python批量爬取b站_Python爬取b站任意up主所有视频弹幕

importrequests

from lxml importetreeimportosimportjsonfrom bs4 importBeautifulSoupfrom requests importexceptionsimportreimporttimedefdownload_page(url):

headers= {

'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"}

data= requests.get(url, headers=headers)returndatadefget_video_page(space_num):

base_url= "https://www.bilibili.com/av"url= "https://space.bilibili.com/ajax/member/getSubmitVideos?mid={}&pagesize=99&tid=0&page=1&keyword=&order=pubdate".format(space_num)

data= json.loads(download_page(url).content)['data']

total= data['count']

page_num= int(total/99) + 1video_list= data['vlist']

video_url=[]for video invideo_list:

video_url.append(bas