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_nico_deerjika (
) -> list:
    URL = ('https://snapshot.search.nicovideo.jp/api/v2/snapshot/video'
           '/contents/search')

    now = datetime.now ()
    base = now - timedelta (hours = 24)

    params = { 'q':          '伊地知ニジカ OR ぼざろクリーチャーシリーズ',
               'targets':    'tags',
               '_sort':      '-startTime',
               'fields':     'contentId,title,description,tags,startTime',
               '_limit':     20,
               'jsonFilter': json.dumps ({ 'type':    'or',
                                           'filters': [{
            'type':          'range',
            'field':         'startTime',
            'from':          ('%04d-%02d-%02dT05:00:00+09:00'
                              % (base.year, base.month, base.day,
                                 base.hour, base.minute)),
            'to':            ('%04d-%02d-%02dT05:00:00+09:00'
                              % (now.year, now.month, now.day)),
            'include_lower': True }] }) }

    try:
        res = requests.get (URL, params = params, timeout = 60).json ()
    except Timeout:
        return []

    data = []
    for datum in res['data']:
        datum['tags'] = datum['tags'].split ()
        data.append (datum)

    return data

    pass


def get_latest_deerjika (
) -> VideoInfo | None:
    tag = '伊地知ニジカ'
    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')