yt-dlp/yt_dlp/extractor/pokemon.py
pukkandan 86e5f3ed2e
[cleanup] Upgrade syntax
Using https://github.com/asottile/pyupgrade

1. `__future__` imports and `coding: utf-8` were removed
2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format`
3. f-strings were cherry-picked from `pyupgrade --py36-plus`

Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
2022-04-12 05:32:51 +05:30

177 lines
7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
extract_attributes,
int_or_none,
js_to_json,
merge_dicts,
)
class PokemonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/(?:[^/]+/)+(?P<display_id>[^/?#&]+))'
_TESTS = [{
'url': 'https://www.pokemon.com/us/pokemon-episodes/20_30-the-ol-raise-and-switch/',
'md5': '2fe8eaec69768b25ef898cda9c43062e',
'info_dict': {
'id': 'afe22e30f01c41f49d4f1d9eab5cd9a4',
'ext': 'mp4',
'title': 'The Ol Raise and Switch!',
'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
},
'add_id': ['LimelightMedia'],
}, {
# no data-video-title
'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
'info_dict': {
'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
'ext': 'mp4',
'title': "Pokémon : L'ascension de Darkrai",
'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
},
'add_id': ['LimelightMedia'],
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
'only_matching': True,
}, {
'url': 'http://www.pokemon.com/fr/episodes-pokemon/18_09-un-hiver-inattendu/',
'only_matching': True,
}, {
'url': 'http://www.pokemon.com/de/pokemon-folgen/01_20-bye-bye-smettbo/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, video_id or display_id)
video_data = extract_attributes(self._search_regex(
r'(<[^>]+data-video-id="%s"[^>]*>)' % (video_id if video_id else '[a-z0-9]{32}'),
webpage, 'video data element'))
video_id = video_data['data-video-id']
title = video_data.get('data-video-title') or self._html_search_meta(
'pkm-title', webpage, ' title', default=None) or self._search_regex(
r'<h1[^>]+\bclass=["\']us-title[^>]+>([^<]+)', webpage, 'title')
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'limelight:media:%s' % video_id,
'title': title,
'description': video_data.get('data-video-summary'),
'thumbnail': video_data.get('data-video-poster'),
'series': 'Pokémon',
'season_number': int_or_none(video_data.get('data-video-season')),
'episode': title,
'episode_number': int_or_none(video_data.get('data-video-episode')),
'ie_key': 'LimelightMedia',
}
class PokemonWatchIE(InfoExtractor):
_VALID_URL = r'https?://watch\.pokemon\.com/[a-z]{2}-[a-z]{2}/(?:#/)?player(?:\.html)?\?id=(?P<id>[a-z0-9]{32})'
_API_URL = 'https://www.pokemon.com/api/pokemontv/v2/channels/{0:}'
_TESTS = [{
'url': 'https://watch.pokemon.com/en-us/player.html?id=8309a40969894a8e8d5bc1311e9c5667',
'md5': '62833938a31e61ab49ada92f524c42ff',
'info_dict': {
'id': '8309a40969894a8e8d5bc1311e9c5667',
'ext': 'mp4',
'title': 'Lillier and the Staff!',
'description': 'md5:338841b8c21b283d24bdc9b568849f04',
}
}, {
'url': 'https://watch.pokemon.com/en-us/#/player?id=3fe7752ba09141f0b0f7756d1981c6b2',
'only_matching': True
}, {
'url': 'https://watch.pokemon.com/de-de/player.html?id=b3c402e111a4459eb47e12160ab0ba07',
'only_matching': True
}]
def _extract_media(self, channel_array, video_id):
for channel in channel_array:
for media in channel.get('media'):
if media.get('id') == video_id:
return media
return None
def _real_extract(self, url):
video_id = self._match_id(url)
info = {
'_type': 'url',
'id': video_id,
'url': 'limelight:media:%s' % video_id,
'ie_key': 'LimelightMedia',
}
# API call can be avoided entirely if we are listing formats
if self.get_param('listformats', False):
return info
webpage = self._download_webpage(url, video_id)
build_vars = self._parse_json(self._search_regex(
r'(?s)buildVars\s*=\s*({.*?})', webpage, 'build vars'),
video_id, transform_source=js_to_json)
region = build_vars.get('region')
channel_array = self._download_json(self._API_URL.format(region), video_id)
video_data = self._extract_media(channel_array, video_id)
if video_data is None:
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
info['_type'] = 'url_transparent'
images = video_data.get('images')
return merge_dicts(info, {
'title': video_data.get('title'),
'description': video_data.get('description'),
'thumbnail': images.get('medium') or images.get('small'),
'series': 'Pokémon',
'season_number': int_or_none(video_data.get('season')),
'episode': video_data.get('title'),
'episode_number': int_or_none(video_data.get('episode')),
})
class PokemonSoundLibraryIE(InfoExtractor):
_VALID_URL = r'https?://soundlibrary\.pokemon\.co\.jp'
_TESTS = [{
'url': 'https://soundlibrary.pokemon.co.jp/',
'info_dict': {
'title': 'Pokémon Diamond and Pearl Sound Tracks',
},
'playlist_mincount': 149,
}]
def _real_extract(self, url):
musicbox_webpage = self._download_webpage(
'https://soundlibrary.pokemon.co.jp/musicbox', None,
'Downloading list of songs')
song_titles = [x.group(1) for x in re.finditer(r'<span>([^>]+?)</span><br/>をてもち曲に加えます。', musicbox_webpage)]
song_titles = song_titles[4::2]
# each songs don't have permalink; instead we return all songs at once
song_entries = [{
'id': f'pokemon-soundlibrary-{song_id}',
'url': f'https://soundlibrary.pokemon.co.jp/api/assets/signing/sounds/wav/{song_id}.wav',
# note: the server always serves MP3 files, despite its extension of the URL above
'ext': 'mp3',
'acodec': 'mp3',
'vcodec': 'none',
'title': song_title,
'track': song_title,
'artist': 'Nintendo / Creatures Inc. / GAME FREAK inc.',
'uploader': 'Pokémon',
'release_year': 2006,
'release_date': '20060928',
'track_number': song_id,
'album': 'Pokémon Diamond and Pearl',
} for song_id, song_title in enumerate(song_titles, 1)]
return self.playlist_result(song_entries, playlist_title='Pokémon Diamond and Pearl Sound Tracks')