Python 自动爬取B站视频

文件名自定义（文件格式为.py），脚本内容:

#!/usr/bin/env python
#-*-coding:utf-8-*-
import requests
import random
import time

def get_json(url):
	headers = {
		'User-Agent':
		'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
	}

	params = {
		'page_size': 10,
		'next_offset': str(num),
		'tag': '今日热门',
		'platform': 'pc'
	}
	try:
		html = requests.get(url,params=params,headers=headers)
		return html.json()

	except BaseException:
		print('request error')
		pass

def download(url,path):
	start = time.time() # 开始时间
	size = 0
	headers = {
		'User-Agent':
		'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
	}

	response = requests.get(url,headers=headers,stream=True) # stream属性必须带上
	chunk_size = 1024 # 每次下载的数据大小
	content_size = int(response.headers['content-length']) # 总大小
	if response.status_code == 200:
		print('[文件大小]:%0.2f MB' %(content_size / chunk_size / 1024)) # 换算单位
		with open(path,'wb') as file:
			for data in response.iter_content(chunk_size=chunk_size):
				file.write(data)
				size += len(data) # 已下载的文件大小

if __name__ == '__main__':
	for i in range(10):
		url = 'http://api.vc.bilibili.com/board/v1/ranking/top?'
		num = i*10 + 1
		html = get_json(url)
		infos = html['data']['items']
		for info in infos:
			title = info['item']['description'] # 小视频的标题
			video_url = info['item']['video_playurl'] # 小视频的下载链接
			print(title)

			# 为了防止有些视频没有提供下载链接的情况
			try:
				download(video_url,path='videos/%s.mp4' %title)
				print('成功下载一个!')
			except BaseException:
				print('凉凉,下载失败')
				pass
		time.sleep(int(format(random.randint(2,8)))) # 设置随机等待时间

爬取效果如下：

爬取的文件：

生成一个windows平台可执行exe程序

工具安装：pip install PyInstaller

生成exe程序：

pyinstaller -i test.ico -F Grasp.py

打包过程:

打包好的文件:

参数含义：

程序:

百度云下载链接

链接：百度云

提取码：hqhr

脚本内容收集自互联网，不保证生成的程序时效