├── isitagirl ├── pigenavne.csv ├── pigenavne-updated.csv ├── is_it_a_girl.php └── unisexnavne.csv ├── .gitattributes ├── index.php ├── OriginalFiler ├── index.php ├── laerere.php ├── skema.php └── lectio.php ├── README.md ├── .gitignore ├── lectio.php └── simple_html_dom.php /isitagirl/pigenavne.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HSPDev/lectio/HEAD/isitagirl/pigenavne.csv -------------------------------------------------------------------------------- /isitagirl/pigenavne-updated.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HSPDev/lectio/HEAD/isitagirl/pigenavne-updated.csv -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- 1 | # Auto detect text files and perform LF normalization 2 | * text=auto 3 | 4 | # Custom for Visual Studio 5 | *.cs diff=csharp 6 | *.sln merge=union 7 | *.csproj merge=union 8 | *.vbproj merge=union 9 | *.fsproj merge=union 10 | *.dbproj merge=union 11 | 12 | # Standard to msysgit 13 | *.doc diff=astextplain 14 | *.DOC diff=astextplain 15 | *.docx diff=astextplain 16 | *.DOCX diff=astextplain 17 | *.dot diff=astextplain 18 | *.DOT diff=astextplain 19 | *.pdf diff=astextplain 20 | *.PDF diff=astextplain 21 | *.rtf diff=astextplain 22 | *.RTF diff=astextplain 23 | -------------------------------------------------------------------------------- /index.php: -------------------------------------------------------------------------------- 1 | get_elever_fra_gymnasie_sorteret('402'); //Henter alle elever fra Nakskov Gymnasium 13 | 14 | $for_processing = array(); //Til at holde alle pigerne :D 15 | foreach($elever as $klasse=>$klassemedlemmer) 16 | { 17 | foreach ($klassemedlemmer as $elev) { 18 | $fornavn = $g->get_firstname($elev['navn']); //Henter fornavnet 19 | $gender = $g->get_gender($fornavn); //Bruger folkekirkens registre til at finde ud af om dreng eller pige 20 | if($gender == 'pige') 21 | { 22 | $for_processing[] = array( 23 | 'navn' => $elev['navn'], 24 | 'klasse' => $klasse, 25 | 'gender' => $gender 26 | ); 27 | } 28 | } 29 | } 30 | var_dump($for_processing); 31 | ?> -------------------------------------------------------------------------------- /isitagirl/is_it_a_girl.php: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /OriginalFiler/index.php: -------------------------------------------------------------------------------- 1 | load($lectio_html); //Parse HTML 26 | $laerer_objekter = $html->find('td a'); //Søg efter alle lærere 27 | for($i=0; $ilectiocontextcard)>0) 31 | { 32 | //Det er et lærer objekt vi har med at gøre! 33 | $navn = trim(html_entity_decode($l->plaintext)); 34 | $initialer = preg_match("/\((.*)\)/", $navn, $match_data); //Match for parantesen med initialer 35 | $link = $l->href; 36 | $lectio_id = substr($link, strpos($link, 'laererid=')+9); 37 | $laerere[] = array( 38 | 'navn' => $navn, 39 | 'initialer' => $match_data[1], 40 | 'lectio_id' => $lectio_id 41 | ); 42 | } 43 | 44 | } 45 | return $laerere; 46 | } 47 | //Hent lærere ud fra gymnasiekode 48 | function get_laerere($gymnasie_kode) 49 | { 50 | $link_start = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/FindSkema.aspx?type=laerer'; 51 | return get_laerere_fra_side($link_start); 52 | } 53 | $laerere = get_laerere('402'); 54 | var_dump($laerere); 55 | ?> -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | lectio 2 | ====== 3 | Lectio API 4 | This is a free API For Lectio that everybody can use as they will. No guarentees, no expectations. 5 | Most of this is in Danish, because Lectio is a Danish system. Please contact me if you need to 6 | discuss this in English. 7 | 8 | Danish text from here: 9 | 10 | Dette er et simpelt API for Lectio som tillader at hente alle nyttige offentlige data og på sigt 11 | også data når man er logget ind (f.eks. beskeder og vedhæftninger samt fravær). 12 | Der er et lille "underprojekt" som måske egentlig ikke hører så meget hjemme her, 13 | kaldet "isitagirl". Det har sin egen class da det på ingen måde skal kobles tæt 14 | med Lectio da de færreste skal bruge det, men grundet at vi havde lidt sjov 15 | med at trække alle pigerne ud af gymnasiets elevliste så er det inkluderet. 16 | 17 | Selve API'et fungerer som følger. 18 | 19 | Liste over funktioner: 20 | 21 | Alle de her bør sige sig selv: 22 | get_skema_til_elev(gymnasiekode, lectio_id) 23 | get_skema_til_elev_og_uge(gymnasiekode, lectio_id, ugekode) 24 | get_skema_til_laerer(gymnasiekode, laerer_id) 25 | get_skema_til_laerer_og_uge(gymnasiekode, laerer_id, ugekode) 26 | 27 | Disse funktioner hiver elever ud fra et givent gymnasie. 28 | get_elever_fra_gymnasie er den lidt simple version, mens den "sorterede" version 29 | kategoriserer eleverne efter klasse og trækker elev nummer (kursist nummer) med ud. 30 | BEMÆRK at get_elever_fra_gymnasie_sorteret ikke garanterer alfabetisk sortering. 31 | get_elever_fra_gymnasie(gymsiekode) 32 | get_elever_fra_gymnasie_sorteret(gymnasiekode) 33 | 34 | Denne funktion henter alle lærerne ud med navn og initialer samt laerer_id til brug ved andre funktioner 35 | get_laerere(gymnasiekode) 36 | 37 | De her funktioner får du nok ikke brug for, de tillader at hente et skema fra en hvilken som helst URL 38 | man selv konstruerer, samt at hente elever fra en given side hvis man f.eks. kun vil have elever 39 | hvis navn begynder med B. 40 | get_skema(url til skemaet) 41 | get_elever_fra_side(url til elevsiden) 42 | 43 | 44 | Forklaringer på parametre: 45 | "Gymnasiekode" er den talkode hvert gymnasie har. Den kan ses i toppen af url'en når man er på en 46 | vilkårlig side på et gymnasie. I en af de næste commits vil der komme funktioner til at finde disse koder. 47 | Men feks. her er Nakskov Gymnasiums URL: 48 | http://www.lectio.dk/lectio/402/default.aspx 49 | 402 er gymnasiekoden i dette tilfælde. 50 | 51 | "Lectio_id" referer til det ID som Lectio tilegner hver elev. Det er for at adskille fra Elev nummer som 52 | er det tal skolen tildeler hver elev i hver klasse. 53 | 54 | "Ugekode" er ret vigtig. Den skal indsættes som WWYYYY dvs. for uge 11 i år 2013 så er koden 112013 -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | ################# 2 | ## Eclipse 3 | ################# 4 | 5 | *.pydevproject 6 | .project 7 | .metadata 8 | bin/ 9 | tmp/ 10 | *.tmp 11 | *.bak 12 | *.swp 13 | *~.nib 14 | local.properties 15 | .classpath 16 | .settings/ 17 | .loadpath 18 | 19 | # External tool builders 20 | .externalToolBuilders/ 21 | 22 | # Locally stored "Eclipse launch configurations" 23 | *.launch 24 | 25 | # CDT-specific 26 | .cproject 27 | 28 | # PDT-specific 29 | .buildpath 30 | 31 | 32 | ################# 33 | ## Visual Studio 34 | ################# 35 | 36 | ## Ignore Visual Studio temporary files, build results, and 37 | ## files generated by popular Visual Studio add-ons. 38 | 39 | # User-specific files 40 | *.suo 41 | *.user 42 | *.sln.docstates 43 | 44 | # Build results 45 | [Dd]ebug/ 46 | [Rr]elease/ 47 | *_i.c 48 | *_p.c 49 | *.ilk 50 | *.meta 51 | *.obj 52 | *.pch 53 | *.pdb 54 | *.pgc 55 | *.pgd 56 | *.rsp 57 | *.sbr 58 | *.tlb 59 | *.tli 60 | *.tlh 61 | *.tmp 62 | *.vspscc 63 | .builds 64 | *.dotCover 65 | 66 | ## TODO: If you have NuGet Package Restore enabled, uncomment this 67 | #packages/ 68 | 69 | # Visual C++ cache files 70 | ipch/ 71 | *.aps 72 | *.ncb 73 | *.opensdf 74 | *.sdf 75 | 76 | # Visual Studio profiler 77 | *.psess 78 | *.vsp 79 | 80 | # ReSharper is a .NET coding add-in 81 | _ReSharper* 82 | 83 | # Installshield output folder 84 | [Ee]xpress 85 | 86 | # DocProject is a documentation generator add-in 87 | DocProject/buildhelp/ 88 | DocProject/Help/*.HxT 89 | DocProject/Help/*.HxC 90 | DocProject/Help/*.hhc 91 | DocProject/Help/*.hhk 92 | DocProject/Help/*.hhp 93 | DocProject/Help/Html2 94 | DocProject/Help/html 95 | 96 | # Click-Once directory 97 | publish 98 | 99 | # Others 100 | [Bb]in 101 | [Oo]bj 102 | sql 103 | TestResults 104 | *.Cache 105 | ClientBin 106 | stylecop.* 107 | ~$* 108 | *.dbmdl 109 | Generated_Code #added for RIA/Silverlight projects 110 | 111 | # Backup & report files from converting an old project file to a newer 112 | # Visual Studio version. Backup files are not needed, because we have git ;-) 113 | _UpgradeReport_Files/ 114 | Backup*/ 115 | UpgradeLog*.XML 116 | 117 | 118 | 119 | ############ 120 | ## Windows 121 | ############ 122 | 123 | # Windows image file caches 124 | Thumbs.db 125 | 126 | # Folder config file 127 | Desktop.ini 128 | 129 | 130 | ############# 131 | ## Python 132 | ############# 133 | 134 | *.py[co] 135 | 136 | # Packages 137 | *.egg 138 | *.egg-info 139 | dist 140 | build 141 | eggs 142 | parts 143 | bin 144 | var 145 | sdist 146 | develop-eggs 147 | .installed.cfg 148 | 149 | # Installer logs 150 | pip-log.txt 151 | 152 | # Unit test / coverage reports 153 | .coverage 154 | .tox 155 | 156 | #Translations 157 | *.mo 158 | 159 | #Mr Developer 160 | .mr.developer.cfg 161 | 162 | # Mac crap 163 | .DS_Store 164 | -------------------------------------------------------------------------------- /OriginalFiler/laerere.php: -------------------------------------------------------------------------------- 1 | load($lectio_html); //Parse HTML 26 | $elev_objekter = $html->find('td a'); //Søg efter alle elever på denne side 27 | $link = ''; 28 | for($i=32; $ihref; 31 | $link_pos = strrpos($link, 'elevid='); 32 | if($link_pos <> -1) 33 | { 34 | $link = trim(substr($link, $link_pos+7)); 35 | if(is_numeric($link)) 36 | { 37 | $link = (int)$link; 38 | $elever[] = array( 39 | 'navn' => trim(html_entity_decode($elev_objekter[$i]->plaintext)), 40 | 'lectio_id' => $link 41 | ); 42 | } 43 | } 44 | } 45 | return $elever; 46 | } 47 | //Hent elever fra gymnasie i relativt usorteret liste (for det meste alfabetisk men ikke garanteret) 48 | function get_elever_fra_gymnasie($gymnasie_kode) 49 | { 50 | $url_start = 'http://www.lectio.dk/lectio/'.$gymnasie_kode.'/FindSkema.aspx?type=elev&forbogstav='; 51 | $final_result = array(); 52 | $keys_to_search = array('A','B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 53 | 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 54 | 'W', 'X', 'Y', 'Z', 'Æ', 'Ø', 'Å', '?'); 55 | foreach ($keys_to_search as $key) { 56 | $final_result = array_merge($final_result, get_elever_fra_side($url_start.$key)); 57 | } 58 | return $final_result; 59 | } 60 | //Hent elever fra gymnasiekode sorteret efter klasse 61 | function get_elever_fra_gymnasie_sorteret($gymnasie_kode) 62 | { 63 | $sorterede_elever = array(); 64 | $input = get_elever_fra_gymnasie($gymnasie_kode); 65 | foreach ($input as $elev) { 66 | preg_match("/\((.*)\s(.*)\)/", $elev['navn'], $match_data); //Parse klasse data 67 | if(count($match_data) == 3) //Hvis der er både klasse og elev ID så sæt det ind 68 | { 69 | if(!array_key_exists($match_data[1], $sorterede_elever)) 70 | { 71 | //Hvis elevens klasse ikke allerede eksisterer så tilføjer vi den lige 72 | $sorterede_elever[$match_data[1]] = array(); 73 | } 74 | $sorterede_elever[$match_data[1]][] = array( 75 | 'navn' => trim(substr($elev['navn'], 0, strpos($elev['navn'], '('))), //Vi fjerner lige klasse fra navn 76 | 'lectio_id' => $elev['lectio_id'], 77 | 'elev_nummer' => (int)$match_data[2], 78 | 'klasse' => $match_data[1] 79 | ); 80 | } 81 | } 82 | return $sorterede_elever; 83 | } 84 | 85 | $elever = get_elever_fra_gymnasie_sorteret('402'); 86 | var_dump($elever); 87 | ?> -------------------------------------------------------------------------------- /OriginalFiler/skema.php: -------------------------------------------------------------------------------- 1 | load($lectio_html); 27 | $skema['titel'] = $html->find('.s2weekHeader td', 0)->plaintext; //Hent overskriften uden html (uge og år) 28 | $headers = $html->find('.s2dayHeader td'); //Søg efter listen over dage i det pågældende skema 29 | for($i=1;$iplaintext; //Tilføj alle overskrifterne på ugedagene (uden html) 32 | $skema['dagskema'][$headers[$i]->plaintext] = array( 33 | 'noter' => array(), 34 | 'fag' => array() 35 | ); //Tilføj en struktur til nøglen for hvert dagskema 36 | } 37 | $collection = $html->find('.s2skemabrikcontainer'); //Søg efter den ydre skema container for hver dag 38 | /* 39 | BEMÆRK!!!! 40 | Den ydre skema container, der er langt flere end antal dage. Feks. kan en uge med 5 dage 41 | have 11 ydre containere pga. 5 til moduler, 5 til "noter" i toppen, og én til sidebaren. 42 | */ 43 | $skemabrik = new simple_html_dom(); //Definer den her for genbrugens skyld da den kan tømmes efter hver iteration 44 | for($i=0; $iload($collection[$i]->innertext); 47 | $noter = $skemabrik->find('.s2skemabrikcontent'); 48 | foreach($noter as $note) 49 | { 50 | //Tilføj til liste over noter for dagen 51 | $skema['dagskema'][$skema['ugedage'][$i]]['noter'][] = trim(html_entity_decode($note->plaintext)); 52 | } 53 | } 54 | //Iterer alle fagene/noterne i selve skemaet for hver dag 55 | //Vi starter iteratoren i count($skema['ugedage']) + 1 fordi vi vil springe topnoter + et stil element i mellem over. 56 | for($i=count($skema['ugedage'])+1; $i<(2*count($skema['ugedage'])+1); $i++) 57 | { 58 | $skemabrik->load($collection[$i]->innertext); 59 | $noter = $skemabrik->find('.s2skemabrikcontent'); 60 | foreach($noter as $note) 61 | { 62 | //Tilføj til dagskemaet 63 | $skema['dagskema'][$skema['ugedage'][$i-count($skema['ugedage'])-1]]['fag'][] = array( 64 | 'tekst' => trim(html_entity_decode($note->plaintext)), 65 | 'note' => '' 66 | ); 67 | } 68 | } 69 | for($i=5; $iload($collection[$i]->innertext); //Indlæs hver dag 72 | $skemabrik_elementer = $skemabrik->find('.s2skemabrik'); //Søg efter alle skemabrikkerne på denne dag 73 | for($y=0; $ytitle)); 77 | } 78 | } 79 | return $skema; 80 | } 81 | function get_skema_til_elev($gymnasie_kode, $lectio_id) 82 | { 83 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=elev&elevid='.$lectio_id; 84 | return get_skema($url_to_get); 85 | } 86 | function get_skema_til_elev_og_uge($gymnasie_kode, $lectio_id, $uge_kode) 87 | { 88 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=elev&elevid='.$lectio_id.'&week='.$uge_kode; 89 | return get_skema($url_to_get); 90 | } 91 | $skema = get_skema_til_elev(402, 4763365585); 92 | var_dump($skema); 93 | ?> -------------------------------------------------------------------------------- /isitagirl/unisexnavne.csv: -------------------------------------------------------------------------------- 1 | Abiola 2 | Acelya 3 | Ada 4 | Adama 5 | Addis 6 | Addison 7 | Adi 8 | Adian 9 | Aezha 10 | Agne 11 | Ahsen 12 | Aiden 13 | Aiko 14 | Aimal 15 | Ajo 16 | Aki 17 | Akila 18 | Akira 19 | Akram 20 | Akshini 21 | Al 22 | Alae 23 | Albi 24 | Alex 25 | Alexis 26 | Alfie 27 | Alham 28 | Alija 29 | Alix 30 | Alla 31 | Almas 32 | Alpha 33 | Alvild 34 | Amal 35 | Aman 36 | Amani 37 | Amar 38 | Amaru 39 | Amel 40 | Amine 41 | Amran 42 | An 43 | Ananda 44 | Andrea 45 | Ange 46 | Angel 47 | Anh 48 | Ani 49 | Anis 50 | Anmol 51 | Anwar 52 | Aputsiaq 53 | Ara 54 | Aria 55 | Arian 56 | Ariel 57 | Arta 58 | Arya 59 | Asa 60 | Ashley 61 | Asil 62 | Aska 63 | Aslaug 64 | Assana 65 | Ata 66 | Auguste 67 | Avalon 68 | Avan 69 | Avery 70 | Avesta 71 | Awin 72 | Ayan 73 | Aye 74 | Ayo 75 | Ayomide 76 | Ayaan 77 | Azhar 78 | Bailey 79 | Bao 80 | Bari 81 | Benne 82 | Benni 83 | Bennie 84 | Benny 85 | Bera 86 | Beren 87 | Bernie 88 | Bi 89 | Biak 90 | Billie 91 | Biruk 92 | Bjørk 93 | Björk 94 | Blake 95 | Blessing 96 | Bo 97 | Bobbie 98 | Bode 99 | Bodhi 100 | Cameron 101 | Cane 102 | Casey 103 | Caspian 104 | Cass 105 | Cassiel 106 | Cecil 107 | Cennet 108 | Chandra 109 | Chang 110 | Chansa 111 | Charlie 112 | Charlot 113 | Chen 114 | Chi 115 | Ching 116 | Chisom 117 | Cho 118 | Chris 119 | Cilla 120 | Cimmy 121 | Conny 122 | Dac 123 | Dai 124 | Dakota 125 | Dan 126 | Dana 127 | Dani 128 | Daniele 129 | Danila 130 | Danni 131 | Dara 132 | Darin 133 | Darma 134 | Dawt 135 | Dayan 136 | Deep 137 | Delvin 138 | Deni 139 | Deniz 140 | Destiny 141 | Devrim 142 | Dhwani 143 | Dia 144 | Dian 145 | Dilan 146 | Dione 147 | Dominikas 148 | Dominique 149 | Dung 150 | Ebba 151 | Echevarria 152 | Eddy 153 | Edem 154 | Ehm 155 | Ehsan 156 | Ekin 157 | Elaf 158 | Elham 159 | Eli 160 | Elia 161 | Elie 162 | Elif 163 | Elin 164 | Elis 165 | Ellis 166 | Elvan 167 | Elvin 168 | Eman 169 | Erin 170 | Esa 171 | Evin 172 | Ezel 173 | Ezra 174 | Fajr 175 | Farah 176 | Felice 177 | Feng 178 | Fidan 179 | Fille 180 | Florens 181 | Frankie 182 | Frey 183 | Fu 184 | Gael 185 | Gerd 186 | Gia 187 | Gilli 188 | Gin 189 | Gisa 190 | Glenn 191 | Grace 192 | Gry 193 | Guggi 194 | Gul 195 | Gunde 196 | Gunder 197 | Gunni 198 | Görkem 199 | Habib 200 | Hamdi 201 | Hami 202 | Han 203 | Hanan 204 | Hani 205 | Hannan 206 | Hao 207 | Harley 208 | Hasti 209 | Havin 210 | Hayan 211 | Hedi 212 | Helfred 213 | Hien 214 | Hilal 215 | Hlei 216 | Hoa 217 | Hoang 218 | Hodan 219 | Hong 220 | Huan 221 | Hui 222 | Huyen 223 | Ilhan 224 | Ilian 225 | Ilja 226 | Illya 227 | Ilya 228 | Indigo 229 | Isa 230 | Issa 231 | Issey 232 | Jackie 233 | Jaime 234 | Jamal 235 | Jamie 236 | Jana 237 | Jannie 238 | Jasmia 239 | Jasmin 240 | Jay 241 | Jazz 242 | Jean 243 | Jessie 244 | Jia 245 | Jian 246 | Jiayi 247 | Jie 248 | Jihan 249 | Jin 250 | Jivan 251 | Jo 252 | Joa 253 | Joan 254 | Jodi 255 | Joe 256 | Johnni 257 | Johnnie 258 | Johnny 259 | Jonni 260 | Jonny 261 | Joud 262 | Judi 263 | Juno 264 | Justice 265 | Kali 266 | Kami 267 | Kani 268 | Kanna 269 | Karam 270 | Kari 271 | Karli 272 | Kavin 273 | Kay 274 | Kaya 275 | Kayra 276 | Kayse 277 | Kazi 278 | Kelly 279 | Kennie 280 | Kenny 281 | Kerry 282 | Khanh 283 | Kim 284 | Kimber 285 | Kimi 286 | Kimm 287 | Kimmy 288 | Kiran 289 | Kit 290 | Kris 291 | Lai 292 | Lam 293 | Lamar 294 | Laurence 295 | Lave 296 | Lawin 297 | Le 298 | Lee 299 | Lei 300 | Lek 301 | Lennie 302 | Lesley 303 | Leslie 304 | Levi 305 | Li 306 | Lian 307 | Liann 308 | Lin 309 | Ling 310 | Lione 311 | Lior 312 | Lo 313 | Lolan 314 | Lou 315 | Loui 316 | Love 317 | Luca 318 | Lucca 319 | Lucka 320 | Ludo 321 | Lue 322 | Luka 323 | Lutfi 324 | Ly 325 | Lykke 326 | Lyn 327 | Mackenzie 328 | Madi 329 | Maes 330 | Mai 331 | Makoto 332 | Malle 333 | Malli 334 | Manar 335 | Manel 336 | Manu 337 | Mar 338 | Marian 339 | Marin 340 | Marion 341 | Marley 342 | Marli 343 | Marlin 344 | Marlon 345 | Marni 346 | Masi 347 | Masih 348 | Matti 349 | Mattie 350 | Mawuli 351 | Mayan 352 | Maysam 353 | Melian 354 | Messi 355 | Mian 356 | Micah 357 | Micha 358 | Michal 359 | Michel 360 | Michele 361 | Michell 362 | Mickie 363 | Mika 364 | Miki 365 | Miko 366 | Milan 367 | Miley 368 | Milja 369 | Millian 370 | Milou 371 | Min 372 | Ming 373 | Mingo 374 | Minh 375 | Minne 376 | Minori 377 | Mir 378 | Miral 379 | Miran 380 | Mire 381 | Mirza 382 | Mischa 383 | Misha 384 | Mishal 385 | Mithra 386 | Mo 387 | Moe 388 | Monroe 389 | Moon 390 | Morgan 391 | Mulle 392 | Musse 393 | Muzaffer 394 | Na 395 | Nadeem 396 | Nadin 397 | Naimi 398 | Naji 399 | Nan 400 | Nana 401 | Nano 402 | Naseem 403 | Nasim 404 | Nat 405 | Nazir 406 | Neel 407 | Neil 408 | Nermin 409 | Nevin 410 | Ngoc 411 | Ngun 412 | Nhan 413 | Nhat 414 | Nichola 415 | Nickey 416 | Nickie 417 | Nicola 418 | Niel 419 | Nika 420 | Nike 421 | Niki 422 | Nikita 423 | Nikki 424 | Nikola 425 | Nil 426 | Nilay 427 | Nima 428 | Nino 429 | Noa 430 | Noel 431 | Noël 432 | Noell 433 | Noha 434 | Noor 435 | Nor 436 | Nour 437 | Nuka 438 | Nuno 439 | Nur 440 | Nuunu 441 | Ny 442 | Nya 443 | Obi 444 | Ola 445 | Oluwakemi 446 | Oreoluwa 447 | Osiris 448 | Paja 449 | Paris 450 | Peng 451 | Phi 452 | Pil 453 | Prana 454 | Qamar 455 | Qi 456 | Rabab 457 | Raden 458 | Raja 459 | Rajan 460 | Raji 461 | Rameen 462 | Ran 463 | Rana 464 | Randy 465 | Rani 466 | Rawand 467 | Rayan 468 | Rayne 469 | Rayaan 470 | Raza 471 | Reddy 472 | Renee 473 | Reneé 474 | Rian 475 | Ricci 476 | Rida 477 | Ridwan 478 | Rihan 479 | Rio 480 | River 481 | Robin 482 | Roine 483 | Rojbin 484 | Rojin 485 | Roma 486 | Rong 487 | Ronnie 488 | Rosario 489 | Rosen 490 | Roshan 491 | Rudi 492 | Rudy 493 | Ruepawadee 494 | Ruhan 495 | Ruiyang 496 | Rumi 497 | Run 498 | Ruoyi 499 | Ryan 500 | Sabah 501 | Sada 502 | Sadaf 503 | Sade 504 | Safa 505 | Safi 506 | Saki 507 | Salam 508 | Sali 509 | Sam 510 | Saman 511 | Samar 512 | Sameer 513 | Samer 514 | Sami 515 | Sammi 516 | Sammy 517 | San 518 | Sanam 519 | Sandi 520 | Sandy 521 | Sanny 522 | Sari 523 | Sasa 524 | Sascha 525 | Sasha 526 | Sava 527 | Sena 528 | Seren 529 | Servan 530 | Servet 531 | Seyda 532 | Shadi 533 | Shah 534 | Shahed 535 | Shaheen 536 | Shahin 537 | Shams 538 | Shan 539 | Shannon 540 | Shiloh 541 | Shu 542 | Si 543 | Sian 544 | Sidney 545 | Sika 546 | Sila 547 | Silva 548 | Sina 549 | Sipan 550 | Siva 551 | Skye 552 | Sohan 553 | Sol 554 | Sole 555 | Soma 556 | Sondos 557 | Sonic 558 | Sonni 559 | Sonny 560 | Star 561 | Stevie 562 | Storm 563 | Suad 564 | Sultan 565 | Suman 566 | Sun 567 | Sung 568 | Sunny 569 | Sølve 570 | Saadat 571 | Taban 572 | Tae 573 | Tahsin 574 | Taïs 575 | Talat 576 | Tam 577 | Tan 578 | Tawheed 579 | Te 580 | Tha 581 | Thai 582 | Thanh 583 | Thien 584 | Thy 585 | Tian 586 | Tich 587 | Tien 588 | Tin 589 | Toma 590 | Tong 591 | Toni 592 | Tonni 593 | Tonnie 594 | Tonny 595 | Tony 596 | Toto 597 | Tran 598 | Trong 599 | Truc 600 | Tu 601 | Tuna 602 | Ul 603 | Um 604 | Van 605 | Vanja 606 | Vi 607 | Vian 608 | Victory 609 | Viet 610 | Vigge 611 | Ville 612 | Vy 613 | Wai 614 | Walli 615 | Wei 616 | Wen 617 | Willow 618 | Wing 619 | Xi 620 | Xiang 621 | Xiao 622 | Xiaoye 623 | Xin 624 | Xing 625 | Xuan 626 | Yahya 627 | Yali 628 | Yan 629 | Yang 630 | Yao 631 | Yi 632 | Yin 633 | Yixuan 634 | Yo 635 | Yoel 636 | Yon 637 | Yong 638 | Young 639 | Yu 640 | Yuan 641 | Yuki 642 | Yumna 643 | Yuri 644 | Yüksel 645 | Zana 646 | Zayed 647 | Zaza 648 | Ze 649 | Zein 650 | Zia 651 | Zidan 652 | Ziggy 653 | Zilin 654 | Zin 655 | -------------------------------------------------------------------------------- /OriginalFiler/lectio.php: -------------------------------------------------------------------------------- 1 | load($lectio_html); 33 | $skema['titel'] = $html->find('.s2weekHeader td', 0)->plaintext; //Hent overskriften uden html (uge og år) 34 | $headers = $html->find('.s2dayHeader td'); //Søg efter listen over dage i det pågældende skema 35 | for($i=1;$iplaintext; //Tilføj alle overskrifterne på ugedagene (uden html) 38 | $skema['dagskema'][$headers[$i]->plaintext] = array( 39 | 'noter' => array(), 40 | 'fag' => array() 41 | ); //Tilføj en struktur til nøglen for hvert dagskema 42 | } 43 | $collection = $html->find('.s2skemabrikcontainer'); //Søg efter den ydre skema container for hver dag 44 | /* 45 | BEMÆRK!!!! 46 | Den ydre skema container, der er langt flere end antal dage. Feks. kan en uge med 5 dage 47 | have 11 ydre containere pga. 5 til moduler, 5 til "noter" i toppen, og én til sidebaren. 48 | */ 49 | $skemabrik = new simple_html_dom(); //Definer den her for genbrugens skyld da den kan tømmes efter hver iteration 50 | for($i=0; $iload($collection[$i]->innertext); 53 | $noter = $skemabrik->find('.s2skemabrikcontent'); 54 | foreach($noter as $note) 55 | { 56 | //Tilføj til liste over noter for dagen 57 | $skema['dagskema'][$skema['ugedage'][$i]]['noter'][] = trim(html_entity_decode($note->plaintext)); 58 | } 59 | } 60 | //Iterer alle fagene/noterne i selve skemaet for hver dag 61 | //Vi starter iteratoren i count($skema['ugedage']) + 1 fordi vi vil springe topnoter + et stil element i mellem over. 62 | for($i=count($skema['ugedage'])+1; $i<(2*count($skema['ugedage'])+1); $i++) 63 | { 64 | $skemabrik->load($collection[$i]->innertext); 65 | $noter = $skemabrik->find('.s2skemabrikcontent'); 66 | foreach($noter as $note) 67 | { 68 | //Tilføj til dagskemaet 69 | $skema['dagskema'][$skema['ugedage'][$i-count($skema['ugedage'])-1]]['fag'][] = array( 70 | 'tekst' => trim(html_entity_decode($note->plaintext)), 71 | 'note' => '' 72 | ); 73 | } 74 | } 75 | for($i=5; $iload($collection[$i]->innertext); //Indlæs hver dag 78 | $skemabrik_elementer = $skemabrik->find('.s2skemabrik'); //Søg efter alle skemabrikkerne på denne dag 79 | for($y=0; $ytitle)); 83 | } 84 | } 85 | return $skema; 86 | } 87 | //Hent skema ud fra gymnasiekode og Lectio ID for elev 88 | public function get_skema_til_elev($gymnasie_kode, $lectio_id) 89 | { 90 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=elev&elevid='.$lectio_id; 91 | return get_skema($url_to_get); 92 | } 93 | //Hent skema ud fra gymnasiekode, Lectio ID for elev og ugekode i format WWYYYY 94 | public function get_skema_til_elev_og_uge($gymnasie_kode, $lectio_id, $uge_kode) 95 | { 96 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=elev&elevid='.$lectio_id.'&week='.$uge_kode; 97 | return get_skema($url_to_get); 98 | } 99 | //Hent skema ud fra gymnasiekode, Lectio ID for lærer 100 | public function get_skema_til_laerer($gymnasie_kode, $lectio_id) 101 | { 102 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=laerer&laererid='.$lectio_id; 103 | return get_skema($url_to_get); 104 | } 105 | //Hent skema ud fra gymnasiekode, Lectio ID for lærer og ugekode i format WWYYYY 106 | public function get_skema_til_laerer_og_uge($gymnasie_kode, $lectio_id,$uge_kode) 107 | { 108 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=laerer&laererid='.$lectio_id.'&week='.$uge_kode; 109 | return get_skema($url_to_get); 110 | } 111 | //Henter den offentlige liste over elever ud fra en URL til siden med elever. Afhængig af get_content(). 112 | public function get_elever_fra_side($url_til_elevside) 113 | { 114 | $lectio_html = get_content($url_til_elevside); 115 | $elever = array(); //Opret array til elever fra denne side 116 | 117 | $html = new simple_html_dom(); 118 | $html->load($lectio_html); //Parse HTML 119 | $elev_objekter = $html->find('td a'); //Søg efter alle elever på denne side 120 | $link = ''; 121 | for($i=32; $ihref; 124 | $link_pos = strrpos($link, 'elevid='); 125 | if($link_pos <> -1) 126 | { 127 | $link = trim(substr($link, $link_pos+7)); 128 | if(is_numeric($link)) 129 | { 130 | $link = (int)$link; 131 | $elever[] = array( 132 | 'navn' => trim(html_entity_decode($elev_objekter[$i]->plaintext)), 133 | 'lectio_id' => $link 134 | ); 135 | } 136 | } 137 | } 138 | return $elever; 139 | } 140 | //Hent elever fra gymnasie i relativt usorteret liste (for det meste alfabetisk men ikke garanteret) 141 | public function get_elever_fra_gymnasie($gymnasie_kode) 142 | { 143 | $url_start = 'http://www.lectio.dk/lectio/'.$gymnasie_kode.'/FindSkema.aspx?type=elev&forbogstav='; 144 | $final_result = array(); 145 | $keys_to_search = array('A','B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 146 | 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 147 | 'W', 'X', 'Y', 'Z', 'Æ', 'Ø', 'Å', '?'); 148 | foreach ($keys_to_search as $key) { 149 | $final_result = array_merge($final_result, get_elever_fra_side($url_start.$key)); 150 | } 151 | return $final_result; 152 | } 153 | //Hent elever fra gymnasiekode sorteret efter klasse 154 | public function get_elever_fra_gymnasie_sorteret($gymnasie_kode) 155 | { 156 | $sorterede_elever = array(); 157 | $input = get_elever_fra_gymnasie($gymnasie_kode); 158 | foreach ($input as $elev) { 159 | preg_match("/\((.*)\s(.*)\)/", $elev['navn'], $match_data); //Parse klasse data 160 | if(count($match_data) == 3) //Hvis der er både klasse og elev ID så sæt det ind 161 | { 162 | if(!array_key_exists($match_data[1], $sorterede_elever)) 163 | { 164 | //Hvis elevens klasse ikke allerede eksisterer så tilføjer vi den lige 165 | $sorterede_elever[$match_data[1]] = array(); 166 | } 167 | $sorterede_elever[$match_data[1]][] = array( 168 | 'navn' => trim(substr($elev['navn'], 0, strpos($elev['navn'], '('))), //Vi fjerner lige klasse fra navn 169 | 'lectio_id' => $elev['lectio_id'], 170 | 'elev_nummer' => (int)$match_data[2], 171 | 'klasse' => $match_data[1] 172 | ); 173 | } 174 | } 175 | return $sorterede_elever; 176 | } 177 | //Henter den offentlige liste over lærere ud fra en URL til siden med elever. Afhængig af get_content(). 178 | public function get_laerere_fra_side($url_til_laererside) 179 | { 180 | $lectio_html = get_content($url_til_laererside); 181 | $laerere = array(); //Opret array til lærere fra denne side 182 | 183 | $html = new simple_html_dom(); 184 | $html->load($lectio_html); //Parse HTML 185 | $laerer_objekter = $html->find('td a'); //Søg efter alle lærere 186 | for($i=0; $ilectiocontextcard)>0) 190 | { 191 | //Det er et lærer objekt vi har med at gøre! 192 | $navn = trim(html_entity_decode($l->plaintext)); 193 | $initialer = preg_match("/\((.*)\)/", $navn, $match_data); //Match for parantesen med initialer 194 | $link = $l->href; 195 | $lectio_id = substr($link, strpos($link, 'laererid=')+9); 196 | $laerere[] = array( 197 | 'navn' => $navn, 198 | 'initialer' => $match_data[1], 199 | 'lectio_id' => $lectio_id 200 | ); 201 | } 202 | 203 | } 204 | return $laerere; 205 | } 206 | //Hent lærere ud fra gymnasiekode 207 | public function get_laerere($gymnasie_kode) 208 | { 209 | $link_start = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/FindSkema.aspx?type=laerer'; 210 | return get_laerere_fra_side($link_start); 211 | } 212 | 213 | } 214 | ?> -------------------------------------------------------------------------------- /lectio.php: -------------------------------------------------------------------------------- 1 | get_content($url_til_skema); 28 | $skema = array(); //Definer skema variabel til return værdi! 29 | $skema['titel'] = ''; //Definer struktur for titel 30 | $skema['ugedage'] = array(); //Definer struktur for liste over ugedage 31 | $skema['dagskema'] = array(); //Definer struktur for dagskemaet 32 | $html = new simple_html_dom(); 33 | $html->load($lectio_html); 34 | $skema['titel'] = $html->find('.s2weekHeader td', 0)->plaintext; //Hent overskriften uden html (uge og år) 35 | $headers = $html->find('.s2dayHeader td'); //Søg efter listen over dage i det pågældende skema 36 | for($i=1;$iplaintext; //Tilføj alle overskrifterne på ugedagene (uden html) 39 | $skema['dagskema'][$headers[$i]->plaintext] = array( 40 | 'noter' => array(), 41 | 'fag' => array() 42 | ); //Tilføj en struktur til nøglen for hvert dagskema 43 | } 44 | $collection = $html->find('.s2skemabrikcontainer'); //Søg efter den ydre skema container for hver dag 45 | /* 46 | BEMÆRK!!!! 47 | Den ydre skema container, der er langt flere end antal dage. Feks. kan en uge med 5 dage 48 | have 11 ydre containere pga. 5 til moduler, 5 til "noter" i toppen, og én til sidebaren. 49 | */ 50 | $skemabrik = new simple_html_dom(); //Definer den her for genbrugens skyld da den kan tømmes efter hver iteration 51 | for($i=0; $iload($collection[$i]->innertext); 54 | $noter = $skemabrik->find('.s2skemabrikcontent'); 55 | foreach($noter as $note) 56 | { 57 | //Tilføj til liste over noter for dagen 58 | $skema['dagskema'][$skema['ugedage'][$i]]['noter'][] = trim(html_entity_decode($note->plaintext)); 59 | } 60 | } 61 | //Iterer alle fagene/noterne i selve skemaet for hver dag 62 | //Vi starter iteratoren i count($skema['ugedage']) + 1 fordi vi vil springe topnoter + et stil element i mellem over. 63 | for($i=count($skema['ugedage'])+1; $i<(2*count($skema['ugedage'])+1); $i++) 64 | { 65 | $skemabrik->load($collection[$i]->innertext); 66 | $noter = $skemabrik->find('.s2skemabrikcontent'); 67 | foreach($noter as $note) 68 | { 69 | //Tilføj til dagskemaet 70 | $skema['dagskema'][$skema['ugedage'][$i-count($skema['ugedage'])-1]]['fag'][] = array( 71 | 'tekst' => trim(html_entity_decode($note->plaintext)), 72 | 'note' => '' 73 | ); 74 | } 75 | } 76 | for($i=5; $iload($collection[$i]->innertext); //Indlæs hver dag 79 | $skemabrik_elementer = $skemabrik->find('.s2skemabrik'); //Søg efter alle skemabrikkerne på denne dag 80 | for($y=0; $ytitle)); 84 | } 85 | } 86 | return $skema; 87 | } 88 | //Hent skema ud fra gymnasiekode og Lectio ID for elev 89 | public function get_skema_til_elev($gymnasie_kode, $lectio_id) 90 | { 91 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=elev&elevid='.$lectio_id; 92 | return $this->get_skema($url_to_get); 93 | } 94 | //Hent skema ud fra gymnasiekode, Lectio ID for elev og ugekode i format WWYYYY 95 | public function get_skema_til_elev_og_uge($gymnasie_kode, $lectio_id, $uge_kode) 96 | { 97 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=elev&elevid='.$lectio_id.'&week='.$uge_kode; 98 | return $this->get_skema($url_to_get); 99 | } 100 | //Hent skema ud fra gymnasiekode, Lectio ID for lærer 101 | public function get_skema_til_laerer($gymnasie_kode, $lectio_id) 102 | { 103 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=laerer&laererid='.$lectio_id; 104 | return $this->get_skema($url_to_get); 105 | } 106 | //Hent skema ud fra gymnasiekode, Lectio ID for lærer og ugekode i format WWYYYY 107 | public function get_skema_til_laerer_og_uge($gymnasie_kode, $lectio_id,$uge_kode) 108 | { 109 | $url_to_get = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/SkemaNy.aspx?type=laerer&laererid='.$lectio_id.'&week='.$uge_kode; 110 | return $this->get_skema($url_to_get); 111 | } 112 | //Henter den offentlige liste over elever ud fra en URL til siden med elever. Afhængig af get_content(). 113 | private function get_elever_fra_side($url_til_elevside) 114 | { 115 | $lectio_html = $this->get_content($url_til_elevside); 116 | $elever = array(); //Opret array til elever fra denne side 117 | 118 | $html = new simple_html_dom(); 119 | $html->load($lectio_html); //Parse HTML 120 | $elev_objekter = $html->find('td a'); //Søg efter alle elever på denne side 121 | $link = ''; 122 | for($i=32; $ihref; 125 | $link_pos = strrpos($link, 'elevid='); 126 | if($link_pos <> -1) 127 | { 128 | $link = trim(substr($link, $link_pos+7)); 129 | if(is_numeric($link)) 130 | { 131 | $link = (int)$link; 132 | $elever[] = array( 133 | 'navn' => trim(html_entity_decode($elev_objekter[$i]->plaintext)), 134 | 'lectio_id' => $link 135 | ); 136 | } 137 | } 138 | } 139 | return $elever; 140 | } 141 | //Hent elever fra gymnasie i relativt usorteret liste (for det meste alfabetisk men ikke garanteret) 142 | public function get_elever_fra_gymnasie($gymnasie_kode) 143 | { 144 | $url_start = 'http://www.lectio.dk/lectio/'.$gymnasie_kode.'/FindSkema.aspx?type=elev&forbogstav='; 145 | $final_result = array(); 146 | $keys_to_search = array('A','B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 147 | 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 148 | 'W', 'X', 'Y', 'Z', 'Æ', 'Ø', 'Å', '?'); 149 | foreach ($keys_to_search as $key) { 150 | $final_result = array_merge($final_result, $this->get_elever_fra_side($url_start.$key)); 151 | } 152 | return $final_result; 153 | } 154 | //Hent elever fra gymnasiekode sorteret efter klasse 155 | public function get_elever_fra_gymnasie_sorteret($gymnasie_kode) 156 | { 157 | $sorterede_elever = array(); 158 | $input = $this->get_elever_fra_gymnasie($gymnasie_kode); 159 | foreach ($input as $elev) { 160 | preg_match("/\((.*)\s(.*)\)/", $elev['navn'], $match_data); //Parse klasse data 161 | if(count($match_data) == 3) //Hvis der er både klasse og elev ID så sæt det ind 162 | { 163 | if(!array_key_exists($match_data[1], $sorterede_elever)) 164 | { 165 | //Hvis elevens klasse ikke allerede eksisterer så tilføjer vi den lige 166 | $sorterede_elever[$match_data[1]] = array(); 167 | } 168 | $sorterede_elever[$match_data[1]][] = array( 169 | 'navn' => trim(substr($elev['navn'], 0, strpos($elev['navn'], '('))), //Vi fjerner lige klasse fra navn 170 | 'lectio_id' => $elev['lectio_id'], 171 | 'elev_nummer' => (int)$match_data[2], 172 | 'klasse' => $match_data[1] 173 | ); 174 | } 175 | } 176 | return $sorterede_elever; 177 | } 178 | //Henter den offentlige liste over lærere ud fra en URL til siden med elever. Afhængig af get_content(). 179 | public function get_laerere_fra_side($url_til_laererside) 180 | { 181 | $lectio_html = $this->get_content($url_til_laererside); 182 | $laerere = array(); //Opret array til lærere fra denne side 183 | 184 | $html = new simple_html_dom(); 185 | $html->load($lectio_html); //Parse HTML 186 | $laerer_objekter = $html->find('td a'); //Søg efter alle lærere 187 | for($i=0; $ilectiocontextcard)>0) 191 | { 192 | //Det er et lærer objekt vi har med at gøre! 193 | $navn = trim(html_entity_decode($l->plaintext)); 194 | $initialer = preg_match("/\((.*)\)/", $navn, $match_data); //Match for parantesen med initialer 195 | $link = $l->href; 196 | $lectio_id = substr($link, strpos($link, 'laererid=')+9); 197 | $laerere[] = array( 198 | 'navn' => $navn, 199 | 'initialer' => $match_data[1], 200 | 'lectio_id' => $lectio_id 201 | ); 202 | } 203 | 204 | } 205 | return $laerere; 206 | } 207 | //Hent lærere ud fra gymnasiekode 208 | public function get_laerere($gymnasie_kode) 209 | { 210 | $link_start = 'https://www.lectio.dk/lectio/'.$gymnasie_kode.'/FindSkema.aspx?type=laerer'; 211 | return $this->get_laerere_fra_side($link_start); 212 | } 213 | 214 | } 215 | ?> -------------------------------------------------------------------------------- /simple_html_dom.php: -------------------------------------------------------------------------------- 1 | size is the "real" number of bytes the dom was created from. 17 | * but for most purposes, it's a really good estimation. 18 | * Paperg - Added the forceTagsClosed to the dom constructor. Forcing tags closed is great for malformed html, but it CAN lead to parsing errors. 19 | * Allow the user to tell us how much they trust the html. 20 | * Paperg add the text and plaintext to the selectors for the find syntax. plaintext implies text in the innertext of a node. text implies that the tag is a text node. 21 | * This allows for us to find tags based on the text they contain. 22 | * Create find_ancestor_tag to see if a tag is - at any level - inside of another specific tag. 23 | * Paperg: added parse_charset so that we know about the character set of the source document. 24 | * NOTE: If the user's system has a routine called get_last_retrieve_url_contents_content_type availalbe, we will assume it's returning the content-type header from the 25 | * last transfer or curl_exec, and we will parse that and use it in preference to any other method of charset detection. 26 | * 27 | * Found infinite loop in the case of broken html in restore_noise. Rewrote to protect from that. 28 | * PaperG (John Schlick) Added get_display_size for "IMG" tags. 29 | * 30 | * Licensed under The MIT License 31 | * Redistributions of files must retain the above copyright notice. 32 | * 33 | * @author S.C. Chen 34 | * @author John Schlick 35 | * @author Rus Carroll 36 | * @version 1.5 ($Rev: 196 $) 37 | * @package PlaceLocalInclude 38 | * @subpackage simple_html_dom 39 | */ 40 | 41 | /** 42 | * All of the Defines for the classes below. 43 | * @author S.C. Chen 44 | */ 45 | define('HDOM_TYPE_ELEMENT', 1); 46 | define('HDOM_TYPE_COMMENT', 2); 47 | define('HDOM_TYPE_TEXT', 3); 48 | define('HDOM_TYPE_ENDTAG', 4); 49 | define('HDOM_TYPE_ROOT', 5); 50 | define('HDOM_TYPE_UNKNOWN', 6); 51 | define('HDOM_QUOTE_DOUBLE', 0); 52 | define('HDOM_QUOTE_SINGLE', 1); 53 | define('HDOM_QUOTE_NO', 3); 54 | define('HDOM_INFO_BEGIN', 0); 55 | define('HDOM_INFO_END', 1); 56 | define('HDOM_INFO_QUOTE', 2); 57 | define('HDOM_INFO_SPACE', 3); 58 | define('HDOM_INFO_TEXT', 4); 59 | define('HDOM_INFO_INNER', 5); 60 | define('HDOM_INFO_OUTER', 6); 61 | define('HDOM_INFO_ENDSPACE',7); 62 | define('DEFAULT_TARGET_CHARSET', 'UTF-8'); 63 | define('DEFAULT_BR_TEXT', "\r\n"); 64 | define('DEFAULT_SPAN_TEXT', " "); 65 | define('MAX_FILE_SIZE', 600000); 66 | // helper functions 67 | // ----------------------------------------------------------------------------- 68 | // get html dom from file 69 | // $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1. 70 | function file_get_html($url, $use_include_path = false, $context=null, $offset = -1, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) 71 | { 72 | // We DO force the tags to be terminated. 73 | $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText); 74 | // For sourceforge users: uncomment the next line and comment the retreive_url_contents line 2 lines down if it is not already done. 75 | $contents = file_get_contents($url, $use_include_path, $context, $offset); 76 | // Paperg - use our own mechanism for getting the contents as we want to control the timeout. 77 | //$contents = retrieve_url_contents($url); 78 | if (empty($contents) || strlen($contents) > MAX_FILE_SIZE) 79 | { 80 | return false; 81 | } 82 | // The second parameter can force the selectors to all be lowercase. 83 | $dom->load($contents, $lowercase, $stripRN); 84 | return $dom; 85 | } 86 | 87 | // get html dom from string 88 | function str_get_html($str, $lowercase=true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) 89 | { 90 | $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText); 91 | if (empty($str) || strlen($str) > MAX_FILE_SIZE) 92 | { 93 | $dom->clear(); 94 | return false; 95 | } 96 | $dom->load($str, $lowercase, $stripRN); 97 | return $dom; 98 | } 99 | 100 | // dump html dom tree 101 | function dump_html_tree($node, $show_attr=true, $deep=0) 102 | { 103 | $node->dump($node); 104 | } 105 | 106 | 107 | /** 108 | * simple html dom node 109 | * PaperG - added ability for "find" routine to lowercase the value of the selector. 110 | * PaperG - added $tag_start to track the start position of the tag in the total byte index 111 | * 112 | * @package PlaceLocalInclude 113 | */ 114 | class simple_html_dom_node 115 | { 116 | public $nodetype = HDOM_TYPE_TEXT; 117 | public $tag = 'text'; 118 | public $attr = array(); 119 | public $children = array(); 120 | public $nodes = array(); 121 | public $parent = null; 122 | // The "info" array - see HDOM_INFO_... for what each element contains. 123 | public $_ = array(); 124 | public $tag_start = 0; 125 | private $dom = null; 126 | 127 | function __construct($dom) 128 | { 129 | $this->dom = $dom; 130 | $dom->nodes[] = $this; 131 | } 132 | 133 | function __destruct() 134 | { 135 | $this->clear(); 136 | } 137 | 138 | function __toString() 139 | { 140 | return $this->outertext(); 141 | } 142 | 143 | // clean up memory due to php5 circular references memory leak... 144 | function clear() 145 | { 146 | $this->dom = null; 147 | $this->nodes = null; 148 | $this->parent = null; 149 | $this->children = null; 150 | } 151 | 152 | // dump node's tree 153 | function dump($show_attr=true, $deep=0) 154 | { 155 | $lead = str_repeat(' ', $deep); 156 | 157 | echo $lead.$this->tag; 158 | if ($show_attr && count($this->attr)>0) 159 | { 160 | echo '('; 161 | foreach ($this->attr as $k=>$v) 162 | echo "[$k]=>\"".$this->$k.'", '; 163 | echo ')'; 164 | } 165 | echo "\n"; 166 | 167 | if ($this->nodes) 168 | { 169 | foreach ($this->nodes as $c) 170 | { 171 | $c->dump($show_attr, $deep+1); 172 | } 173 | } 174 | } 175 | 176 | 177 | // Debugging function to dump a single dom node with a bunch of information about it. 178 | function dump_node($echo=true) 179 | { 180 | 181 | $string = $this->tag; 182 | if (count($this->attr)>0) 183 | { 184 | $string .= '('; 185 | foreach ($this->attr as $k=>$v) 186 | { 187 | $string .= "[$k]=>\"".$this->$k.'", '; 188 | } 189 | $string .= ')'; 190 | } 191 | if (count($this->_)>0) 192 | { 193 | $string .= ' $_ ('; 194 | foreach ($this->_ as $k=>$v) 195 | { 196 | if (is_array($v)) 197 | { 198 | $string .= "[$k]=>("; 199 | foreach ($v as $k2=>$v2) 200 | { 201 | $string .= "[$k2]=>\"".$v2.'", '; 202 | } 203 | $string .= ")"; 204 | } else { 205 | $string .= "[$k]=>\"".$v.'", '; 206 | } 207 | } 208 | $string .= ")"; 209 | } 210 | 211 | if (isset($this->text)) 212 | { 213 | $string .= " text: (" . $this->text . ")"; 214 | } 215 | 216 | $string .= " HDOM_INNER_INFO: '"; 217 | if (isset($node->_[HDOM_INFO_INNER])) 218 | { 219 | $string .= $node->_[HDOM_INFO_INNER] . "'"; 220 | } 221 | else 222 | { 223 | $string .= ' NULL '; 224 | } 225 | 226 | $string .= " children: " . count($this->children); 227 | $string .= " nodes: " . count($this->nodes); 228 | $string .= " tag_start: " . $this->tag_start; 229 | $string .= "\n"; 230 | 231 | if ($echo) 232 | { 233 | echo $string; 234 | return; 235 | } 236 | else 237 | { 238 | return $string; 239 | } 240 | } 241 | 242 | // returns the parent of node 243 | // If a node is passed in, it will reset the parent of the current node to that one. 244 | function parent($parent=null) 245 | { 246 | // I am SURE that this doesn't work properly. 247 | // It fails to unset the current node from it's current parents nodes or children list first. 248 | if ($parent !== null) 249 | { 250 | $this->parent = $parent; 251 | $this->parent->nodes[] = $this; 252 | $this->parent->children[] = $this; 253 | } 254 | 255 | return $this->parent; 256 | } 257 | 258 | // verify that node has children 259 | function has_child() 260 | { 261 | return !empty($this->children); 262 | } 263 | 264 | // returns children of node 265 | function children($idx=-1) 266 | { 267 | if ($idx===-1) 268 | { 269 | return $this->children; 270 | } 271 | if (isset($this->children[$idx])) return $this->children[$idx]; 272 | return null; 273 | } 274 | 275 | // returns the first child of node 276 | function first_child() 277 | { 278 | if (count($this->children)>0) 279 | { 280 | return $this->children[0]; 281 | } 282 | return null; 283 | } 284 | 285 | // returns the last child of node 286 | function last_child() 287 | { 288 | if (($count=count($this->children))>0) 289 | { 290 | return $this->children[$count-1]; 291 | } 292 | return null; 293 | } 294 | 295 | // returns the next sibling of node 296 | function next_sibling() 297 | { 298 | if ($this->parent===null) 299 | { 300 | return null; 301 | } 302 | 303 | $idx = 0; 304 | $count = count($this->parent->children); 305 | while ($idx<$count && $this!==$this->parent->children[$idx]) 306 | { 307 | ++$idx; 308 | } 309 | if (++$idx>=$count) 310 | { 311 | return null; 312 | } 313 | return $this->parent->children[$idx]; 314 | } 315 | 316 | // returns the previous sibling of node 317 | function prev_sibling() 318 | { 319 | if ($this->parent===null) return null; 320 | $idx = 0; 321 | $count = count($this->parent->children); 322 | while ($idx<$count && $this!==$this->parent->children[$idx]) 323 | ++$idx; 324 | if (--$idx<0) return null; 325 | return $this->parent->children[$idx]; 326 | } 327 | 328 | // function to locate a specific ancestor tag in the path to the root. 329 | function find_ancestor_tag($tag) 330 | { 331 | global $debugObject; 332 | if (is_object($debugObject)) { $debugObject->debugLogEntry(1); } 333 | 334 | // Start by including ourselves in the comparison. 335 | $returnDom = $this; 336 | 337 | while (!is_null($returnDom)) 338 | { 339 | if (is_object($debugObject)) { $debugObject->debugLog(2, "Current tag is: " . $returnDom->tag); } 340 | 341 | if ($returnDom->tag == $tag) 342 | { 343 | break; 344 | } 345 | $returnDom = $returnDom->parent; 346 | } 347 | return $returnDom; 348 | } 349 | 350 | // get dom node's inner html 351 | function innertext() 352 | { 353 | if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; 354 | if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); 355 | 356 | $ret = ''; 357 | foreach ($this->nodes as $n) 358 | $ret .= $n->outertext(); 359 | return $ret; 360 | } 361 | 362 | // get dom node's outer text (with tag) 363 | function outertext() 364 | { 365 | global $debugObject; 366 | if (is_object($debugObject)) 367 | { 368 | $text = ''; 369 | if ($this->tag == 'text') 370 | { 371 | if (!empty($this->text)) 372 | { 373 | $text = " with text: " . $this->text; 374 | } 375 | } 376 | $debugObject->debugLog(1, 'Innertext of tag: ' . $this->tag . $text); 377 | } 378 | 379 | if ($this->tag==='root') return $this->innertext(); 380 | 381 | // trigger callback 382 | if ($this->dom && $this->dom->callback!==null) 383 | { 384 | call_user_func_array($this->dom->callback, array($this)); 385 | } 386 | 387 | if (isset($this->_[HDOM_INFO_OUTER])) return $this->_[HDOM_INFO_OUTER]; 388 | if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); 389 | 390 | // render begin tag 391 | if ($this->dom && $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]) 392 | { 393 | $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup(); 394 | } else { 395 | $ret = ""; 396 | } 397 | 398 | // render inner text 399 | if (isset($this->_[HDOM_INFO_INNER])) 400 | { 401 | // If it's a br tag... don't return the HDOM_INNER_INFO that we may or may not have added. 402 | if ($this->tag != "br") 403 | { 404 | $ret .= $this->_[HDOM_INFO_INNER]; 405 | } 406 | } else { 407 | if ($this->nodes) 408 | { 409 | foreach ($this->nodes as $n) 410 | { 411 | $ret .= $this->convert_text($n->outertext()); 412 | } 413 | } 414 | } 415 | 416 | // render end tag 417 | if (isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0) 418 | $ret .= 'tag.'>'; 419 | return $ret; 420 | } 421 | 422 | // get dom node's plain text 423 | function text() 424 | { 425 | if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; 426 | switch ($this->nodetype) 427 | { 428 | case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); 429 | case HDOM_TYPE_COMMENT: return ''; 430 | case HDOM_TYPE_UNKNOWN: return ''; 431 | } 432 | if (strcasecmp($this->tag, 'script')===0) return ''; 433 | if (strcasecmp($this->tag, 'style')===0) return ''; 434 | 435 | $ret = ''; 436 | // In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed for some span tags, and some p tags) $this->nodes is set to NULL. 437 | // NOTE: This indicates that there is a problem where it's set to NULL without a clear happening. 438 | // WHY is this happening? 439 | if (!is_null($this->nodes)) 440 | { 441 | foreach ($this->nodes as $n) 442 | { 443 | $ret .= $this->convert_text($n->text()); 444 | } 445 | 446 | // If this node is a span... add a space at the end of it so multiple spans don't run into each other. This is plaintext after all. 447 | if ($this->tag == "span") 448 | { 449 | $ret .= $this->dom->default_span_text; 450 | } 451 | 452 | 453 | } 454 | return $ret; 455 | } 456 | 457 | function xmltext() 458 | { 459 | $ret = $this->innertext(); 460 | $ret = str_ireplace('', '', $ret); 462 | return $ret; 463 | } 464 | 465 | // build node's text with tag 466 | function makeup() 467 | { 468 | // text, comment, unknown 469 | if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); 470 | 471 | $ret = '<'.$this->tag; 472 | $i = -1; 473 | 474 | foreach ($this->attr as $key=>$val) 475 | { 476 | ++$i; 477 | 478 | // skip removed attribute 479 | if ($val===null || $val===false) 480 | continue; 481 | 482 | $ret .= $this->_[HDOM_INFO_SPACE][$i][0]; 483 | //no value attr: nowrap, checked selected... 484 | if ($val===true) 485 | $ret .= $key; 486 | else { 487 | switch ($this->_[HDOM_INFO_QUOTE][$i]) 488 | { 489 | case HDOM_QUOTE_DOUBLE: $quote = '"'; break; 490 | case HDOM_QUOTE_SINGLE: $quote = '\''; break; 491 | default: $quote = ''; 492 | } 493 | $ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote; 494 | } 495 | } 496 | $ret = $this->dom->restore_noise($ret); 497 | return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>'; 498 | } 499 | 500 | // find elements by css selector 501 | //PaperG - added ability for find to lowercase the value of the selector. 502 | function find($selector, $idx=null, $lowercase=false) 503 | { 504 | $selectors = $this->parse_selector($selector); 505 | if (($count=count($selectors))===0) return array(); 506 | $found_keys = array(); 507 | 508 | // find each selector 509 | for ($c=0; $c<$count; ++$c) 510 | { 511 | // The change on the below line was documented on the sourceforge code tracker id 2788009 512 | // used to be: if (($levle=count($selectors[0]))===0) return array(); 513 | if (($levle=count($selectors[$c]))===0) return array(); 514 | if (!isset($this->_[HDOM_INFO_BEGIN])) return array(); 515 | 516 | $head = array($this->_[HDOM_INFO_BEGIN]=>1); 517 | 518 | // handle descendant selectors, no recursive! 519 | for ($l=0; $l<$levle; ++$l) 520 | { 521 | $ret = array(); 522 | foreach ($head as $k=>$v) 523 | { 524 | $n = ($k===-1) ? $this->dom->root : $this->dom->nodes[$k]; 525 | //PaperG - Pass this optional parameter on to the seek function. 526 | $n->seek($selectors[$c][$l], $ret, $lowercase); 527 | } 528 | $head = $ret; 529 | } 530 | 531 | foreach ($head as $k=>$v) 532 | { 533 | if (!isset($found_keys[$k])) 534 | $found_keys[$k] = 1; 535 | } 536 | } 537 | 538 | // sort keys 539 | ksort($found_keys); 540 | 541 | $found = array(); 542 | foreach ($found_keys as $k=>$v) 543 | $found[] = $this->dom->nodes[$k]; 544 | 545 | // return nth-element or array 546 | if (is_null($idx)) return $found; 547 | else if ($idx<0) $idx = count($found) + $idx; 548 | return (isset($found[$idx])) ? $found[$idx] : null; 549 | } 550 | 551 | // seek for given conditions 552 | // PaperG - added parameter to allow for case insensitive testing of the value of a selector. 553 | protected function seek($selector, &$ret, $lowercase=false) 554 | { 555 | global $debugObject; 556 | if (is_object($debugObject)) { $debugObject->debugLogEntry(1); } 557 | 558 | list($tag, $key, $val, $exp, $no_key) = $selector; 559 | 560 | // xpath index 561 | if ($tag && $key && is_numeric($key)) 562 | { 563 | $count = 0; 564 | foreach ($this->children as $c) 565 | { 566 | if ($tag==='*' || $tag===$c->tag) { 567 | if (++$count==$key) { 568 | $ret[$c->_[HDOM_INFO_BEGIN]] = 1; 569 | return; 570 | } 571 | } 572 | } 573 | return; 574 | } 575 | 576 | $end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0; 577 | if ($end==0) { 578 | $parent = $this->parent; 579 | while (!isset($parent->_[HDOM_INFO_END]) && $parent!==null) { 580 | $end -= 1; 581 | $parent = $parent->parent; 582 | } 583 | $end += $parent->_[HDOM_INFO_END]; 584 | } 585 | 586 | for ($i=$this->_[HDOM_INFO_BEGIN]+1; $i<$end; ++$i) { 587 | $node = $this->dom->nodes[$i]; 588 | 589 | $pass = true; 590 | 591 | if ($tag==='*' && !$key) { 592 | if (in_array($node, $this->children, true)) 593 | $ret[$i] = 1; 594 | continue; 595 | } 596 | 597 | // compare tag 598 | if ($tag && $tag!=$node->tag && $tag!=='*') {$pass=false;} 599 | // compare key 600 | if ($pass && $key) { 601 | if ($no_key) { 602 | if (isset($node->attr[$key])) $pass=false; 603 | } else { 604 | if (($key != "plaintext") && !isset($node->attr[$key])) $pass=false; 605 | } 606 | } 607 | // compare value 608 | if ($pass && $key && $val && $val!=='*') { 609 | // If they have told us that this is a "plaintext" search then we want the plaintext of the node - right? 610 | if ($key == "plaintext") { 611 | // $node->plaintext actually returns $node->text(); 612 | $nodeKeyValue = $node->text(); 613 | } else { 614 | // this is a normal search, we want the value of that attribute of the tag. 615 | $nodeKeyValue = $node->attr[$key]; 616 | } 617 | if (is_object($debugObject)) {$debugObject->debugLog(2, "testing node: " . $node->tag . " for attribute: " . $key . $exp . $val . " where nodes value is: " . $nodeKeyValue);} 618 | 619 | //PaperG - If lowercase is set, do a case insensitive test of the value of the selector. 620 | if ($lowercase) { 621 | $check = $this->match($exp, strtolower($val), strtolower($nodeKeyValue)); 622 | } else { 623 | $check = $this->match($exp, $val, $nodeKeyValue); 624 | } 625 | if (is_object($debugObject)) {$debugObject->debugLog(2, "after match: " . ($check ? "true" : "false"));} 626 | 627 | // handle multiple class 628 | if (!$check && strcasecmp($key, 'class')===0) { 629 | foreach (explode(' ',$node->attr[$key]) as $k) { 630 | // Without this, there were cases where leading, trailing, or double spaces lead to our comparing blanks - bad form. 631 | if (!empty($k)) { 632 | if ($lowercase) { 633 | $check = $this->match($exp, strtolower($val), strtolower($k)); 634 | } else { 635 | $check = $this->match($exp, $val, $k); 636 | } 637 | if ($check) break; 638 | } 639 | } 640 | } 641 | if (!$check) $pass = false; 642 | } 643 | if ($pass) $ret[$i] = 1; 644 | unset($node); 645 | } 646 | // It's passed by reference so this is actually what this function returns. 647 | if (is_object($debugObject)) {$debugObject->debugLog(1, "EXIT - ret: ", $ret);} 648 | } 649 | 650 | protected function match($exp, $pattern, $value) { 651 | global $debugObject; 652 | if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} 653 | 654 | switch ($exp) { 655 | case '=': 656 | return ($value===$pattern); 657 | case '!=': 658 | return ($value!==$pattern); 659 | case '^=': 660 | return preg_match("/^".preg_quote($pattern,'/')."/", $value); 661 | case '$=': 662 | return preg_match("/".preg_quote($pattern,'/')."$/", $value); 663 | case '*=': 664 | if ($pattern[0]=='/') { 665 | return preg_match($pattern, $value); 666 | } 667 | return preg_match("/".$pattern."/i", $value); 668 | } 669 | return false; 670 | } 671 | 672 | protected function parse_selector($selector_string) { 673 | global $debugObject; 674 | if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} 675 | 676 | // pattern of CSS selectors, modified from mootools 677 | // Paperg: Add the colon to the attrbute, so that it properly finds like google does. 678 | // Note: if you try to look at this attribute, yo MUST use getAttribute since $dom->x:y will fail the php syntax check. 679 | // Notice the \[ starting the attbute? and the @? following? This implies that an attribute can begin with an @ sign that is not captured. 680 | // This implies that an html attribute specifier may start with an @ sign that is NOT captured by the expression. 681 | // farther study is required to determine of this should be documented or removed. 682 | // $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; 683 | $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; 684 | preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER); 685 | if (is_object($debugObject)) {$debugObject->debugLog(2, "Matches Array: ", $matches);} 686 | 687 | $selectors = array(); 688 | $result = array(); 689 | //print_r($matches); 690 | 691 | foreach ($matches as $m) { 692 | $m[0] = trim($m[0]); 693 | if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue; 694 | // for browser generated xpath 695 | if ($m[1]==='tbody') continue; 696 | 697 | list($tag, $key, $val, $exp, $no_key) = array($m[1], null, null, '=', false); 698 | if (!empty($m[2])) {$key='id'; $val=$m[2];} 699 | if (!empty($m[3])) {$key='class'; $val=$m[3];} 700 | if (!empty($m[4])) {$key=$m[4];} 701 | if (!empty($m[5])) {$exp=$m[5];} 702 | if (!empty($m[6])) {$val=$m[6];} 703 | 704 | // convert to lowercase 705 | if ($this->dom->lowercase) {$tag=strtolower($tag); $key=strtolower($key);} 706 | //elements that do NOT have the specified attribute 707 | if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;} 708 | 709 | $result[] = array($tag, $key, $val, $exp, $no_key); 710 | if (trim($m[7])===',') { 711 | $selectors[] = $result; 712 | $result = array(); 713 | } 714 | } 715 | if (count($result)>0) 716 | $selectors[] = $result; 717 | return $selectors; 718 | } 719 | 720 | function __get($name) { 721 | if (isset($this->attr[$name])) 722 | { 723 | return $this->convert_text($this->attr[$name]); 724 | } 725 | switch ($name) { 726 | case 'outertext': return $this->outertext(); 727 | case 'innertext': return $this->innertext(); 728 | case 'plaintext': return $this->text(); 729 | case 'xmltext': return $this->xmltext(); 730 | default: return array_key_exists($name, $this->attr); 731 | } 732 | } 733 | 734 | function __set($name, $value) { 735 | switch ($name) { 736 | case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value; 737 | case 'innertext': 738 | if (isset($this->_[HDOM_INFO_TEXT])) return $this->_[HDOM_INFO_TEXT] = $value; 739 | return $this->_[HDOM_INFO_INNER] = $value; 740 | } 741 | if (!isset($this->attr[$name])) { 742 | $this->_[HDOM_INFO_SPACE][] = array(' ', '', ''); 743 | $this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE; 744 | } 745 | $this->attr[$name] = $value; 746 | } 747 | 748 | function __isset($name) { 749 | switch ($name) { 750 | case 'outertext': return true; 751 | case 'innertext': return true; 752 | case 'plaintext': return true; 753 | } 754 | //no value attr: nowrap, checked selected... 755 | return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]); 756 | } 757 | 758 | function __unset($name) { 759 | if (isset($this->attr[$name])) 760 | unset($this->attr[$name]); 761 | } 762 | 763 | // PaperG - Function to convert the text from one character set to another if the two sets are not the same. 764 | function convert_text($text) 765 | { 766 | global $debugObject; 767 | if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} 768 | 769 | $converted_text = $text; 770 | 771 | $sourceCharset = ""; 772 | $targetCharset = ""; 773 | 774 | if ($this->dom) 775 | { 776 | $sourceCharset = strtoupper($this->dom->_charset); 777 | $targetCharset = strtoupper($this->dom->_target_charset); 778 | } 779 | if (is_object($debugObject)) {$debugObject->debugLog(3, "source charset: " . $sourceCharset . " target charaset: " . $targetCharset);} 780 | 781 | if (!empty($sourceCharset) && !empty($targetCharset) && (strcasecmp($sourceCharset, $targetCharset) != 0)) 782 | { 783 | // Check if the reported encoding could have been incorrect and the text is actually already UTF-8 784 | if ((strcasecmp($targetCharset, 'UTF-8') == 0) && ($this->is_utf8($text))) 785 | { 786 | $converted_text = $text; 787 | } 788 | else 789 | { 790 | $converted_text = iconv($sourceCharset, $targetCharset, $text); 791 | } 792 | } 793 | 794 | // Lets make sure that we don't have that silly BOM issue with any of the utf-8 text we output. 795 | if ($targetCharset == 'UTF-8') 796 | { 797 | if (substr($converted_text, 0, 3) == "\xef\xbb\xbf") 798 | { 799 | $converted_text = substr($converted_text, 3); 800 | } 801 | if (substr($converted_text, -3) == "\xef\xbb\xbf") 802 | { 803 | $converted_text = substr($converted_text, 0, -3); 804 | } 805 | } 806 | 807 | return $converted_text; 808 | } 809 | 810 | /** 811 | * Returns true if $string is valid UTF-8 and false otherwise. 812 | * 813 | * @param mixed $str String to be tested 814 | * @return boolean 815 | */ 816 | static function is_utf8($str) 817 | { 818 | $c=0; $b=0; 819 | $bits=0; 820 | $len=strlen($str); 821 | for($i=0; $i<$len; $i++) 822 | { 823 | $c=ord($str[$i]); 824 | if($c > 128) 825 | { 826 | if(($c >= 254)) return false; 827 | elseif($c >= 252) $bits=6; 828 | elseif($c >= 248) $bits=5; 829 | elseif($c >= 240) $bits=4; 830 | elseif($c >= 224) $bits=3; 831 | elseif($c >= 192) $bits=2; 832 | else return false; 833 | if(($i+$bits) > $len) return false; 834 | while($bits > 1) 835 | { 836 | $i++; 837 | $b=ord($str[$i]); 838 | if($b < 128 || $b > 191) return false; 839 | $bits--; 840 | } 841 | } 842 | } 843 | return true; 844 | } 845 | /* 846 | function is_utf8($string) 847 | { 848 | //this is buggy 849 | return (utf8_encode(utf8_decode($string)) == $string); 850 | } 851 | */ 852 | 853 | /** 854 | * Function to try a few tricks to determine the displayed size of an img on the page. 855 | * NOTE: This will ONLY work on an IMG tag. Returns FALSE on all other tag types. 856 | * 857 | * @author John Schlick 858 | * @version April 19 2012 859 | * @return array an array containing the 'height' and 'width' of the image on the page or -1 if we can't figure it out. 860 | */ 861 | function get_display_size() 862 | { 863 | global $debugObject; 864 | 865 | $width = -1; 866 | $height = -1; 867 | 868 | if ($this->tag !== 'img') 869 | { 870 | return false; 871 | } 872 | 873 | // See if there is aheight or width attribute in the tag itself. 874 | if (isset($this->attr['width'])) 875 | { 876 | $width = $this->attr['width']; 877 | } 878 | 879 | if (isset($this->attr['height'])) 880 | { 881 | $height = $this->attr['height']; 882 | } 883 | 884 | // Now look for an inline style. 885 | if (isset($this->attr['style'])) 886 | { 887 | // Thanks to user gnarf from stackoverflow for this regular expression. 888 | $attributes = array(); 889 | preg_match_all("/([\w-]+)\s*:\s*([^;]+)\s*;?/", $this->attr['style'], $matches, PREG_SET_ORDER); 890 | foreach ($matches as $match) { 891 | $attributes[$match[1]] = $match[2]; 892 | } 893 | 894 | // If there is a width in the style attributes: 895 | if (isset($attributes['width']) && $width == -1) 896 | { 897 | // check that the last two characters are px (pixels) 898 | if (strtolower(substr($attributes['width'], -2)) == 'px') 899 | { 900 | $proposed_width = substr($attributes['width'], 0, -2); 901 | // Now make sure that it's an integer and not something stupid. 902 | if (filter_var($proposed_width, FILTER_VALIDATE_INT)) 903 | { 904 | $width = $proposed_width; 905 | } 906 | } 907 | } 908 | 909 | // If there is a width in the style attributes: 910 | if (isset($attributes['height']) && $height == -1) 911 | { 912 | // check that the last two characters are px (pixels) 913 | if (strtolower(substr($attributes['height'], -2)) == 'px') 914 | { 915 | $proposed_height = substr($attributes['height'], 0, -2); 916 | // Now make sure that it's an integer and not something stupid. 917 | if (filter_var($proposed_height, FILTER_VALIDATE_INT)) 918 | { 919 | $height = $proposed_height; 920 | } 921 | } 922 | } 923 | 924 | } 925 | 926 | // Future enhancement: 927 | // Look in the tag to see if there is a class or id specified that has a height or width attribute to it. 928 | 929 | // Far future enhancement 930 | // Look at all the parent tags of this image to see if they specify a class or id that has an img selector that specifies a height or width 931 | // Note that in this case, the class or id will have the img subselector for it to apply to the image. 932 | 933 | // ridiculously far future development 934 | // If the class or id is specified in a SEPARATE css file thats not on the page, go get it and do what we were just doing for the ones on the page. 935 | 936 | $result = array('height' => $height, 937 | 'width' => $width); 938 | return $result; 939 | } 940 | 941 | // camel naming conventions 942 | function getAllAttributes() {return $this->attr;} 943 | function getAttribute($name) {return $this->__get($name);} 944 | function setAttribute($name, $value) {$this->__set($name, $value);} 945 | function hasAttribute($name) {return $this->__isset($name);} 946 | function removeAttribute($name) {$this->__set($name, null);} 947 | function getElementById($id) {return $this->find("#$id", 0);} 948 | function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);} 949 | function getElementByTagName($name) {return $this->find($name, 0);} 950 | function getElementsByTagName($name, $idx=null) {return $this->find($name, $idx);} 951 | function parentNode() {return $this->parent();} 952 | function childNodes($idx=-1) {return $this->children($idx);} 953 | function firstChild() {return $this->first_child();} 954 | function lastChild() {return $this->last_child();} 955 | function nextSibling() {return $this->next_sibling();} 956 | function previousSibling() {return $this->prev_sibling();} 957 | function hasChildNodes() {return $this->has_child();} 958 | function nodeName() {return $this->tag;} 959 | function appendChild($node) {$node->parent($this); return $node;} 960 | 961 | } 962 | 963 | /** 964 | * simple html dom parser 965 | * Paperg - in the find routine: allow us to specify that we want case insensitive testing of the value of the selector. 966 | * Paperg - change $size from protected to public so we can easily access it 967 | * Paperg - added ForceTagsClosed in the constructor which tells us whether we trust the html or not. Default is to NOT trust it. 968 | * 969 | * @package PlaceLocalInclude 970 | */ 971 | class simple_html_dom 972 | { 973 | public $root = null; 974 | public $nodes = array(); 975 | public $callback = null; 976 | public $lowercase = false; 977 | // Used to keep track of how large the text was when we started. 978 | public $original_size; 979 | public $size; 980 | protected $pos; 981 | protected $doc; 982 | protected $char; 983 | protected $cursor; 984 | protected $parent; 985 | protected $noise = array(); 986 | protected $token_blank = " \t\r\n"; 987 | protected $token_equal = ' =/>'; 988 | protected $token_slash = " />\r\n\t"; 989 | protected $token_attr = ' >'; 990 | // Note that this is referenced by a child node, and so it needs to be public for that node to see this information. 991 | public $_charset = ''; 992 | public $_target_charset = ''; 993 | protected $default_br_text = ""; 994 | public $default_span_text = ""; 995 | 996 | // use isset instead of in_array, performance boost about 30%... 997 | protected $self_closing_tags = array('img'=>1, 'br'=>1, 'input'=>1, 'meta'=>1, 'link'=>1, 'hr'=>1, 'base'=>1, 'embed'=>1, 'spacer'=>1); 998 | protected $block_tags = array('root'=>1, 'body'=>1, 'form'=>1, 'div'=>1, 'span'=>1, 'table'=>1); 999 | // Known sourceforge issue #2977341 1000 | // B tags that are not closed cause us to return everything to the end of the document. 1001 | protected $optional_closing_tags = array( 1002 | 'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1), 1003 | 'th'=>array('th'=>1), 1004 | 'td'=>array('td'=>1), 1005 | 'li'=>array('li'=>1), 1006 | 'dt'=>array('dt'=>1, 'dd'=>1), 1007 | 'dd'=>array('dd'=>1, 'dt'=>1), 1008 | 'dl'=>array('dd'=>1, 'dt'=>1), 1009 | 'p'=>array('p'=>1), 1010 | 'nobr'=>array('nobr'=>1), 1011 | 'b'=>array('b'=>1), 1012 | 'option'=>array('option'=>1), 1013 | ); 1014 | 1015 | function __construct($str=null, $lowercase=true, $forceTagsClosed=true, $target_charset=DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) 1016 | { 1017 | if ($str) 1018 | { 1019 | if (preg_match("/^http:\/\//i",$str) || is_file($str)) 1020 | { 1021 | $this->load_file($str); 1022 | } 1023 | else 1024 | { 1025 | $this->load($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText); 1026 | } 1027 | } 1028 | // Forcing tags to be closed implies that we don't trust the html, but it can lead to parsing errors if we SHOULD trust the html. 1029 | if (!$forceTagsClosed) { 1030 | $this->optional_closing_array=array(); 1031 | } 1032 | $this->_target_charset = $target_charset; 1033 | } 1034 | 1035 | function __destruct() 1036 | { 1037 | $this->clear(); 1038 | } 1039 | 1040 | // load html from string 1041 | function load($str, $lowercase=true, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) 1042 | { 1043 | global $debugObject; 1044 | 1045 | // prepare 1046 | $this->prepare($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText); 1047 | // strip out comments 1048 | $this->remove_noise("''is"); 1049 | // strip out cdata 1050 | $this->remove_noise("''is", true); 1051 | // Per sourceforge http://sourceforge.net/tracker/?func=detail&aid=2949097&group_id=218559&atid=1044037 1052 | // Script tags removal now preceeds style tag removal. 1053 | // strip out