哔哩哔哩 Bilibili 视频与字幕 API 教程：搜索、详情与字幕提取

python3 -m pip install requests
export JUSTONEAPI_TOKEN='your_token'

import json
import os
from datetime import datetime, timezone
from pathlib import Path

import requests

BASE_URL = "https://api.justoneapi.com"
TOKEN = os.environ.get("JUSTONEAPI_TOKEN", "")


def call_api(path, **params):
    try:
        response = requests.get(
            BASE_URL + path,
            params={"token": TOKEN, **params},
            timeout=120, allow_redirects=False,
        )
    except requests.RequestException:
        raise RuntimeError("API network error or timeout") from None
    if response.status_code != 200:
        raise RuntimeError(f"API HTTP {response.status_code}")
    try:
        result = response.json()
    except ValueError:
        raise RuntimeError("API response is not JSON") from None
    if not isinstance(result, dict) or result.get("code") != 0:
        code = result.get("code") if isinstance(result, dict) else None
        raise RuntimeError(f"API failed: code={code}; check the docs")
    data = result.get("data")
    if not isinstance(data, dict):
        raise RuntimeError("Unexpected data shape; inspect the docs")
    inner = data.get("base_resp")
    if isinstance(inner, dict) and inner.get("status_code") not in (0, "0"):
        raise RuntimeError("Platform response was unsuccessful")
    return result


def save_json(folder, name, value):
    (folder / name).write_text(
        json.dumps(value, ensure_ascii=False, indent=2), encoding="utf-8"
    )


def require_list(data, key):
    value = data.get(key)
    if not isinstance(value, list):
        raise RuntimeError(f"Expected a list at {key}; inspect saved JSON")
    return value


def output_folder(topic):
    if not TOKEN or TOKEN == "your_token":
        raise RuntimeError("Set JUSTONEAPI_TOKEN before running")
    run_id = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%S%fZ")
    folder = Path(topic + "-output") / run_id
    folder.mkdir(parents=True, exist_ok=False)
    return folder


from urllib.parse import urlparse

KEYWORD = "Python 入门"
MAX_VIDEOS = 2


def download_subtitle(url):
    if url.startswith("//"):
        url = "https:" + url
    parsed = urlparse(url)
    host = parsed.hostname or ""
    if (parsed.scheme != "https" or parsed.username or parsed.password
            or parsed.port not in (None, 443)
            or not (host == "hdslb.com" or host.endswith(".hdslb.com"))):
        raise RuntimeError("Subtitle host needs manual review")
    try:
        response = requests.get(url, timeout=30, allow_redirects=False)
    except requests.RequestException:
        raise RuntimeError("Subtitle download failed") from None
    if response.status_code != 200:
        raise RuntimeError(f"Subtitle HTTP {response.status_code}")
    try:
        payload = response.json()
    except ValueError:
        raise RuntimeError("Subtitle response is not JSON") from None
    if not isinstance(payload, dict):
        raise RuntimeError("Unexpected subtitle document")
    segments = require_list(payload, "body")
    if any(not isinstance(s, dict) or not isinstance(s.get("content"), str)
           for s in segments):
        raise RuntimeError("Unexpected subtitle segment")
    return payload, "\n".join(s["content"] for s in segments)


def main():
    folder = output_folder("bilibili")
    result = call_api(
        "/api/bilibili/search-video/v2", keyword=KEYWORD,
        page="1", order="general",
    )
    save_json(folder, "search-1.json", result)
    search = result["data"]
    if search.get("code") != 0 or not isinstance(search.get("data"), dict):
        raise RuntimeError("Video search was unsuccessful")
    rows = require_list(search["data"], "result")
    ids, seen = [], set()
    for row in rows:
        bvid = row.get("bvid") if isinstance(row, dict) else None
        if bvid and str(bvid) not in seen:
            seen.add(str(bvid))
            ids.append(str(bvid))
    selected = ids[:MAX_VIDEOS]
    save_json(folder, "selected-videos.json", selected)
    outcomes = []
    for index, bvid in enumerate(selected, start=1):
        detail = call_api("/api/bilibili/get-video-detail/v2", bvid=bvid)
        save_json(folder, f"video-{index}-detail.json", detail)
        video = detail["data"].get("videoData")
        if not isinstance(video, dict) or not video.get("aid"):
            raise RuntimeError("Missing videoData/AID; inspect saved JSON")
        pages = require_list(video, "pages")
        if not pages or not isinstance(pages[0], dict) or not pages[0].get("cid"):
            raise RuntimeError("Missing segment CID; inspect saved JSON")
        cid = str(pages[0]["cid"])
        captions = call_api(
            "/api/bilibili/get-video-caption/v2",
            bvid=bvid, aid=str(video["aid"]), cid=cid,
        )
        save_json(folder, f"video-{index}-captions.json", captions)
        tracks = require_list(captions["data"], "data")
        if not tracks:
            outcomes.append({"bvid": bvid, "cid": cid, "status": "no_tracks"})
            continue
        track = tracks[0]
        url = track.get("subtitle_url") if isinstance(track, dict) else None
        if not isinstance(url, str) or not url:
            raise RuntimeError("Missing subtitle URL; inspect saved JSON")
        outcome = {"bvid": bvid, "cid": cid, "language": track.get("lan")}
        try:
            payload, text = download_subtitle(url)
        except (RuntimeError, ValueError) as error:
            outcome.update(status="download_failed", error=str(error))
        else:
            save_json(folder, f"video-{index}-subtitle.json", payload)
            (folder / f"video-{index}-subtitle.txt").write_text(text, encoding="utf-8")
            outcome["status"] = "downloaded" if text else "empty_text"
        outcomes.append(outcome)
    save_json(folder, "subtitle-outcomes.json", outcomes)
    print(f"Saved {len(selected)} video samples to {folder}")


if __name__ == "__main__":
    try:
        main()
    except RuntimeError as error:
        raise SystemExit(str(error)) from None

请仅根据提供的字幕整理本视频的主要知识点。
列出每个知识点对应的原文片段；若提供了时间信息，也保留时间位置。
字幕没有说明的内容标为“字幕未说明”，不要自行补充。