yep scraper fix, removed image and news

This commit is contained in:
2026-04-26 05:08:15 -04:00
parent b1f5974e40
commit a54f212550
3 changed files with 200 additions and 503 deletions

View File

@@ -14,227 +14,202 @@ class yep{
public function getfilters($page){
return [
"country" => [
"display" => "Country",
"lang" => [
"display" => "Language",
"option" => [
"all" => "All regions",
"af" => "Afghanistan",
"al" => "Albania",
"dz" => "Algeria",
"as" => "American Samoa",
"ad" => "Andorra",
"ao" => "Angola",
"ai" => "Anguilla",
"ag" => "Antigua and Barbuda",
"ar" => "Argentina",
"am" => "Armenia",
"aw" => "Aruba",
"au" => "Australia",
"at" => "Austria",
"az" => "Azerbaijan",
"bs" => "Bahamas",
"bh" => "Bahrain",
"bd" => "Bangladesh",
"bb" => "Barbados",
"by" => "Belarus",
"be" => "Belgium",
"bz" => "Belize",
"bj" => "Benin",
"bt" => "Bhutan",
"bo" => "Bolivia",
"ba" => "Bosnia and Herzegovina",
"bw" => "Botswana",
"br" => "Brazil",
"bn" => "Brunei Darussalam",
"bg" => "Bulgaria",
"bf" => "Burkina Faso",
"bi" => "Burundi",
"cv" => "Cabo Verde",
"kh" => "Cambodia",
"cm" => "Cameroon",
"ca" => "Canada",
"ky" => "Cayman Islands",
"cf" => "Central African Republic",
"td" => "Chad",
"cl" => "Chile",
"cn" => "China",
"co" => "Colombia",
"cg" => "Congo",
"cd" => "Congo, Democratic Republic",
"ck" => "Cook Islands",
"cr" => "Costa Rica",
"hr" => "Croatia",
"cu" => "Cuba",
"cy" => "Cyprus",
"cz" => "Czechia",
"ci" => "Côte d'Ivoire",
"dk" => "Denmark",
"dj" => "Djibouti",
"dm" => "Dominica",
"do" => "Dominican Republic",
"ec" => "Ecuador",
"eg" => "Egypt",
"sv" => "El Salvador",
"gq" => "Equatorial Guinea",
"ee" => "Estonia",
"et" => "Ethiopia",
"fo" => "Faroe Islands",
"fj" => "Fiji",
"fi" => "Finland",
"fr" => "France",
"gf" => "French Guiana",
"pf" => "French Polynesia",
"ga" => "Gabon",
"gm" => "Gambia",
"ge" => "Georgia",
"de" => "Germany",
"gh" => "Ghana",
"gi" => "Gibraltar",
"gr" => "Greece",
"gl" => "Greenland",
"gd" => "Grenada",
"gp" => "Guadeloupe",
"gu" => "Guam",
"gt" => "Guatemala",
"gg" => "Guernsey",
"gn" => "Guinea",
"gy" => "Guyana",
"ht" => "Haiti",
"hn" => "Honduras",
"hk" => "Hong Kong",
"hu" => "Hungary",
"is" => "Iceland",
"in" => "India",
"id" => "Indonesia",
"iq" => "Iraq",
"ie" => "Ireland",
"im" => "Isle of Man",
"il" => "Israel",
"it" => "Italy",
"jm" => "Jamaica",
"jp" => "Japan",
"je" => "Jersey",
"jo" => "Jordan",
"kz" => "Kazakhstan",
"ke" => "Kenya",
"ki" => "Kiribati",
"kw" => "Kuwait",
"kg" => "Kyrgyzstan",
"la" => "Lao People's Democratic Republic",
"lv" => "Latvia",
"lb" => "Lebanon",
"ls" => "Lesotho",
"ly" => "Libya",
"li" => "Liechtenstein",
"lt" => "Lithuania",
"lu" => "Luxembourg",
"mk" => "Macedonia",
"mg" => "Madagascar",
"mw" => "Malawi",
"my" => "Malaysia",
"mv" => "Maldives",
"ml" => "Mali",
"mt" => "Malta",
"mq" => "Martinique",
"mr" => "Mauritania",
"mu" => "Mauritius",
"yt" => "Mayotte",
"mx" => "Mexico",
"fm" => "Micronesia, Federated States of",
"md" => "Moldova",
"mc" => "Monaco",
"mn" => "Mongolia",
"me" => "Montenegro",
"ms" => "Montserrat",
"ma" => "Morocco",
"mz" => "Mozambique",
"mm" => "Myanmar",
"na" => "Namibia",
"nr" => "Nauru",
"np" => "Nepal",
"nl" => "Netherlands",
"nc" => "New Caledonia",
"nz" => "New Zealand",
"ni" => "Nicaragua",
"ne" => "Niger",
"ng" => "Nigeria",
"nu" => "Niue",
"no" => "Norway",
"om" => "Oman",
"pk" => "Pakistan",
"ps" => "Palestine, State of",
"pa" => "Panama",
"pg" => "Papua New Guinea",
"py" => "Paraguay",
"pe" => "Peru",
"ph" => "Philippines",
"pn" => "Pitcairn",
"pl" => "Poland",
"pt" => "Portugal",
"pr" => "Puerto Rico",
"qa" => "Qatar",
"ro" => "Romania",
"ru" => "Russian Federation",
"rw" => "Rwanda",
"re" => "Réunion",
"sh" => "Saint Helena",
"kn" => "Saint Kitts and Nevis",
"lc" => "Saint Lucia",
"vc" => "Saint Vincent and the Grenadines",
"ws" => "Samoa",
"sm" => "San Marino",
"st" => "Sao Tome and Principe",
"sa" => "Saudi Arabia",
"sn" => "Senegal",
"rs" => "Serbia",
"sc" => "Seychelles",
"sl" => "Sierra Leone",
"sg" => "Singapore",
"sk" => "Slovakia",
"si" => "Slovenia",
"sb" => "Solomon Islands",
"so" => "Somalia",
"kr" => "Sourth Korea",
"za" => "South Africa",
"es" => "Spain",
"lk" => "Sri Lanka",
"sr" => "Suriname",
"se" => "Sweden",
"ch" => "Switzerland",
"tw" => "Taiwan",
"tj" => "Tajikistan",
"tz" => "Tanzania",
"th" => "Thailand",
"tl" => "Timor-Leste",
"tg" => "Togo",
"tk" => "Tokelau",
"any" => "Any language",
"aa" => "Afar",
"ab" => "Abkhazian",
"ae" => "Avestan",
"af" => "Afrikaans",
"ak" => "Akan",
"am" => "Amharic",
"an" => "Aragonese",
"ar" => "Arabic",
"as" => "Assamese",
"av" => "Avaric",
"ay" => "Aymara",
"az" => "Azerbaijani",
"ba" => "Bashkir",
"be" => "Belarusian",
"bg" => "Bulgarian",
"bh" => "Bihari",
"bi" => "Bislama",
"bm" => "Bambara",
"bn" => "Bengali",
"bo" => "Tibetan",
"br" => "Breton",
"bs" => "Bosnian",
"ca" => "Catalan",
"ce" => "Chechen",
"ch" => "Chamorro",
"co" => "Corsican",
"cr" => "Cree",
"cs" => "Czech",
"cu" => "Church Slavic",
"cv" => "Chuvash",
"cy" => "Welsh",
"da" => "Danish",
"de" => "German",
"dv" => "Divehi",
"dz" => "Dzongkha",
"ee" => "Ewe",
"el" => "Greek",
"en" => "English",
"eo" => "Esperanto",
"es" => "Spanish",
"et" => "Estonian",
"eu" => "Basque",
"fa" => "Persian",
"ff" => "Fulah",
"fi" => "Finnish",
"fj" => "Fijian",
"fo" => "Faroese",
"fr" => "French",
"fy" => "Western Frisian",
"ga" => "Irish",
"gd" => "Scottish Gaelic",
"gl" => "Galician",
"gn" => "Guarani",
"gu" => "Gujarati",
"gv" => "Manx",
"ha" => "Hausa",
"he" => "Hebrew",
"hi" => "Hindi",
"ho" => "Hiri Motu",
"hr" => "Croatian",
"ht" => "Haitian",
"hu" => "Hungarian",
"hy" => "Armenian",
"hz" => "Herero",
"ia" => "Interlingua",
"id" => "Indonesian",
"ie" => "Interlingue",
"ig" => "Igbo",
"ii" => "Sichuan Yi",
"ik" => "Inupiaq",
"io" => "Ido",
"is" => "Icelandic",
"it" => "Italian",
"iu" => "Inuktitut",
"ja" => "Japanese",
"jv" => "Javanese",
"ka" => "Georgian",
"kg" => "Kongo",
"ki" => "Kikuyu",
"kj" => "Kuanyama",
"kk" => "Kazakh",
"kl" => "Kalaallisut",
"km" => "Central Khmer",
"kn" => "Kannada",
"ko" => "Korean",
"kr" => "Kanuri",
"ks" => "Kashmiri",
"ku" => "Kurdish",
"kv" => "Komi",
"kw" => "Cornish",
"ky" => "Kyrgyz",
"la" => "Latin",
"lb" => "Luxembourgish",
"lg" => "Ganda",
"li" => "Limburgish",
"ln" => "Lingala",
"lo" => "Lao",
"lt" => "Lithuanian",
"lu" => "Luba-Katanga",
"lv" => "Latvian",
"mg" => "Malagasy",
"mh" => "Marshallese",
"mi" => "Maori",
"mk" => "Macedonian",
"ml" => "Malayalam",
"mn" => "Mongolian",
"mr" => "Marathi",
"ms" => "Malay",
"mt" => "Maltese",
"my" => "Burmese",
"na" => "Nauru",
"nb" => "Norwegian Bokmål",
"nd" => "North Ndebele",
"ne" => "Nepali",
"ng" => "Ndonga",
"nl" => "Dutch",
"nn" => "Norwegian Nynorsk",
"no" => "Norwegian",
"nr" => "South Ndebele",
"nv" => "Navajo",
"ny" => "Chichewa",
"oc" => "Occitan",
"oj" => "Ojibwa",
"om" => "Oromo",
"or" => "Oriya",
"os" => "Ossetian",
"pa" => "Punjabi",
"pi" => "Pali",
"pl" => "Polish",
"ps" => "Pashto",
"pt" => "Portuguese",
"qu" => "Quechua",
"rm" => "Romansh",
"rn" => "Rundi",
"ro" => "Romanian",
"ru" => "Russian",
"rw" => "Kinyarwanda",
"sa" => "Sanskrit",
"sc" => "Sardinian",
"sd" => "Sindhi",
"se" => "Northern Sami",
"sg" => "Sango",
"si" => "Sinhala",
"sk" => "Slovak",
"sl" => "Slovenian",
"sm" => "Samoan",
"sn" => "Shona",
"so" => "Somali",
"sq" => "Albanian",
"sr" => "Serbian",
"ss" => "Swati",
"st" => "Southern Sotho",
"su" => "Sundanese",
"sv" => "Swedish",
"sw" => "Swahili",
"ta" => "Tamil",
"te" => "Telugu",
"tg" => "Tajik",
"th" => "Thai",
"ti" => "Tigrinya",
"tk" => "Turkmen",
"tl" => "Tagalog",
"tn" => "Tswana",
"to" => "Tonga",
"tt" => "Trinidad and Tobago",
"tn" => "Tunisia",
"tr" => "Turkey",
"tm" => "Turkmenistan",
"ug" => "Uganda",
"ua" => "Ukraine",
"ae" => "United Arab Emirates",
"gb" => "United Kingdom",
"us" => "United States",
"uy" => "Uruguay",
"uz" => "Uzbekistan",
"vu" => "Vanuatu",
"ve" => "Venezuela",
"vn" => "Vietnam",
"vg" => "Virgin Islands, British",
"vi" => "Virgin Islands, U.S.",
"ye" => "Yemen",
"zm" => "Zambia",
"zw" => "Zimbabwe"
"tr" => "Turkish",
"ts" => "Tsonga",
"tt" => "Tatar",
"tw" => "Twi",
"ty" => "Tahitian",
"ug" => "Uyghur",
"uk" => "Ukrainian",
"ur" => "Urdu",
"uz" => "Uzbek",
"ve" => "Venda",
"vi" => "Vietnamese",
"vo" => "Volapük",
"wa" => "Walloon",
"wo" => "Wolof",
"xh" => "Xhosa",
"yi" => "Yiddish",
"yo" => "Yoruba",
"za" => "Zhuang",
"zh" => "Chinese",
"zh-cn" => "Chinese (Simplified)",
"zh-tw" => "Chinese (Traditional)",
"zu" => "Zulu"
]
],
"nsfw" => [
"display" => "NSFW",
"option" => [
"yes" => "Yes",
"maybe" => "Maybe",
"no" => "No"
]
]
@@ -301,16 +276,6 @@ class yep{
throw new Exception("Search term is empty!");
}
$country = $get["country"];
$nsfw = $get["nsfw"];
switch($nsfw){
case "yes": $nsfw = "off"; break;
case "maybe": $nsfw = "moderate"; break;
case "no": $nsfw = "strict"; break;
}
$out = [
"status" => "ok",
"spelling" => [
@@ -327,22 +292,23 @@ class yep{
"related" => []
];
// parse filters
$filters = [
"limit" => 100, // wwwwwwwwwwwwwww
"query" => $search,
];
if($get["nsfw"] == "no"){ $filters["safeSearch"] = "moderate"; }
if($get["lang"] != "any"){ $filters["hl"] = $get["lang"]; }
try{
// https://api.yep.com/fs/2/search?client=web&gl=CA&no_correct=false&q=undefined+variable+javascript&safeSearch=off&type=web
// https://api.yep.com/fs/2/search?limit=20&query=asmr
$json =
$this->get(
$this->backend->get_ip(),
"https://api.yep.com/fs/2/search",
[
"client" => "web",
"gl" => $country == "all" ? $country : strtoupper($country),
"limit" => "99999",
"no_correct" => "false",
"q" => $search,
"safeSearch" => $nsfw,
"type" => "web"
]
$filters
);
}catch(Exception $error){
@@ -408,7 +374,7 @@ class yep{
)
),
"url" => $item["url"],
"date" => strtotime($item["first_seen"]),
"date" => null,
"type" => "web",
"thumb" => [
"url" => null,
@@ -422,265 +388,6 @@ class yep{
}
}
if(isset($json[1]["featured_news"])){
foreach($json[1]["featured_news"] as $news){
$out["news"][] = [
"title" => $news["title"],
"description" =>
$this->titledots(
strip_tags(
html_entity_decode(
$news["snippet"]
)
)
),
"date" => strtotime($news["first_seen"]),
"thumb" =>
isset($news["img"]) ?
[
"url" => $this->unshiturl($news["img"]),
"ratio" => "16:9"
] :
[
"url" => null,
"ratio" => null
],
"url" => $news["url"]
];
}
}
if(isset($json[1]["featured_images"])){
foreach($json[1]["featured_images"] as $image){
if(
$image["width"] !== 0 &&
$image["height"] !== 0
){
$thumb_width = $image["width"] >= 260 ? 260 : $image["width"];
$thumb_height = ceil($image["height"] * ($thumb_width / $image["width"]));
$width = $image["width"];
$height = $image["height"];
}else{
$thumb_width = null;
$thumb_height = null;
$width = null;
$height = null;
}
$out["image"][] = [
"title" => $image["title"],
"source" => [
[
"url" => $image["image_id"],
"width" => $width,
"height" => $height
],
[
"url" => $image["src"],
"width" => $thumb_width,
"height" => $thumb_height
]
],
"url" => $image["host_page"]
];
}
}
return $out;
}
public function image($get){
$search = $get["s"];
if(strlen($search) === 0){
throw new Exception("Search term is empty!");
}
$country = $get["country"];
$nsfw = $get["nsfw"];
switch($nsfw){
case "yes": $nsfw = "off"; break;
case "maybe": $nsfw = "moderate"; break;
case "no": $nsfw = "strict"; break;
}
$out = [
"status" => "ok",
"npt" => null,
"image" => []
];
try{
$json =
$this->get(
$this->backend->get_ip(), // no nextpage!
"https://api.yep.com/fs/2/search",
[
"client" => "web",
"gl" => $country == "all" ? $country : strtoupper($country),
"no_correct" => "false",
"q" => $search,
"safeSearch" => $nsfw,
"type" => "images"
]
);
}catch(Exception $error){
throw new Exception("Failed to fetch JSON");
}
$this->detect_cf($json);
$json = json_decode($json, true);
if($json === null){
throw new Exception("Failed to decode JSON");
}
if(isset($json[1]["results"])){
foreach($json[1]["results"] as $item){
if(
$item["width"] !== 0 &&
$item["height"] !== 0
){
$thumb_width = $item["width"] >= 260 ? 260 : $item["width"];
$thumb_height = ceil($item["height"] * ($thumb_width / $item["width"]));
$width = $item["width"];
$height = $item["height"];
}else{
$thumb_width = null;
$thumb_height = null;
$width = null;
$height = null;
}
$out["image"][] = [
"title" => $item["title"],
"source" => [
[
"url" => $item["image_id"],
"width" => $width,
"height" => $height
],
[
"url" => $item["src"],
"width" => $thumb_width,
"height" => $thumb_height
]
],
"url" => $item["host_page"]
];
}
}
return $out;
}
public function news($get){
$search = $get["s"];
if(strlen($search) === 0){
throw new Exception("Search term is empty!");
}
$country = $get["country"];
$nsfw = $get["nsfw"];
switch($nsfw){
case "yes": $nsfw = "off"; break;
case "maybe": $nsfw = "moderate"; break;
case "no": $nsfw = "strict"; break;
}
$out = [
"status" => "ok",
"npt" => null,
"news" => []
];
try{
// https://api.yep.com/fs/2/search?client=web&gl=CA&no_correct=false&q=undefined+variable+javascript&safeSearch=off&type=web
$json =
$this->get(
$this->backend->get_ip(),
"https://api.yep.com/fs/2/search",
[
"client" => "web",
"gl" => $country == "all" ? $country : strtoupper($country),
"limit" => "99999",
"no_correct" => "false",
"q" => $search,
"safeSearch" => $nsfw,
"type" => "news"
]
);
}catch(Exception $error){
throw new Exception("Failed to fetch JSON");
}
$this->detect_cf($json);
$json = json_decode($json, true);
//$json = json_decode(file_get_contents("scraper/yep.json"), true);
if($json === null){
throw new Exception("Failed to decode JSON");
}
if(isset($json[1]["results"])){
foreach($json[1]["results"] as $item){
$out["news"][] = [
"title" => $item["title"],
"author" => null,
"description" =>
$this->titledots(
strip_tags(
html_entity_decode(
$item["snippet"]
)
)
),
"date" => strtotime($item["first_seen"]),
"thumb" =>
isset($item["img"]) ?
[
"url" => $this->unshiturl($item["img"]),
"ratio" => "16:9"
] :
[
"url" => null,
"ratio" => null
],
"url" => $item["url"]
];
}
}
return $out;
}