import re
import requests
from urllib.parse import urlparse

from ..common.common import video_metadata
from ..common.innertube import prepare_infocards, prepare_endcards, G

def prepare_metadata(metadata):
    meta = metadata['videoDetails']

    # the actual video streams have exact information:
    try:
        sd = metadata['streamingData']
        some_stream = (sd.get('adaptiveFormats',[]) + sd.get('formats',[]))[0]
        aspect_ratio = some_stream['width'] / some_stream['height']
    # if that's unavailable (e.g. on livestreams), fall back to 16:9
    except:
        aspect_ratio = 16/9

    # Note: we could get subtitles in multiple formats directly by querying
    # https://video.google.com/timedtext?hl=en&type=list&v=<VIDEO_ID> followed by
    # https://www.youtube.com/api/timedtext?lang=<LANG_CODE>&v=<VIDEO_ID>&fmt={srv1|srv2|srv3|ttml|vtt},
    # but that won't give us autogenerated subtitles (and is an extra request).
    # we can still add &fmt= to the extracted URLs below (first one takes precedence).
    try: # find the native language captions (assuming there is only 1 audioTrack) (any level might not exist):
        default_track = metadata.get('captions',{}).get('playerCaptionsTracklistRenderer',{}).get('defaultAudioTrackIndex', 0)
        main_subtitle = metadata['captions']['playerCaptionsTracklistRenderer']['audioTracks'][default_track]['captionTrackIndices']
    except:
        main_subtitle = -1
    subtitles = sorted([
        {'url':cc['baseUrl'],
         'code':cc['languageCode'],
         'autogenerated':cc.get('kind')=="asr",
         'name':cc['name']|G.text,
         'default':i==main_subtitle,
         'query':"fmt=vtt&"+urlparse(cc['baseUrl']).query} # for our internal proxy
        for i,cc in enumerate(metadata|G('captions')
            |G('playerCaptionsTracklistRenderer')
            |G('captionTracks') or [])
    # sort order: default lang gets weight 0 (first), other manually translated weight 1, autogenerated weight 2:
    ], key=lambda cc: (not cc['default']) + cc['autogenerated'])

    endcards = prepare_endcards(metadata)

    thumbs = meta['thumbnail']['thumbnails']
    poster = sorted(thumbs, key=lambda t: t['width'], reverse=True)[0]['url']

    return {
        **video_metadata(metadata),
        'description': meta['shortDescription'],
        'aspectr': aspect_ratio,
        'unlisted': not meta['isCrawlable'],
        'poster': poster,
        'endcards': endcards,
        'all_cards': endcards,
        'subtitles': subtitles,
    }

def channel_exists(feed_id):
    feed_type = "channel_id" if re.match(r"^UC[A-Za-z0-9_-]{22}$", feed_id) else "user"
    r = requests.head("https://www.youtube.com/feeds/videos.xml", params={
        feed_type: feed_id,
    })
    return r.ok

def microformat_parser(metadata):
    """ parses additional metadata only available with get_video_info(metaOnly=True) """
    meta2 = metadata.get('microformat',{}).get('playerMicroformatRenderer',{})
    all_countries = """AD AE AF AG AI AL AM AO AQ AR AS AT AU AW AX AZ BA BB BD
        BE BF BG BH BI BJ BL BM BN BO BQ BR BS BT BV BW BY BZ CA CC CD CF CG CH
        CI CK CL CM CN CO CR CU CV CW CX CY CZ DE DJ DK DM DO DZ EC EE EG EH ER
        ES ET FI FJ FK FM FO FR GA GB GD GE GF GG GH GI GL GM GN GP GQ GR GS GT
        GU GW GY HK HM HN HR HT HU ID IE IL IM IN IO IQ IR IS IT JE JM JO JP KE
        KG KH KI KM KN KP KR KW KY KZ LA LB LC LI LK LR LS LT LU LV LY MA MC MD
        ME MF MG MH MK ML MM MN MO MP MQ MR MS MT MU MV MW MX MY MZ NA NC NE NF
        NG NI NL NO NP NR NU NZ OM PA PE PF PG PH PK PL PM PN PR PS PT PW PY QA
        RE RO RS RU RW SA SB SC SD SE SG SH SI SJ SK SL SM SN SO SR SS ST SV SX
        SY SZ TC TD TF TG TH TJ TK TL TM TN TO TR TT TV TW TZ UA UG UM US UY UZ
        VA VC VE VG VI VN VU WF WS YE YT ZA ZM ZW""".split()
    whitelisted = sorted(meta2.get('availableCountries',[]))
    blacklisted = sorted(set(all_countries) - set(whitelisted))
    regions = (
        'all' if not blacklisted else
        'none' if not whitelisted else
        f"not in {' '.join(blacklisted)}" if len(blacklisted) < len(whitelisted) else
        f"only in {' '.join(whitelisted)}"
    )
    try:
        poster = sorted(meta2['thumbnail']['thumbnails'], key=lambda t: t['width'], reverse=True)[0]['url']
    except: poster = None
    infocards = prepare_infocards(metadata)
    endcards = prepare_endcards(metadata)
    # combine cards to weed out duplicates. for videos and playlists prefer
    # infocards, for channels and websites prefer endcards, as those have more
    # information than the other.
    # if the card type is not in ident, we use the whole card for comparison
    # (otherwise they'd all replace each other)
    ident = { # ctype -> ident
        'VIDEO': 'video_id',
        'PLAYLIST': 'playlist_id',
        'CHANNEL': 'channel_id',
        'WEBSITE': 'url',
        'POLL': 'question',
    }
    getident = lambda c: c['content'].get(ident.get(c['type']), c)
    mkexclude = lambda cards, types: [getident(c) for c in cards if c['type'] in types]
    exclude = lambda cards, without: [c for c in cards if getident(c) not in without]

    allcards = exclude(infocards, mkexclude(endcards,  ['CHANNEL','WEBSITE'])) + \
               exclude(endcards,  mkexclude(infocards, ['VIDEO','PLAYLIST']))

    return {
        'published': meta2.get('publishDate'),
        #'uploaded': meta2.get('uploadDate'),
        #'infocards': infocards,
        #'endcards': endcards,
        'all_cards': allcards,
        'poster': poster,
        'regions': regions,
    }