base_url)
        url_list = self.analysis_url(data)
        
        for url in url_list:
            data = self.secend_request(url)
            self. save_file(self.dir_name,self.count,data,)
            print("正在下载第{}个图片".format(self.count))
            self.count += 1
        return "下载完毕"


if __name__ == '__main__':
    while True:
        page_num = int(input("请输入下载的页数"))
        dir_name = input("请输入想要存放的文件夹的名字")
        file_name = int(input("请输入文件的起始名字。仅限纯数字"))
        if type(file_name) == int:
            test = BiliBili(page_num,dir_name,file_name)
            test.run()

https://pan.baidu.com/s/1N_aKCbToxqEC5q-Y7CsgJg