nizika_bluesky/nico.py

"""
ニコニコのニジカ動画取得モヂュール
"""

from typing import TypedDict

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


class VideoInfo (TypedDict):
    contentId:      str
    title:          str
    tags:           list[str]
    description:    str


def get_latest_deerjika (
) -> VideoInfo | None:
    tag = '伊地知ニジカ OR ぼざろクリーチャーシリーズ'
    url = f"https://www.nicovideo.jp/tag/{ tag }"

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

    video_info = { }

    bs = get_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 Exception:
        return None

    bs = get_bs_from_url ('https://www.nicovideo.jp/watch/'
                          + video_info['contentId'])
    if bs is None:
        return None

    try:
        video_info['title'] = '-'.join (bs.find ('title').text.split ('-')[:(-1)])[:(-1)]

        tags = bs.find ('meta', attrs = { 'name': 'keywords' }).get ('content')
        video_info['tags'] = tags.split (',')

        video_info['description'] = bs.find ('meta', attrs = { 'name': 'description' }).get ('content')
    except Exception:
        return None

    return video_info


def get_bs_from_url (
        url:    str,
        params: dict    = { },
) -> BeautifulSoup | None:
    """
    URL から BeautifulSoup インスタンス生成

    Parameters
    ----------
    url:    str
        捜査する URL
    params: dict
        パラメータ

    Return
    ------
    BeautifulSoup | None
        BeautifulSoup オブゼクト（失敗したら None）
    """

    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')