invidious-experimenting/src/invidious/videos.cr

794 lines
28 KiB
Crystal
Raw Normal View History

2018-08-13 06:34:13 +05:30
CAPTION_LANGUAGES = {
2018-08-06 23:53:36 +05:30
"",
"English",
"English (auto-generated)",
"Afrikaans",
"Albanian",
"Amharic",
"Arabic",
"Armenian",
"Azerbaijani",
"Bangla",
"Basque",
"Belarusian",
"Bosnian",
"Bulgarian",
"Burmese",
"Catalan",
"Cebuano",
"Chinese (Simplified)",
"Chinese (Traditional)",
"Corsican",
"Croatian",
"Czech",
"Danish",
"Dutch",
"Esperanto",
"Estonian",
"Filipino",
"Finnish",
"French",
"Galician",
"Georgian",
"German",
"Greek",
"Gujarati",
"Haitian Creole",
"Hausa",
"Hawaiian",
"Hebrew",
"Hindi",
"Hmong",
"Hungarian",
"Icelandic",
"Igbo",
"Indonesian",
"Irish",
"Italian",
"Japanese",
"Javanese",
"Kannada",
"Kazakh",
"Khmer",
"Korean",
"Kurdish",
"Kyrgyz",
"Lao",
"Latin",
"Latvian",
"Lithuanian",
"Luxembourgish",
"Macedonian",
"Malagasy",
"Malay",
"Malayalam",
"Maltese",
"Maori",
"Marathi",
"Mongolian",
"Nepali",
"Norwegian",
"Nyanja",
"Pashto",
"Persian",
"Polish",
"Portuguese",
"Punjabi",
"Romanian",
"Russian",
"Samoan",
"Scottish Gaelic",
"Serbian",
"Shona",
"Sindhi",
"Sinhala",
"Slovak",
"Slovenian",
"Somali",
"Southern Sotho",
"Spanish",
2018-08-07 04:55:25 +05:30
"Spanish (Latin America)",
2018-08-06 23:53:36 +05:30
"Sundanese",
"Swahili",
"Swedish",
"Tajik",
"Tamil",
"Telugu",
"Thai",
"Turkish",
"Ukrainian",
"Urdu",
"Uzbek",
"Vietnamese",
"Welsh",
"Western Frisian",
"Xhosa",
"Yiddish",
"Yoruba",
"Zulu",
2018-08-13 06:34:13 +05:30
}
2018-08-06 23:53:36 +05:30
2018-09-25 00:54:33 +05:30
REGIONS = {"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"}
2018-09-24 05:59:47 +05:30
BYPASS_REGIONS = {
2018-09-26 07:37:18 +05:30
"GB",
2018-09-25 00:54:33 +05:30
"DE",
"FR",
2018-09-24 05:59:47 +05:30
"IN",
2018-09-25 00:54:33 +05:30
"CN",
"RU",
"CA",
"JP",
"IT",
"TH",
"ES",
"AE",
"KR",
"IR",
2018-09-24 05:59:47 +05:30
"BR",
"PK",
2018-09-25 00:54:33 +05:30
"ID",
2018-09-24 05:59:47 +05:30
"BD",
"MX",
"PH",
"EG",
"VN",
"CD",
"TR",
}
2018-08-13 19:47:28 +05:30
2018-08-13 06:34:13 +05:30
VIDEO_THUMBNAILS = {
2018-09-21 20:41:04 +05:30
{name: "maxres", host: "invidio.us", url: "maxres", height: 720, width: 1280},
{name: "maxresdefault", host: "i.ytimg.com", url: "maxresdefault", height: 720, width: 1280},
{name: "sddefault", host: "i.ytimg.com", url: "sddefault", height: 480, width: 640},
{name: "high", host: "i.ytimg.com", url: "hqdefault", height: 360, width: 480},
{name: "medium", host: "i.ytimg.com", url: "mqdefault", height: 180, width: 320},
{name: "default", host: "i.ytimg.com", url: "default", height: 90, width: 120},
{name: "start", host: "i.ytimg.com", url: "1", height: 90, width: 120},
{name: "middle", host: "i.ytimg.com", url: "2", height: 90, width: 120},
{name: "end", host: "i.ytimg.com", url: "3", height: 90, width: 120},
2018-08-13 06:34:13 +05:30
}
2018-08-12 20:04:26 +05:30
# See https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/youtube.py#L380-#L476
VIDEO_FORMATS = {
"5" => {"ext" => "flv", "width" => 400, "height" => 240, "acodec" => "mp3", "abr" => 64, "vcodec" => "h263"},
"6" => {"ext" => "flv", "width" => 450, "height" => 270, "acodec" => "mp3", "abr" => 64, "vcodec" => "h263"},
"13" => {"ext" => "3gp", "acodec" => "aac", "vcodec" => "mp4v"},
"17" => {"ext" => "3gp", "width" => 176, "height" => 144, "acodec" => "aac", "abr" => 24, "vcodec" => "mp4v"},
"18" => {"ext" => "mp4", "width" => 640, "height" => 360, "acodec" => "aac", "abr" => 96, "vcodec" => "h264"},
"22" => {"ext" => "mp4", "width" => 1280, "height" => 720, "acodec" => "aac", "abr" => 192, "vcodec" => "h264"},
"34" => {"ext" => "flv", "width" => 640, "height" => 360, "acodec" => "aac", "abr" => 128, "vcodec" => "h264"},
"35" => {"ext" => "flv", "width" => 854, "height" => 480, "acodec" => "aac", "abr" => 128, "vcodec" => "h264"},
"36" => {"ext" => "3gp", "width" => 320, "acodec" => "aac", "vcodec" => "mp4v"},
"37" => {"ext" => "mp4", "width" => 1920, "height" => 1080, "acodec" => "aac", "abr" => 192, "vcodec" => "h264"},
"38" => {"ext" => "mp4", "width" => 4096, "height" => 3072, "acodec" => "aac", "abr" => 192, "vcodec" => "h264"},
"43" => {"ext" => "webm", "width" => 640, "height" => 360, "acodec" => "vorbis", "abr" => 128, "vcodec" => "vp8"},
"44" => {"ext" => "webm", "width" => 854, "height" => 480, "acodec" => "vorbis", "abr" => 128, "vcodec" => "vp8"},
"45" => {"ext" => "webm", "width" => 1280, "height" => 720, "acodec" => "vorbis", "abr" => 192, "vcodec" => "vp8"},
"46" => {"ext" => "webm", "width" => 1920, "height" => 1080, "acodec" => "vorbis", "abr" => 192, "vcodec" => "vp8"},
"59" => {"ext" => "mp4", "width" => 854, "height" => 480, "acodec" => "aac", "abr" => 128, "vcodec" => "h264"},
"78" => {"ext" => "mp4", "width" => 854, "height" => 480, "acodec" => "aac", "abr" => 128, "vcodec" => "h264"},
# 3D videos
"82" => {"ext" => "mp4", "height" => 360, "format" => "3D", "acodec" => "aac", "abr" => 128, "vcodec" => "h264"},
"83" => {"ext" => "mp4", "height" => 480, "format" => "3D", "acodec" => "aac", "abr" => 128, "vcodec" => "h264"},
"84" => {"ext" => "mp4", "height" => 720, "format" => "3D", "acodec" => "aac", "abr" => 192, "vcodec" => "h264"},
"85" => {"ext" => "mp4", "height" => 1080, "format" => "3D", "acodec" => "aac", "abr" => 192, "vcodec" => "h264"},
"100" => {"ext" => "webm", "height" => 360, "format" => "3D", "acodec" => "vorbis", "abr" => 128, "vcodec" => "vp8"},
"101" => {"ext" => "webm", "height" => 480, "format" => "3D", "acodec" => "vorbis", "abr" => 192, "vcodec" => "vp8"},
"102" => {"ext" => "webm", "height" => 720, "format" => "3D", "acodec" => "vorbis", "abr" => 192, "vcodec" => "vp8"},
# Apple HTTP Live Streaming
"91" => {"ext" => "mp4", "height" => 144, "format" => "HLS", "acodec" => "aac", "abr" => 48, "vcodec" => "h264"},
"92" => {"ext" => "mp4", "height" => 240, "format" => "HLS", "acodec" => "aac", "abr" => 48, "vcodec" => "h264"},
"93" => {"ext" => "mp4", "height" => 360, "format" => "HLS", "acodec" => "aac", "abr" => 128, "vcodec" => "h264"},
"94" => {"ext" => "mp4", "height" => 480, "format" => "HLS", "acodec" => "aac", "abr" => 128, "vcodec" => "h264"},
"95" => {"ext" => "mp4", "height" => 720, "format" => "HLS", "acodec" => "aac", "abr" => 256, "vcodec" => "h264"},
"96" => {"ext" => "mp4", "height" => 1080, "format" => "HLS", "acodec" => "aac", "abr" => 256, "vcodec" => "h264"},
"132" => {"ext" => "mp4", "height" => 240, "format" => "HLS", "acodec" => "aac", "abr" => 48, "vcodec" => "h264"},
"151" => {"ext" => "mp4", "height" => 72, "format" => "HLS", "acodec" => "aac", "abr" => 24, "vcodec" => "h264"},
# DASH mp4 video
"133" => {"ext" => "mp4", "height" => 240, "format" => "DASH video", "vcodec" => "h264"},
"134" => {"ext" => "mp4", "height" => 360, "format" => "DASH video", "vcodec" => "h264"},
"135" => {"ext" => "mp4", "height" => 480, "format" => "DASH video", "vcodec" => "h264"},
"136" => {"ext" => "mp4", "height" => 720, "format" => "DASH video", "vcodec" => "h264"},
"137" => {"ext" => "mp4", "height" => 1080, "format" => "DASH video", "vcodec" => "h264"},
"138" => {"ext" => "mp4", "format" => "DASH video", "vcodec" => "h264"}, # Height can vary (https=>//github.com/rg3/youtube-dl/issues/4559)
"160" => {"ext" => "mp4", "height" => 144, "format" => "DASH video", "vcodec" => "h264"},
"212" => {"ext" => "mp4", "height" => 480, "format" => "DASH video", "vcodec" => "h264"},
"264" => {"ext" => "mp4", "height" => 1440, "format" => "DASH video", "vcodec" => "h264"},
"298" => {"ext" => "mp4", "height" => 720, "format" => "DASH video", "vcodec" => "h264", "fps" => 60},
"299" => {"ext" => "mp4", "height" => 1080, "format" => "DASH video", "vcodec" => "h264", "fps" => 60},
"266" => {"ext" => "mp4", "height" => 2160, "format" => "DASH video", "vcodec" => "h264"},
# Dash mp4 audio
"139" => {"ext" => "m4a", "format" => "DASH audio", "acodec" => "aac", "abr" => 48, "container" => "m4a_dash"},
"140" => {"ext" => "m4a", "format" => "DASH audio", "acodec" => "aac", "abr" => 128, "container" => "m4a_dash"},
"141" => {"ext" => "m4a", "format" => "DASH audio", "acodec" => "aac", "abr" => 256, "container" => "m4a_dash"},
"256" => {"ext" => "m4a", "format" => "DASH audio", "acodec" => "aac", "container" => "m4a_dash"},
"258" => {"ext" => "m4a", "format" => "DASH audio", "acodec" => "aac", "container" => "m4a_dash"},
"325" => {"ext" => "m4a", "format" => "DASH audio", "acodec" => "dtse", "container" => "m4a_dash"},
"328" => {"ext" => "m4a", "format" => "DASH audio", "acodec" => "ec-3", "container" => "m4a_dash"},
# Dash webm
"167" => {"ext" => "webm", "height" => 360, "width" => 640, "format" => "DASH video", "container" => "webm", "vcodec" => "vp8"},
"168" => {"ext" => "webm", "height" => 480, "width" => 854, "format" => "DASH video", "container" => "webm", "vcodec" => "vp8"},
"169" => {"ext" => "webm", "height" => 720, "width" => 1280, "format" => "DASH video", "container" => "webm", "vcodec" => "vp8"},
"170" => {"ext" => "webm", "height" => 1080, "width" => 1920, "format" => "DASH video", "container" => "webm", "vcodec" => "vp8"},
"218" => {"ext" => "webm", "height" => 480, "width" => 854, "format" => "DASH video", "container" => "webm", "vcodec" => "vp8"},
"219" => {"ext" => "webm", "height" => 480, "width" => 854, "format" => "DASH video", "container" => "webm", "vcodec" => "vp8"},
"278" => {"ext" => "webm", "height" => 144, "format" => "DASH video", "container" => "webm", "vcodec" => "vp9"},
"242" => {"ext" => "webm", "height" => 240, "format" => "DASH video", "vcodec" => "vp9"},
"243" => {"ext" => "webm", "height" => 360, "format" => "DASH video", "vcodec" => "vp9"},
"244" => {"ext" => "webm", "height" => 480, "format" => "DASH video", "vcodec" => "vp9"},
"245" => {"ext" => "webm", "height" => 480, "format" => "DASH video", "vcodec" => "vp9"},
"246" => {"ext" => "webm", "height" => 480, "format" => "DASH video", "vcodec" => "vp9"},
"247" => {"ext" => "webm", "height" => 720, "format" => "DASH video", "vcodec" => "vp9"},
"248" => {"ext" => "webm", "height" => 1080, "format" => "DASH video", "vcodec" => "vp9"},
"271" => {"ext" => "webm", "height" => 1440, "format" => "DASH video", "vcodec" => "vp9"},
# itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
"272" => {"ext" => "webm", "height" => 2160, "format" => "DASH video", "vcodec" => "vp9"},
"302" => {"ext" => "webm", "height" => 720, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"303" => {"ext" => "webm", "height" => 1080, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"308" => {"ext" => "webm", "height" => 1440, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"313" => {"ext" => "webm", "height" => 2160, "format" => "DASH video", "vcodec" => "vp9"},
"315" => {"ext" => "webm", "height" => 2160, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"330" => {"ext" => "webm", "height" => 144, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"331" => {"ext" => "webm", "height" => 240, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"332" => {"ext" => "webm", "height" => 360, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"333" => {"ext" => "webm", "height" => 480, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"334" => {"ext" => "webm", "height" => 720, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"335" => {"ext" => "webm", "height" => 1080, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"336" => {"ext" => "webm", "height" => 1440, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
"337" => {"ext" => "webm", "height" => 2160, "format" => "DASH video", "vcodec" => "vp9", "fps" => 60},
# Dash webm audio
"171" => {"ext" => "webm", "acodec" => "vorbis", "format" => "DASH audio", "abr" => 128},
"172" => {"ext" => "webm", "acodec" => "vorbis", "format" => "DASH audio", "abr" => 256},
# Dash webm audio with opus inside
"249" => {"ext" => "webm", "format" => "DASH audio", "acodec" => "opus", "abr" => 50},
"250" => {"ext" => "webm", "format" => "DASH audio", "acodec" => "opus", "abr" => 70},
"251" => {"ext" => "webm", "format" => "DASH audio", "acodec" => "opus", "abr" => 160},
}
2018-08-05 02:00:44 +05:30
class Video
property player_json : JSON::Any?
2018-08-05 02:00:44 +05:30
module HTTPParamConverter
def self.from_rs(rs)
HTTP::Params.parse(rs.read(String))
end
end
2018-08-05 09:37:38 +05:30
def fmt_stream(decrypt_function)
streams = [] of HTTP::Params
self.info["url_encoded_fmt_stream_map"].split(",") do |string|
if !string.empty?
streams << HTTP::Params.parse(string)
end
end
streams.each { |s| s.add("label", "#{s["quality"]} - #{s["type"].split(";")[0].split("/")[1]}") }
streams = streams.uniq { |s| s["label"] }
2018-10-02 05:31:44 +05:30
if self.info["region"]?
streams.each do |fmt|
fmt["url"] += "&region=" + self.info["region"]
end
end
2018-08-05 09:37:38 +05:30
if streams[0]? && streams[0]["s"]?
streams.each do |fmt|
fmt["url"] += "&signature=" + decrypt_signature(fmt["s"], decrypt_function)
end
end
return streams
end
def adaptive_fmts(decrypt_function)
adaptive_fmts = [] of HTTP::Params
2018-09-15 20:55:43 +05:30
2018-08-05 09:37:38 +05:30
if self.info.has_key?("adaptive_fmts")
self.info["adaptive_fmts"].split(",") do |string|
adaptive_fmts << HTTP::Params.parse(string)
end
elsif self.info.has_key?("dashmpd")
client = make_client(YT_URL)
response = client.get(self.info["dashmpd"])
document = XML.parse_html(response.body)
document.xpath_nodes(%q(//adaptationset)).each do |adaptation_set|
mime_type = adaptation_set["mimetype"]
document.xpath_nodes(%q(.//representation)).each do |representation|
codecs = representation["codecs"]
itag = representation["id"]
bandwidth = representation["bandwidth"]
url = representation.xpath_node(%q(.//baseurl)).not_nil!.content
clen = url.match(/clen\/(?<clen>\d+)/).try &.["clen"]
clen ||= "0"
2018-09-15 19:26:47 +05:30
lmt = url.match(/lmt\/(?<lmt>\d+)/).try &.["lmt"]
lmt ||= "#{((Time.now + 1.hour).epoch_f.to_f64 * 1000000).to_i64}"
segment_list = representation.xpath_node(%q(.//segmentlist)).not_nil!
2018-09-15 19:26:47 +05:30
init = segment_list.xpath_node(%q(.//initialization))
# TODO: Replace with sane defaults when byteranges are absent
2018-09-15 20:55:43 +05:30
if init && !init["sourceurl"].starts_with? "sq"
2018-09-15 19:26:47 +05:30
init = init["sourceurl"].lchop("range/")
index = segment_list.xpath_node(%q(.//segmenturl)).not_nil!["media"]
index = index.lchop("range/")
index = "#{init.split("-")[1].to_i + 1}-#{index.split("-")[0].to_i}"
2018-09-15 19:26:47 +05:30
else
init = "0-0"
index = "1-1"
end
params = {
"type" => ["#{mime_type}; codecs=\"#{codecs}\""],
"url" => [url],
"projection_type" => ["1"],
"index" => [index],
"init" => [init],
"xtags" => [] of String,
"lmt" => [lmt],
"clen" => [clen],
"bitrate" => [bandwidth],
"itag" => [itag],
}
if mime_type == "video/mp4"
width = representation["width"]?
height = representation["height"]?
fps = representation["framerate"]?
metadata = itag_to_metadata?(itag)
if metadata
width ||= metadata["width"]?
height ||= metadata["height"]?
fps ||= metadata["fps"]?
end
if width && height
params["size"] = ["#{width}x#{height}"]
end
if width
params["quality_label"] = ["#{height}p"]
end
end
adaptive_fmts << HTTP::Params.new(params)
end
end
2018-08-05 09:37:38 +05:30
end
2018-10-02 05:31:44 +05:30
if self.info["region"]?
adaptive_fmts.each do |fmt|
fmt["url"] += "&region=" + self.info["region"]
end
end
2018-08-05 09:37:38 +05:30
if adaptive_fmts[0]? && adaptive_fmts[0]["s"]?
adaptive_fmts.each do |fmt|
fmt["url"] += "&signature=" + decrypt_signature(fmt["s"], decrypt_function)
end
end
return adaptive_fmts
end
2018-08-07 22:09:56 +05:30
def video_streams(adaptive_fmts)
video_streams = adaptive_fmts.compact_map { |s| s["type"].starts_with?("video") ? s : nil }
return video_streams
end
2018-08-05 09:37:38 +05:30
def audio_streams(adaptive_fmts)
audio_streams = adaptive_fmts.compact_map { |s| s["type"].starts_with?("audio") ? s : nil }
audio_streams.sort_by! { |s| s["bitrate"].to_i }.reverse!
audio_streams.each do |stream|
stream["bitrate"] = (stream["bitrate"].to_f64/1000).to_i.to_s
end
return audio_streams
end
def player_response
if !@player_json
@player_json = JSON.parse(@info["player_response"])
end
2018-08-05 09:37:38 +05:30
return @player_json.not_nil!
end
2018-10-16 21:45:14 +05:30
def paid
reason = self.player_response["playabilityStatus"]?.try &.["reason"]?
if reason == "This video requires payment to watch."
paid = true
else
paid = false
end
return paid
end
def premium
premium = self.player_response.to_s.includes? "Get YouTube without the ads."
return premium
end
def captions
2018-08-07 04:55:25 +05:30
captions = [] of Caption
2018-08-05 09:37:38 +05:30
if player_response["captions"]?
caption_list = player_response["captions"]["playerCaptionsTracklistRenderer"]["captionTracks"]?.try &.as_a
caption_list ||= [] of JSON::Any
2018-08-07 04:55:25 +05:30
caption_list.each do |caption|
caption = Caption.from_json(caption.to_json)
caption.name.simpleText = caption.name.simpleText.split(" - ")[0]
captions << caption
end
2018-08-05 09:37:38 +05:30
end
return captions
end
def short_description
description = self.description.gsub("<br>", " ")
description = description.gsub("<br/>", " ")
description = XML.parse_html(description).content[0..200].gsub('"', "&quot;").gsub("\n", " ").strip(" ")
if description.empty?
description = " "
end
return description
end
2018-08-05 02:00:44 +05:30
add_mapping({
id: String,
info: {
type: HTTP::Params,
default: HTTP::Params.parse(""),
converter: Video::HTTPParamConverter,
},
updated: Time,
title: String,
views: Int64,
likes: Int32,
dislikes: Int32,
wilson_score: Float64,
published: Time,
description: String,
language: String?,
author: String,
ucid: String,
allowed_regions: Array(String),
is_family_friendly: Bool,
genre: String,
2018-09-10 01:04:16 +05:30
genre_url: String,
license: String,
sub_count_text: String,
author_thumbnail: {
2018-09-10 01:17:26 +05:30
type: String,
default: "",
2018-09-10 01:17:26 +05:30
},
2018-08-05 02:00:44 +05:30
})
end
2018-08-07 04:55:25 +05:30
class Caption
JSON.mapping(
name: CaptionName,
baseUrl: String,
languageCode: String
)
end
class CaptionName
JSON.mapping(
simpleText: String,
)
end
class VideoRedirect < Exception
end
2018-09-26 04:37:00 +05:30
def get_video(id, db, proxies = {} of String => Array({ip: String, port: Int32}), refresh = true)
2018-08-05 02:00:44 +05:30
if db.query_one?("SELECT EXISTS (SELECT true FROM videos WHERE id = $1)", id, as: Bool)
video = db.query_one("SELECT * FROM videos WHERE id = $1", id, as: Video)
2018-09-10 01:11:29 +05:30
# If record was last updated over 10 minutes ago, refresh (expire param in response lasts for 6 hours)
if refresh && Time.now - video.updated > 10.minutes
2018-08-05 02:00:44 +05:30
begin
2018-09-26 04:26:59 +05:30
video = fetch_video(id, proxies)
2018-08-05 02:00:44 +05:30
video_array = video.to_a
2018-09-04 20:20:19 +05:30
2018-08-05 02:00:44 +05:30
args = arg_array(video_array[1..-1], 2)
db.exec("UPDATE videos SET (info,updated,title,views,likes,dislikes,wilson_score,\
2018-10-14 06:33:48 +05:30
published,description,language,author,ucid,allowed_regions,is_family_friendly,\
genre,genre_url,license,sub_count_text,author_thumbnail)\
= (#{args}) WHERE id = $1", video_array)
2018-08-05 02:00:44 +05:30
rescue ex
db.exec("DELETE FROM videos * WHERE id = $1", id)
raise ex
end
end
else
2018-09-26 04:26:59 +05:30
video = fetch_video(id, proxies)
2018-08-05 02:00:44 +05:30
video_array = video.to_a
2018-09-04 20:20:19 +05:30
2018-08-05 02:00:44 +05:30
args = arg_array(video_array)
db.exec("INSERT INTO videos VALUES (#{args}) ON CONFLICT (id) DO NOTHING", video_array)
end
return video
end
2018-09-26 04:37:00 +05:30
def fetch_video(id, proxies)
html_channel = Channel(XML::Node | String).new
2018-08-05 02:00:44 +05:30
info_channel = Channel(HTTP::Params).new
spawn do
client = make_client(YT_URL)
2018-09-26 04:12:17 +05:30
html = client.get("/watch?v=#{id}&bpctr=#{Time.new.epoch + 2000}&gl=US&hl=en&disable_polymer=1")
2018-08-05 02:00:44 +05:30
if md = html.headers["location"]?.try &.match(/v=(?<id>[a-zA-Z0-9_-]{11})/)
next html_channel.send(md["id"])
end
html = XML.parse_html(html.body)
2018-08-05 02:00:44 +05:30
html_channel.send(html)
end
spawn do
client = make_client(YT_URL)
info = client.get("/get_video_info?video_id=#{id}&el=detailpage&ps=default&eurl=&gl=US&hl=en&disable_polymer=1")
info = HTTP::Params.parse(info.body)
if info["reason"]?
info = client.get("/get_video_info?video_id=#{id}&ps=default&eurl=&gl=US&hl=en&disable_polymer=1")
info = HTTP::Params.parse(info.body)
end
info_channel.send(info)
end
html = html_channel.receive
if html.as?(String)
raise VideoRedirect.new("#{html.as(String)}")
end
html = html.as(XML::Node)
2018-08-05 02:00:44 +05:30
info = info_channel.receive
2018-08-13 19:47:28 +05:30
if info["reason"]? && info["reason"].includes? "your country"
2018-10-02 05:31:44 +05:30
bypass_channel = Channel(HTTPProxy | Nil).new
2018-08-13 19:47:28 +05:30
2018-09-26 04:26:59 +05:30
proxies.each do |region, list|
2018-08-13 19:47:28 +05:30
spawn do
2018-10-03 21:08:07 +05:30
info = HTTP::Params.new({
"reason" => [info["reason"]],
})
2018-10-02 05:31:44 +05:30
list.each do |proxy|
begin
client = HTTPClient.new(YT_URL)
client.read_timeout = 10.seconds
client.connect_timeout = 10.seconds
proxy = HTTPProxy.new(proxy_host: proxy[:ip], proxy_port: proxy[:port])
client.set_proxy(proxy)
info = HTTP::Params.parse(client.get("/get_video_info?video_id=#{id}&ps=default&eurl=&gl=US&hl=en&disable_polymer=1").body)
if !info["reason"]?
2018-10-02 05:31:44 +05:30
bypass_channel.send(proxy)
2018-10-14 20:23:40 +05:30
break
2018-10-02 05:31:44 +05:30
end
rescue ex
2018-08-13 19:47:28 +05:30
end
end
2018-10-03 21:08:07 +05:30
# If none of the proxies we tried returned a valid response
if info["reason"]?
bypass_channel.send(nil)
end
2018-08-13 19:47:28 +05:30
end
end
2018-09-26 04:37:00 +05:30
proxies.size.times do
2018-10-02 05:31:44 +05:30
proxy = bypass_channel.receive
if proxy
begin
client = HTTPClient.new(YT_URL)
client.read_timeout = 10.seconds
client.connect_timeout = 10.seconds
client.set_proxy(proxy)
2018-10-02 05:31:44 +05:30
html = XML.parse_html(client.get("/watch?v=#{id}&bpctr=#{Time.new.epoch + 2000}&gl=US&hl=en&disable_polymer=1").body)
info = HTTP::Params.parse(client.get("/get_video_info?video_id=#{id}&el=detailpage&ps=default&eurl=&gl=US&hl=en&disable_polymer=1").body)
2018-10-02 05:31:44 +05:30
if info["reason"]?
info = HTTP::Params.parse(client.get("/get_video_info?video_id=#{id}&ps=default&eurl=&gl=US&hl=en&disable_polymer=1").body)
end
2018-10-02 05:31:44 +05:30
proxy = {ip: proxy.proxy_host, port: proxy.proxy_port}
region = proxies.select { |region, list| list.includes? proxy }
if !region.empty?
info["region"] = region.keys[0]
end
2018-10-02 06:32:14 +05:30
break
rescue ex
2018-10-02 05:31:44 +05:30
end
2018-08-13 19:47:28 +05:30
end
end
end
2018-08-05 02:00:44 +05:30
if info["reason"]?
raise info["reason"]
end
title = info["title"]
views = info["view_count"].to_i64
author = info["author"]
ucid = info["ucid"]
likes = html.xpath_node(%q(//button[@title="I like this"]/span))
likes = likes.try &.content.delete(",").try &.to_i
likes ||= 0
dislikes = html.xpath_node(%q(//button[@title="I dislike this"]/span))
dislikes = dislikes.try &.content.delete(",").try &.to_i
dislikes ||= 0
description = html.xpath_node(%q(//p[@id="eow-description"]))
description = description ? description.to_xml : ""
wilson_score = ci_lower_bound(likes, likes + dislikes)
published = html.xpath_node(%q(//meta[@itemprop="datePublished"])).not_nil!["content"]
published = Time.parse(published, "%Y-%m-%d", Time::Location.local)
allowed_regions = html.xpath_node(%q(//meta[@itemprop="regionsAllowed"])).try &.["content"].split(",")
allowed_regions ||= [] of String
is_family_friendly = html.xpath_node(%q(//meta[@itemprop="isFamilyFriendly"])).try &.["content"] == "True"
is_family_friendly ||= true
2018-09-04 20:20:19 +05:30
2018-08-05 02:00:44 +05:30
genre = html.xpath_node(%q(//meta[@itemprop="genre"])).not_nil!["content"]
genre_url = html.xpath_node(%(//a[text()="#{genre}"])).try &.["href"]
case genre
when "Movies"
genre_url = "/channel/UClgRkhTL3_hImCAmdLfDE4g"
when "Education"
# Education channel is linked but does not exist
# genre_url = "/channel/UC3yA8nDwraeOfnYfBWun83g"
genre_url = ""
end
genre_url ||= ""
2018-08-05 02:00:44 +05:30
2018-09-10 01:17:26 +05:30
license = html.xpath_node(%q(//h4[contains(text(),"License")]/parent::*/ul/li))
if license
license = license.content
else
license = ""
end
sub_count_text = html.xpath_node(%q(//span[contains(@class, "yt-subscriber-count")]))
if sub_count_text
sub_count_text = sub_count_text["title"]
else
sub_count_text = "0"
2018-09-10 01:17:26 +05:30
end
author_thumbnail = html.xpath_node(%(//img[@alt="#{author}"]))
if author_thumbnail
author_thumbnail = author_thumbnail["data-thumb"]
else
author_thumbnail = ""
end
2018-08-05 02:00:44 +05:30
video = Video.new(id, info, Time.now, title, views, likes, dislikes, wilson_score, published, description,
nil, author, ucid, allowed_regions, is_family_friendly, genre, genre_url, license, sub_count_text, author_thumbnail)
2018-08-05 02:00:44 +05:30
return video
end
2018-08-12 19:54:59 +05:30
def itag_to_metadata?(itag : String)
2018-08-12 20:04:26 +05:30
return VIDEO_FORMATS[itag]?
2018-08-05 02:00:44 +05:30
end
2018-08-05 09:37:38 +05:30
def process_video_params(query, preferences)
autoplay = query["autoplay"]?.try &.to_i?
preferred_captions = query["subtitles"]?.try &.split(",").map { |a| a.downcase }
quality = query["quality"]?
speed = query["speed"]?.try &.to_f?
2018-08-05 09:37:38 +05:30
video_loop = query["loop"]?.try &.to_i?
volume = query["volume"]?.try &.to_i?
2018-08-05 09:37:38 +05:30
if preferences
autoplay ||= preferences.autoplay.to_unsafe
preferred_captions ||= preferences.captions
quality ||= preferences.quality
speed ||= preferences.speed
2018-08-05 09:37:38 +05:30
video_loop ||= preferences.video_loop.to_unsafe
volume ||= preferences.volume
2018-08-05 09:37:38 +05:30
end
autoplay ||= 0
preferred_captions ||= [] of String
quality ||= "hd720"
speed ||= 1
2018-08-05 09:37:38 +05:30
video_loop ||= 0
volume ||= 100
autoplay = autoplay == 1
2018-08-05 09:37:38 +05:30
video_loop = video_loop == 1
if query["t"]?
video_start = decode_time(query["t"])
end
video_start ||= 0
2018-08-31 06:55:43 +05:30
if query["time_continue"]?
2018-08-31 07:34:41 +05:30
video_start = decode_time(query["time_continue"])
2018-08-05 23:05:33 +05:30
end
video_start ||= 0
if query["start"]?
video_start = decode_time(query["start"])
end
2018-08-05 09:37:38 +05:30
if query["end"]?
video_end = decode_time(query["end"])
end
video_end ||= -1
if query["listen"]? && (query["listen"] == "true" || query["listen"] == "1")
listen = true
end
listen ||= false
raw = query["raw"]?.try &.to_i?
raw ||= 0
raw = raw == 1
controls = query["controls"]?.try &.to_i?
controls ||= 1
controls = controls == 1
params = {
autoplay: autoplay,
controls: controls,
listen: listen,
preferred_captions: preferred_captions,
quality: quality,
raw: raw,
speed: speed,
video_end: video_end,
video_loop: video_loop,
video_start: video_start,
volume: volume,
}
return params
2018-08-05 09:37:38 +05:30
end
2018-08-10 19:20:25 +05:30
def generate_thumbnails(json, id)
json.array do
VIDEO_THUMBNAILS.each do |thumbnail|
2018-08-10 19:20:25 +05:30
json.object do
json.field "quality", thumbnail[:name]
2018-09-21 20:41:04 +05:30
json.field "url", "https://#{thumbnail[:host]}/vi/#{id}/#{thumbnail["url"]}.jpg"
json.field "width", thumbnail[:width]
json.field "height", thumbnail[:height]
2018-08-10 19:20:25 +05:30
end
end
end
end