爬取弹幕

main
pzmji3gwt 2 months ago
parent e65efe6b85
commit fa8de5809b

@ -0,0 +1,105 @@
import time
from typing import List
import requests
import re
from urllib import parse
from concurrent.futures import ThreadPoolExecutor, as_completed
class BilibiliVideoSpider:
def __init__(self, session_cookie: str, user_agent: str):
self.session_cookie = session_cookie
self.user_agent = user_agent
def search_videos(self, keyword: str, page: int, page_size: int) -> list:
headers = {
"Accept": "application/json, text/plain, */*",
"Accept-Encoding": "gzip, deflate, br, zstd",
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
"Cache-Control": "no-cache",
"Cookie": self.session_cookie,
"Origin": "https://search.bilibili.com",
"Pragma": "no-cache",
"Referer": f"https://search.bilibili.com/all?keyword={parse.quote(keyword)}",
"User-Agent": self.user_agent,
}
params = {
"search_type": "video",
"page": page,
"page_size": page_size,
"keyword": keyword,
}
while True:
try:
response = requests.get("https://api.bilibili.com/x/web-interface/search/type", headers=headers, params=params).json()
if response['code'] == 0:
return [item['id'] for item in response['data']['result']]
except Exception as error:
print(error)
time.sleep(1)
def retrieve_cid(self, aid: int) -> int:
headers = {
"Accept": "application/json, text/plain, */*",
"User-Agent": self.user_agent,
"Cookie": self.session_cookie,
}
response = requests.get(f"https://api.bilibili.com/x/player/pagelist?aid={aid}", headers=headers)
if response.status_code == 200:
data = response.json()
if data and 'data' in data and len(data['data']) > 0:
return data['data'][0]['cid']
raise ValueError(f"No video found for aid {aid}.")
def fetch_danmaku(self, aid: int) -> List[str]:
headers = {
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8",
"Cookie": self.session_cookie,
"User-Agent": self.user_agent
}
response = requests.get(f'https://comment.bilibili.com/{aid}.xml', headers=headers)
response.encoding = 'utf-8'
return re.findall("<d p=.+?>(.+?)</d>", response.text)
def fetch_bullet_screen(spider: BilibiliVideoSpider, aid: int) -> List[str]:
try:
print(f"Fetching bullet screen for video with aid {aid}...")
cid = spider.retrieve_cid(aid)
return spider.fetch_danmaku(cid)
except Exception as error:
print(f"Error fetching data for aid {aid}: {error}")
return []
def main():
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"
session_cookie = "CURRENT_BLACKGAP=0; buvid_fp_plain=undefined; buvid4=AD99F657-25EE-E722-504A-38818AB2C96431271-022083012-SK3hbof5R8m0%2FMDXrqLXF0ew7%2BFE4Qf8ZlKJTIBem2GNFTrtkIOz1g%3D%3D; hit-dyn-v2=1; DedeUserID=379056927; DedeUserID__ckMd5=f108d9af1bf79bfa; enable_web_push=DISABLE; header_theme_version=CLOSE; rpdid=|(u)luk))YJY0J'u~|JJk)m~|; LIVE_BUVID=AUTO7417034221177410; FEED_LIVE_VERSION=V_WATCHLATER_PIP_WINDOW3; PVID=1; fingerprint=15814142e80dfa9c068eed7a71851bf5; CURRENT_FNVAL=4048; CURRENT_QUALITY=80; buvid3=1ABDB66E-4FED-982B-9E33-0B8252C286A183741infoc; b_nut=1726320983; _uuid=993A102D3-51024-9AFA-A267-911A4D7E1051590626infoc; buvid_fp=15814142e80dfa9c068eed7a71851bf5; SESSDATA=73515621%2C1742135177%2C0e2a5%2A91CjD4Y5RhCOEVNl9wRlHMuu46raFGvX_PIZISKjPfA6kidgWNqhp7ORMi42EVo7IHscoSVmdsTlNiTDltTzFnSEtSam54WnpjVnZvUzdHTGNnd1pUNGZTb1pvYTlmSjdTby0wTVlCMFFvU1lpVGxkd1owTktpY1NDVWlpUTV2b1lmNUJfenpGa0RnIIEC; bili_jct=53fef919101982fb820518642f8ea298; sid=7s0heoa0; b_lsid=5A10234D8_19204359DD8; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjY5MDcxODYsImlhdCI6MTcyNjY0NzkyNiwicGx0IjotMX0.1EN8gxd6-3GfZQ3b4b-Iz-4vmICUJHaoAoKpMbLlRtg; bili_ticket_expires=1726907126; bp_t_offset_379056927=978437006507900928; home_feed_column=4; browser_resolution=1065-941"
spider = BilibiliVideoSpider(session_cookie, user_agent)
keyword = "2024巴黎奥运会"
results_per_page = 30
total_pages = 10
all_danmaku = []
with ThreadPoolExecutor(max_workers=10) as executor:
futures = []
for page in range(1, total_pages + 1):
print(f"Fetching search results for page {page}...")
aids = spider.search_videos(keyword, page, results_per_page)
for aid in aids:
futures.append(executor.submit(fetch_bullet_screen, spider, aid))
for future in as_completed(futures):
all_danmaku.extend(future.result())
print(f"Total bullet screens fetched: {len(all_danmaku)}")
# 将弹幕数据保存到 "弹幕.txt" 文件
with open("弹幕.txt", mode='w', encoding="utf-8") as file: # 以写入模式打开文件
for danmaku in all_danmaku: # 遍历所有弹幕数据
file.write(danmaku + '\n') # 将弹幕数据写入文件
if __name__ == "__main__":
main()
Loading…
Cancel
Save