MediaCrawler/media_platform/bilibili/client.py

202 lines
7.6 KiB
Python
Raw Normal View History

2023-12-02 16:30:10 +00:00
# -*- coding: utf-8 -*-
# @Author : relakkes@gmail.com
# @Time : 2023/12/2 18:44
# @Desc : bilibili 请求客户端
import asyncio
import json
from typing import Any, Callable, Dict, List, Optional, Tuple, Union
2023-12-02 16:30:10 +00:00
from urllib.parse import urlencode
import httpx
from playwright.async_api import BrowserContext, Page
from tools import utils
from .exception import DataFetchError
2023-12-06 15:49:56 +00:00
from .field import CommentOrderType, SearchOrderType
from .help import BilibiliSign
2023-12-02 16:30:10 +00:00
class BilibiliClient:
def __init__(
self,
timeout=10,
proxies=None,
*,
headers: Dict[str, str],
playwright_page: Page,
cookie_dict: Dict[str, str],
):
self.proxies = proxies
self.timeout = timeout
self.headers = headers
self._host = "https://api.bilibili.com"
self.playwright_page = playwright_page
self.cookie_dict = cookie_dict
async def request(self, method, url, **kwargs) -> Any:
async with httpx.AsyncClient(proxies=self.proxies) as client:
response = await client.request(
method, url, timeout=self.timeout,
**kwargs
)
data: Dict = response.json()
if data.get("code") != 0:
raise DataFetchError(data.get("message", "unkonw error"))
else:
return data.get("data", {})
async def pre_request_data(self, req_data: Dict) -> Dict:
"""
发送请求进行请求参数签名
需要从 localStorage wbi_img_urls 这参数值如下
https://i0.hdslb.com/bfs/wbi/7cd084941338484aae1ad9425b84077c.png-https://i0.hdslb.com/bfs/wbi/4932caff0ff746eab6f01bf08b70ac45.png
:param req_data:
:return:
"""
if not req_data:
return {}
2023-12-03 15:19:02 +00:00
img_key, sub_key = await self.get_wbi_keys()
2023-12-02 16:30:10 +00:00
return BilibiliSign(img_key, sub_key).sign(req_data)
async def get_wbi_keys(self) -> Tuple[str, str]:
2023-12-02 16:30:10 +00:00
"""
获取最新的 img_key sub_key
:return:
"""
local_storage = await self.playwright_page.evaluate("() => window.localStorage")
2023-12-04 15:16:02 +00:00
wbi_img_urls = local_storage.get("wbi_img_urls", "") or local_storage.get(
"wbi_img_url") + "-" + local_storage.get("wbi_sub_url")
2023-12-03 15:19:02 +00:00
if wbi_img_urls and "-" in wbi_img_urls:
img_url, sub_url = wbi_img_urls.split("-")
else:
2023-12-02 16:30:10 +00:00
resp = await self.request(method="GET", url=self._host + "/x/web-interface/nav")
img_url: str = resp['wbi_img']['img_url']
sub_url: str = resp['wbi_img']['sub_url']
img_key = img_url.rsplit('/', 1)[1].split('.')[0]
sub_key = sub_url.rsplit('/', 1)[1].split('.')[0]
return img_key, sub_key
2023-12-09 13:10:01 +00:00
async def get(self, uri: str, params=None, enable_params_sign: bool = True) -> Dict:
2023-12-02 16:30:10 +00:00
final_uri = uri
2023-12-09 13:10:01 +00:00
if enable_params_sign:
params = await self.pre_request_data(params)
2023-12-02 16:30:10 +00:00
if isinstance(params, dict):
final_uri = (f"{uri}?"
f"{urlencode(params)}")
return await self.request(method="GET", url=f"{self._host}{final_uri}", headers=self.headers)
async def post(self, uri: str, data: dict) -> Dict:
2023-12-03 15:19:02 +00:00
data = await self.pre_request_data(data)
2023-12-02 16:30:10 +00:00
json_str = json.dumps(data, separators=(',', ':'), ensure_ascii=False)
return await self.request(method="POST", url=f"{self._host}{uri}",
data=json_str, headers=self.headers)
async def pong(self) -> bool:
"""get a note to check if login state is ok"""
utils.logger.info("[BilibiliClient.pong] Begin pong bilibili...")
2023-12-02 16:30:10 +00:00
ping_flag = False
try:
check_login_uri = "/x/web-interface/nav"
response = await self.get(check_login_uri)
if response.get("isLogin"):
utils.logger.info("[BilibiliClient.pong] Use cache login state get web interface successfull!")
ping_flag = True
2023-12-02 16:30:10 +00:00
except Exception as e:
utils.logger.error(f"[BilibiliClient.pong] Pong bilibili failed: {e}, and try to login again...")
2023-12-02 16:30:10 +00:00
ping_flag = False
return ping_flag
async def update_cookies(self, browser_context: BrowserContext):
cookie_str, cookie_dict = utils.convert_cookies(await browser_context.cookies())
self.headers["Cookie"] = cookie_str
self.cookie_dict = cookie_dict
2023-12-03 15:19:02 +00:00
async def search_video_by_keyword(self, keyword: str, page: int = 1, page_size: int = 20,
2023-12-04 15:16:02 +00:00
order: SearchOrderType = SearchOrderType.DEFAULT):
2023-12-02 16:30:10 +00:00
"""
KuaiShou web search api
2023-12-03 15:19:02 +00:00
:param keyword: 搜索关键词
:param page: 分页参数具体第几页
:param page_size: 每一页参数的数量
:param order: 搜索结果排序默认位综合排序
2023-12-02 16:30:10 +00:00
:return:
"""
2023-12-03 15:19:02 +00:00
uri = "/x/web-interface/wbi/search/type"
2023-12-02 16:30:10 +00:00
post_data = {
2023-12-03 15:19:02 +00:00
"search_type": "video",
"keyword": keyword,
"page": page,
"page_size": page_size,
"order": order.value
2023-12-02 16:30:10 +00:00
}
2023-12-03 15:19:02 +00:00
return await self.get(uri, post_data)
2023-12-02 16:30:10 +00:00
async def get_video_info(self, aid: Union[int, None] = None, bvid: Union[str, None] = None) -> Dict:
2023-12-02 16:30:10 +00:00
"""
Bilibli web video detail api, aid bvid任选一个参数
:param aid: 稿件avid
:param bvid: 稿件bvid
2023-12-02 16:30:10 +00:00
:return:
"""
if not aid and not bvid:
raise ValueError("请提供 aid 或 bvid 中的至少一个参数")
2023-12-09 13:10:01 +00:00
uri = "/x/web-interface/view/detail"
params = dict()
if aid:
params.update({"aid": aid})
else:
params.update({"bvid": bvid})
2023-12-09 13:10:01 +00:00
return await self.get(uri, params, enable_params_sign=False)
2023-12-02 16:30:10 +00:00
2023-12-04 15:16:02 +00:00
async def get_video_comments(self,
video_id: str,
order_mode: CommentOrderType = CommentOrderType.DEFAULT,
2023-12-09 13:10:01 +00:00
next: int = 0
2023-12-04 15:16:02 +00:00
) -> Dict:
2023-12-02 16:30:10 +00:00
"""get video comments
2023-12-04 15:16:02 +00:00
:param video_id: 视频 ID
:param order_mode: 排序方式
2023-12-09 13:10:01 +00:00
:param next: 评论页选择
2023-12-02 16:30:10 +00:00
:return:
"""
2023-12-04 15:16:02 +00:00
uri = "/x/v2/reply/wbi/main"
2023-12-02 16:30:10 +00:00
post_data = {
2023-12-04 15:16:02 +00:00
"oid": video_id,
"mode": order_mode.value,
"type": 1,
2023-12-09 13:10:01 +00:00
"ps": 20,
"next": next
2023-12-02 16:30:10 +00:00
}
2023-12-09 13:10:01 +00:00
return await self.get(uri, post_data)
2023-12-02 16:30:10 +00:00
2023-12-04 15:16:02 +00:00
async def get_video_all_comments(self, video_id: str, crawl_interval: float = 1.0, is_fetch_sub_comments=False,
2023-12-02 16:30:10 +00:00
callback: Optional[Callable] = None, ):
"""
get video all comments include sub comments
2023-12-04 15:16:02 +00:00
:param video_id:
2023-12-02 16:30:10 +00:00
:param crawl_interval:
:param is_fetch_sub_comments:
:param callback:
:return:
"""
result = []
2023-12-04 15:16:02 +00:00
is_end = False
2023-12-09 13:10:01 +00:00
next_page =0
2023-12-04 15:16:02 +00:00
while not is_end:
2023-12-09 13:10:01 +00:00
comments_res = await self.get_video_comments(video_id, CommentOrderType.DEFAULT, next_page)
curson_info: Dict = comments_res.get("cursor")
2023-12-04 15:16:02 +00:00
comment_list: List[Dict] = comments_res.get("replies", [])
is_end = curson_info.get("is_end")
2023-12-09 13:10:01 +00:00
next_page = curson_info.get("next")
2023-12-02 16:30:10 +00:00
if callback: # 如果有回调函数,就执行回调函数
2023-12-04 15:16:02 +00:00
await callback(video_id, comment_list)
2023-12-02 16:30:10 +00:00
await asyncio.sleep(crawl_interval)
if not is_fetch_sub_comments:
2023-12-04 15:16:02 +00:00
result.extend(comment_list)
2023-12-02 16:30:10 +00:00
continue
# todo handle get sub comments
return result