You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

45 lines
1.4 KiB

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

# bullet screen为弹幕
"""
说明爬取b站弹幕的模块
"""
import re
import requests
from bs4 import BeautifulSoup
from bv_maker import get_bv, BV_NUM
"https://api.bilibili.com/x/v1/dm/list.so?oid=" # 获取b站弹幕api,需要提供bv号获取cid
"https://comment.bilibili.com/{cid}.xml" # 提供bv号获取cid
header = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0",
"referer": "https://www.bilibili.com/"
}
# print(bv_list)
def get_bullet_screen(bv_list):
bullet_screen_list = [] #存放弹幕
for bv in bv_list:
cid_url = f"https://api.bilibili.com/x/player/pagelist?bvid={bv}&jsonp=jsonp"
resp1 = requests.get(cid_url, headers=header)
# print(resp1.json())
dict = resp1.json()
cid = dict["data"][0]["cid"] #获取字典中的cid
api_url = f"https://comment.bilibili.com/{cid}.xml"
resp2 = requests.get(api_url, headers=header)
resp2.encoding = "utf-8"
# print(resp2.text)
xml = BeautifulSoup(resp2.text, "xml")
ds = xml.find_all("d")
for d in ds:
bullet_screen_list.append(d.text)
print(f"爬取{bv}的弹幕成功")
return bullet_screen_list
if __name__ == '__main__':
bv_list = get_bv(BV_NUM)
print(get_bullet_screen(bv_list))