pc7si35ku
/
Crawler
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ADD file via upload

Browse Source
main
pc7si35ku 2 months ago
parent b9fbed966a
commit d82d59e8be
1 changed files with 167 additions and 0 deletions
Show Stats Download Patch File Download Diff File

167
Crawler.py
Unescape View File

@ -0,0 +1,167 @@
import time
from typing import List
import requests
import json
from urllib import parse
import re
class BilibiliSpider:
def __init__(self, cookie: str, user_agent):
self.cookie = cookie
self.user_agent = user_agent
def get_search_result(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.cookie,
"Origin": "https://search.bilibili.com",
"Pragma": "no-cache",
"Priority": "u=1, i",
"Referer": f"https://search.bilibili.com/all?vt=71519330&keyword={parse.quote(keyword)}&from_source=webtop_search&spm_id_from=333.1007&search_source=5&page=3&o=48",
"Sec-Ch-Ua": "\"Not)A;Brand\";v=\"99\", \"Google Chrome\";v=\"127\", \"Chromium\";v=\"127\"",
"Sec-Ch-Ua-Mobile": "?0",
"Sec-Ch-Ua-Platform": "\"Windows\"",
"Sec-Fetch-Dest": "empty",
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Site": "same-site",
"User-Agent": self.user_agent
}
params = {
"category_id": "",
"search_type": "video",
"ad_resource": 5654,
"__refresh__": True,
"_extra": "",
"context": "",
"page": page,
"page_size": page_size,
"from_source": "",
"from_spmid": "333.337",
"platform": "pc",
"highlight": 1,
"single_column": 0,
"keyword": keyword,
"qv_id": "D9L6NRPnDle6B4EA2dJ4hfRjUOIvKeIM",
"source_tag": 3,
"gaia_vtoken": "",
"dynamic_offset": 48,
"web_location": 1430654,
"w_rid": "dc50190c40844231b9ad3622eebcc62b",
"wts": 1724771963
}
while True:
try:
url = "https://api.bilibili.com/x/web-interface/search/type"
response = requests.get(url, headers=headers, params=params).json()
if response['code'] == 0:
aids = [item['id'] for item in response['data']['result']]
return aids
except Exception as e:
print(e)
time.sleep(1)
def get_cid(self, aid: int) -> int:
headers = {
"Accept": "application/json, text/plain, */*",
"User-Agent": self.user_agent,
"Cookie": self.cookie,
}
# 假设这个URL是获取视频详细信息的API
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:
# 假设返回的数据结构中 cid 在每个页面对象中
return data['data'][0]['cid'] # 返回第一个页面的 cid
else:
raise ValueError(f"No video found for aid {aid}.")
else:
raise Exception(f"Failed to retrieve CID for aid {aid}. Status code: {response.status_code}")
def get_bullet_screen(self, aid: int) -> List:
headers = {
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
"Accept-Encoding": "gzip, deflate, br, zstd",
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
"Cache-Control": "no-cache",
"Cookie": self.cookie,
"Pragma": "no-cache",
"Priority": "u=0, i",
"Sec-CH-UA": "\"Not)A;Brand\";v=\"99\", \"Google Chrome\";v=\"127\", \"Chromium\";v=\"127\"",
"Sec-CH-UA-Mobile": "?0",
"Sec-CH-UA-Platform": "\"Windows\"",
"Sec-Fetch-Dest": "document",
"Sec-Fetch-Mode": "navigate",
"Sec-Fetch-Site": "none",
"Sec-Fetch-User": "?1",
"Upgrade-Insecure-Requests": "1",
"User-Agent": self.user_agent
}
url = 'https://comment.bilibili.com/' + str(aid) + '.xml'
response = requests.get(url, headers=headers)
response.encoding = 'utf-8'
html = response.text
return re.findall("<d p=.+?>(.+?)</d>", html)
User_Agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 " \
"Safari/537.36 Core/1.94.265.400 QQBrowser/12.7.5769.400 "
cookies = "buvid3=0010B368-0E93-5612-1F55-B0AEFA2A788E68736infoc; b_nut=1722828468; _uuid=65A45AC6-10CC5-FD72-3AE5-EDD1D94C6B2A71555infoc; enable_web_push=DISABLE; home_feed_column=5; buvid4=D4A818B4-3DAF-E9E9-CCA6-2292209CA07D70717-024080503-n8yYBXNzLps6TrOphT3zww%3D%3D; header_theme_version=CLOSE; rpdid=|(J|)Rl|kRuk0J'u~kk)k)lJY; CURRENT_QUALITY=80; fingerprint=6d7a6d23f809895ad523f52c214cab31; buvid_fp_plain=undefined; b-user-id=06265419-2000-a180-a632-d8face940e87; CURRENT_BLACKGAP=0; is-2022-channel=1; buvid_fp=6d7a6d23f809895ad523f52c214cab31; bili_ticket_expires=1726804000; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjY4MDQwNjAsImlhdCI6MTcyNjU0NDgwMCwicGx0IjotMX0.GNq3G9bTe-3WQ8VAVc0sI4Qz9p3p7_dhcjMvGWeptHU; browser_resolution=1491-706; bp_t_offset_342699701=978044347712798720; CURRENT_FNVAL=4048; b_lsid=E10FCACF9_191FEFD995E; SESSDATA=a362140e%2C1742111957%2Cf7826%2A91CjBL7AZ1ewk0PKshkKehAyTa-FGUdcmmYfvGIZvLIvE3mrP0Lp1ZFo7Vp-Hg1cnTkFcSVkpPSlUwSkpFWWNodXFmNDdRNnFOdkdfTkpkbmpQNjlDUGkxLXpMRXZIMWpLUkVVSU1sNjM2clZVUmp1dEZDeDFmRTZJS0JObEstb1RVeV94ek91UktnIIEC; bili_jct=2627cc66d6b22d78edd09ea63d44b26e; DedeUserID=3546763816339525; DedeUserID__ckMd5=d856350aecedd530; sid=8ec23v36"
Bili = BilibiliSpider(cookies, User_Agent)
print(Bili.get_search_result("巴黎奥运会", 1, 30))
Bili2 = BilibiliSpider(cookies, User_Agent)
# a=1856498793
# print(Bili2.get_cid(int(a)))
# data_list=Bili2.get_bullet_screen(1646728264)
def main():
# 创建 BilibiliSpider 实例
Bili = BilibiliSpider(cookies, User_Agent)
# 搜索关键词
keyword = "2024巴黎奥运会"
page_size = 30 # 每页30个结果
total_pages = 10 # 总共爬取10页，300个视频
data_list = [] # 存储所有弹幕数据
for page in range(1, total_pages + 1):
print(f"Fetching search results for page {page}...")
aids = Bili.get_search_result(keyword, page, page_size)
for aid in aids:
try:
print(f"Fetching bullet screen for video with aid {aid}...")
# 获取视频的 cid
cid = Bili.get_cid(aid)
# 获取弹幕数据
bullet_screens = Bili.get_bullet_screen(cid)
data_list.extend(bullet_screens) # 将弹幕数据添加到 data_list
print(f"Fetched {len(bullet_screens)} bullet screens for aid {aid}.")
except Exception as e:
print(f"An error occurred while fetching data for aid {aid}: {e}")
# 打印所有弹幕数据的数量
print(f"Total bullet screens fetched: {len(data_list)}")
# 你可以选择将 data_list 保存到文件或进行其他处理
# 例如，保存到文件
# with open('bullet_screens.json', 'w', encoding='utf-8') as f:
# json.dump(data_list, f, ensure_ascii=False, indent=4)
for data in data_list:
with open("弹幕.txt", mode='a', encoding="utf-8") as f:
f.write(data + '\n')
if __name__ == "__main__":
main()
Write Preview
Loading…
Cancel
Save