MediaCrawler/media_platform/bilibili/client.py

# -*- 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, Optional, List, Tuple
from urllib.parse import urlencode

import httpx
from playwright.async_api import BrowserContext, Page

from tools import utils

from .help import BilibiliSign
from .exception import DataFetchError
from .field import SearchOrderType, CommentOrderType


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 拿 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 {}
        img_key, sub_key = await self.get_wbi_keys()
        return BilibiliSign(img_key, sub_key).sign(req_data)

    async def get_wbi_keys(self) -> Tuple[str, str]:
        """
        获取最新的 img_key 和 sub_key
        :return:
        """
        local_storage = await self.playwright_page.evaluate("() => window.localStorage")
        wbi_img_urls = local_storage.get("wbi_img_urls", "") or local_storage.get(
            "wbi_img_url") + "-" + local_storage.get("wbi_sub_url")
        if wbi_img_urls and "-" in wbi_img_urls:
            img_url, sub_url = wbi_img_urls.split("-")
        else:
            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

    async def get(self, uri: str, params=None) -> Dict:
        final_uri = uri
        params = await self.pre_request_data(params)
        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:
        data = await self.pre_request_data(data)
        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("Begin pong bilibili...")
        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("use cache login state get web interface successfull!")
                ping_flag = True
        except Exception as e:
            utils.logger.error(f"Pong kuaishou failed: {e}, and try to login again...")
            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

    async def search_video_by_keyword(self, keyword: str, page: int = 1, page_size: int = 20,
                                      order: SearchOrderType = SearchOrderType.DEFAULT):
        """
        KuaiShou web search api
        :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
        :return:
        """
        uri = "/x/web-interface/wbi/search/type"
        post_data = {
            "search_type": "video",
            "keyword": keyword,
            "page": page,
            "page_size": page_size,
            "order": order.value
        }
        return await self.get(uri, post_data)

    async def get_video_info(self, video_id: str) -> Dict:
        """
        Kuaishou web video detail api
        :param video_id:
        :return:
        """
        post_data = {
        }
        return await self.post("", post_data)

    async def get_video_comments(self,
                                 video_id: str,
                                 order_mode: CommentOrderType = CommentOrderType.DEFAULT,
                                 pagination_str: str = '{"offset":""}'
                                 ) -> Dict:
        """get video comments
        :param video_id: 视频 ID
        :param order_mode: 排序方式
        :param pagination_str: 分页字符串，由 api 返回下一个评论请求的分页信息
        :return:
        """
        uri = "/x/v2/reply/wbi/main"
        post_data = {
            "oid": video_id,
            "mode": order_mode.value,
            "type": 1,
            "pagination_str": pagination_str
        }
        return await self.post(uri, post_data)

    async def get_video_all_comments(self, video_id: str, crawl_interval: float = 1.0, is_fetch_sub_comments=False,
                                     callback: Optional[Callable] = None, ):
        """
        get video all comments include sub comments
        :param video_id:
        :param crawl_interval:
        :param is_fetch_sub_comments:
        :param callback:
        :return:
        """

        result = []
        is_end = False
        pagination_str = '{"offset":""}'
        while not is_end:
            comments_res = await self.get_video_comments(video_id, CommentOrderType.DEFAULT, pagination_str)
            curson_info: Dict = comments_res.get("data").get("cursor")
            comment_list: List[Dict] = comments_res.get("replies", [])
            is_end = curson_info.get("is_end")
            pagination_str = curson_info.get("pagination_reply").get("next_offset")
            if callback:  # 如果有回调函数，就执行回调函数
                await callback(video_id, comment_list)
            await asyncio.sleep(crawl_interval)
            if not is_fetch_sub_comments:
                result.extend(comment_list)
                continue
            # todo handle get sub comments
        return result