nicolib/module.py

"""
ニコニコ動画から動画情報を取得するためのヘルパ集
"""

from __future__ import annotations

from typing import TypedDict

import requests
from bs4 import BeautifulSoup
from requests.exceptions import Timeout


def fetch_video_info (
        video_code: str,
) -> VideoInfo | None:
    """
    動画コードからタイトル、タグ、説明を取得して返す．

    Parameters
    ----------
    video_code: str
        動画コード

    Return
    ------
    VideoInfo | None
        動画情報
    """

    bs = _create_bs_from_url (f"https://www.nicovideo.jp/watch/{ video_code }")
    if bs is None:
        return None

    try:
        title_tag = bs.find ('title')
        if title_tag is None:
            return None
        title = '-'.join (title_tag.text.split ('-')[:(-1)]).strip ()

        tags_str: str = (bs.find ('meta', attrs = { 'name': 'keywords' })
                         .get ('content'))  # type: ignore
        tags = tags_str.split (',')

        description = (bs.find ('meta', attrs = { 'name': 'description' })
                       .get ('content'))  # type: ignore
    except (AttributeError, TypeError):
        return None

    return { 'contentId':   video_code,
             'title':       title,
             'tags':        tags,
             'description': str (description) }


def fetch_embed_info (
        url:    str,
) -> tuple[str, str, str]:
    """
    ニコニコ動画の URL からタイトル、詳細、サムネールを取得して返す．

    Parameters
    ----------
    url:    str
        動画 URL

    Return
    ------
    tuple[str, str, str]
        タイトル、詳細、サムネールからなるタプル
    """

    title = ''
    description = ''
    thumbnail = ''

    bs = _create_bs_from_url (url)
    if bs is None:
        return ('', '', '')

    tmp = bs.find ('title')
    if tmp is not None:
        title = tmp.text

    tmp = bs.find ('meta', attrs = { 'name': 'description' })
    if tmp is not None and hasattr (tmp, 'get'):
        try:
            description = str (tmp.get ('content'))
        except (AttributeError, TypeError):
            pass

    tmp = bs.find ('meta', attrs = { 'name': 'thumbnail' })
    if tmp is not None and hasattr (tmp, 'get'):
        try:
            thumbnail = str (tmp.get ('content'))
        except (AttributeError, TypeError):
            pass

    return (title, description, thumbnail)


def fetch_latest_video (
        tags:   list[str],
) -> VideoInfo | None:
    """
    ニコニコから指定したタグが含まれる動画を検索し，最新のものを返す．

    Parameters
    ----------
    tags:   list[str]
        タグ・リスト

    Return
    ------
    VideoInfo | None
        動画情報
    """

    tag = ' OR '.join (tags)
    url = f"https://www.nicovideo.jp/tag/{ tag }"

    params = { 'sort':  'f',
               'order': 'd' }

    video_info = { }

    bs = _create_bs_from_url (url, params)
    if bs is None:
        return None

    try:
        video = (bs.find_all ('ul', class_ = 'videoListInner')[1]
                 .find ('li', class_ = 'item'))

        video_info['contentId'] = video['data-video-id']
    except (AttributeError, IndexError, KeyError, TypeError):
        return None

    return fetch_video_info (video_info['contentId'])


def _create_bs_from_url (
        url:    str,
        params: dict | None = None,
) -> BeautifulSoup | None:
    """
    URL から BeautifulSoup オブゼクトを作成する．

    Parameters
    ----------
    url:    str
        URL
    params: dict | None
        パラメータ

    Return
    ------
    BeautifulSoup | None
        BeautifulSoup オブゼクト
    """

    if params is None:
        params = { }

    try:
        req = requests.get (url, params = params, timeout = 60)
    except Timeout:
        return None

    if req.status_code != 200:
        return None

    req.encoding = req.apparent_encoding

    return BeautifulSoup (req.text, 'html.parser')


class VideoInfo (TypedDict):
    """
    動画情報
    """

    contentId:      str
    title:          str
    tags:           list[str]
    description:    str