|
1
|
|
|
<?php declare(strict_types=1); defined('BASEPATH') OR exit('No direct script access allowed'); |
|
2
|
|
|
|
|
3
|
|
|
abstract class Site_Model extends CI_Model { |
|
4
|
102 |
|
public function __construct() { |
|
5
|
102 |
|
parent::__construct(); |
|
6
|
|
|
|
|
7
|
102 |
|
$this->load->database(); |
|
8
|
102 |
|
} |
|
9
|
|
|
|
|
10
|
|
|
abstract public function getFullTitleURL(string $title_url) : string; |
|
11
|
|
|
|
|
12
|
|
|
abstract public function getChapterData(string $title_url, string $chapter) : array; |
|
13
|
|
|
|
|
14
|
|
|
//TODO: When ci-phpunit-test supports PHP Parser 3.x, add " : ?array" |
|
15
|
|
|
abstract public function getTitleData(string $title_url); |
|
16
|
|
|
|
|
17
|
|
|
abstract public function isValidTitleURL(string $title_url) : bool; |
|
18
|
|
|
abstract public function isValidChapter(string $chapter) : bool; |
|
19
|
|
|
|
|
20
|
14 |
|
final protected function get_content(string $url, string $cookie_string = "", string $cookiejar_path = "", bool $follow_redirect = FALSE) { |
|
21
|
14 |
|
$ch = curl_init(); |
|
22
|
14 |
|
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); |
|
23
|
14 |
|
curl_setopt($ch, CURLOPT_ENCODING , "gzip"); |
|
24
|
|
|
//curl_setopt($ch, CURLOPT_VERBOSE, 1); |
|
25
|
14 |
|
curl_setopt($ch, CURLOPT_HEADER, 1); |
|
26
|
|
|
|
|
27
|
14 |
|
if($follow_redirect) curl_setopt($ch, CURLOPT_FOLLOWLOCATION, TRUE); |
|
28
|
|
|
|
|
29
|
14 |
|
if(!empty($cookie_string)) curl_setopt($ch, CURLOPT_COOKIE, $cookie_string); |
|
30
|
14 |
|
if(!empty($cookiejar_path)) curl_setopt($ch, CURLOPT_COOKIEFILE, $cookiejar_path); |
|
31
|
|
|
|
|
32
|
|
|
//Some sites check the useragent for stuff, use a pre-defined user-agent to avoid stuff. |
|
33
|
14 |
|
curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2824.0 Safari/537.36'); |
|
34
|
|
|
|
|
35
|
|
|
//TODO: Check in a while if this being enabled still causes issues |
|
36
|
|
|
//curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE); //FIXME: This isn't safe, but it allows us to grab SSL URLs |
|
37
|
|
|
|
|
38
|
14 |
|
curl_setopt($ch, CURLOPT_URL, $url); |
|
39
|
14 |
|
$response = curl_exec($ch); |
|
40
|
|
|
|
|
41
|
14 |
|
$status_code = curl_getinfo($ch, CURLINFO_HTTP_CODE); |
|
42
|
14 |
|
$header_size = curl_getinfo($ch, CURLINFO_HEADER_SIZE); |
|
43
|
14 |
|
$header = http_parse_headers(substr($response, 0, $header_size)); |
|
44
|
14 |
|
$body = substr($response, $header_size); |
|
45
|
14 |
|
curl_close($ch); |
|
46
|
|
|
|
|
47
|
|
|
return [ |
|
48
|
14 |
|
'headers' => $header, |
|
49
|
14 |
|
'status_code' => $status_code, |
|
50
|
14 |
|
'body' => $body |
|
51
|
|
|
]; |
|
52
|
|
|
} |
|
53
|
|
|
|
|
54
|
|
|
/** |
|
55
|
|
|
* @param array $content |
|
56
|
|
|
* @param string $site |
|
57
|
|
|
* @param string $title_url |
|
58
|
|
|
* @param string $node_title_string |
|
59
|
|
|
* @param string $node_row_string |
|
60
|
|
|
* @param string $node_latest_string |
|
61
|
|
|
* @param string $node_chapter_string |
|
62
|
|
|
* @param string $failure_string |
|
63
|
|
|
* |
|
64
|
|
|
* @return DOMElement[]|false |
|
65
|
|
|
*/ |
|
66
|
7 |
|
final protected function parseTitleDataDOM( |
|
67
|
|
|
array $content, string $site, string $title_url, |
|
68
|
|
|
string $node_title_string, string $node_row_string, |
|
69
|
|
|
string $node_latest_string, string $node_chapter_string, |
|
70
|
|
|
string $failure_string = "") { |
|
71
|
|
|
//list('headers' => $headers, 'status_code' => $status_code, 'body' => $data) = $content; //TODO: PHP 7.1 |
|
72
|
7 |
|
$headers = $content['headers']; |
|
|
|
|
|
|
73
|
7 |
|
$status_code = $content['status_code']; |
|
74
|
7 |
|
$data = $content['body']; |
|
75
|
|
|
|
|
76
|
7 |
|
if(!($status_code >= 200 && $status_code < 300)) { |
|
77
|
3 |
|
log_message('error', "{$site} : {$title_url} | Bad Status Code ({$status_code})"); |
|
78
|
4 |
|
} else if(empty($data)) { |
|
79
|
|
|
log_message('error', "{$site} : {$title_url} | Data is empty? (Status code: {$status_code})"); |
|
80
|
4 |
|
} else if($failure_string !== "" && strpos($data, $failure_string) !== FALSE) { |
|
81
|
1 |
|
log_message('error', "{$site} : {$title_url} | Failure string matched"); |
|
82
|
|
|
} else { |
|
83
|
3 |
|
$data = $this->cleanTitleDataDOM($data); //This allows us to clean the DOM prior to parsing. It's faster to grab the only part we need THEN parse it. |
|
84
|
|
|
|
|
85
|
3 |
|
$dom = new DOMDocument(); |
|
86
|
3 |
|
libxml_use_internal_errors(TRUE); |
|
87
|
3 |
|
$dom->loadHTML($data); |
|
88
|
3 |
|
libxml_use_internal_errors(FALSE); |
|
89
|
|
|
|
|
90
|
3 |
|
$xpath = new DOMXPath($dom); |
|
|
|
|
|
|
91
|
3 |
|
$nodes_title = $xpath->query($node_title_string); |
|
92
|
3 |
|
$nodes_row = $xpath->query($node_row_string); |
|
93
|
3 |
|
if($nodes_title->length === 1 && $nodes_row->length === 1) { |
|
94
|
3 |
|
$firstRow = $nodes_row->item(0); |
|
95
|
3 |
|
$nodes_latest = $xpath->query($node_latest_string, $firstRow); |
|
96
|
3 |
|
$nodes_chapter = $xpath->query($node_chapter_string, $firstRow); |
|
97
|
|
|
|
|
98
|
3 |
|
if($nodes_latest->length === 1 && $nodes_chapter->length === 1) { |
|
99
|
|
|
return [ |
|
100
|
3 |
|
'nodes_title' => $nodes_title->item(0), |
|
101
|
3 |
|
'nodes_latest' => $nodes_latest->item(0), |
|
102
|
3 |
|
'nodes_chapter' => $nodes_chapter->item(0) |
|
103
|
|
|
]; |
|
104
|
|
|
} else { |
|
105
|
|
|
log_message('error', "{$site} : {$title_url} | Invalid amount of nodes (LATEST: {$nodes_latest->length} | CHAPTER: {$nodes_chapter->length})"); |
|
106
|
|
|
} |
|
107
|
|
|
} else { |
|
108
|
|
|
log_message('error', "{$site} : {$title_url} | Invalid amount of nodes (TITLE: {$nodes_title->length} | ROW: {$nodes_row->length})"); |
|
109
|
|
|
} |
|
110
|
|
|
} |
|
111
|
4 |
|
return FALSE; |
|
112
|
|
|
} |
|
113
|
|
|
|
|
114
|
3 |
|
public function cleanTitleDataDOM(string $data) : string { |
|
115
|
3 |
|
return $data; |
|
116
|
|
|
} |
|
117
|
|
|
} |
|
118
|
|
|
class Sites_Model extends CI_Model { |
|
119
|
|
|
public $MangaFox; |
|
120
|
|
|
public $MangaHere; |
|
121
|
|
|
public $Batoto; |
|
122
|
|
|
public $DynastyScans; |
|
123
|
|
|
public $MangaPanda; |
|
124
|
|
|
public $MangaStream; |
|
125
|
|
|
public $WebToons; |
|
126
|
|
|
public $KissManga; |
|
127
|
|
|
public $KireiCake; |
|
128
|
|
|
public $GameOfScanlation; |
|
129
|
|
|
public $MangaCow; |
|
130
|
|
|
public $SeaOtterScans; |
|
131
|
|
|
public $HelveticaScans; |
|
132
|
|
|
public $SenseScans; |
|
133
|
|
|
|
|
134
|
102 |
|
public function __construct() { |
|
135
|
102 |
|
parent::__construct(); |
|
136
|
|
|
|
|
137
|
102 |
|
$this->MangaFox = new MangaFox(); |
|
138
|
102 |
|
$this->MangaHere = new MangaHere(); |
|
139
|
102 |
|
$this->Batoto = new Batoto(); |
|
140
|
102 |
|
$this->DynastyScans = new DynastyScans(); |
|
141
|
102 |
|
$this->MangaPanda = new MangaPanda(); |
|
142
|
102 |
|
$this->MangaStream = new MangaStream(); |
|
143
|
102 |
|
$this->WebToons = new WebToons(); |
|
144
|
102 |
|
$this->KissManga = new KissManga(); |
|
145
|
102 |
|
$this->KireiCake = new KireiCake(); |
|
146
|
102 |
|
$this->GameOfScanlation = new GameOfScanlation(); |
|
147
|
102 |
|
$this->MangaCow = new MangaCow(); |
|
148
|
102 |
|
$this->SeaOtterScans = new SeaOtterScans(); |
|
149
|
102 |
|
$this->HelveticaScans = new HelveticaScans(); |
|
150
|
102 |
|
$this->SenseScans = new SenseScans(); |
|
151
|
102 |
|
} |
|
152
|
|
|
} |
|
153
|
|
|
|
|
154
|
|
|
class MangaFox extends Site_Model { |
|
155
|
2 |
|
public function getFullTitleURL(string $title_url) : string { |
|
156
|
2 |
|
return "http://mangafox.me/manga/{$title_url}/"; |
|
157
|
|
|
} |
|
158
|
|
|
|
|
159
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
160
|
|
|
$success = (bool) preg_match('/^[a-z0-9_]+$/', $title_url); |
|
161
|
|
|
if(!$success) log_message('error', "Invalid Title URL (MangaFox): {$title_url}"); |
|
162
|
|
|
return $success; |
|
163
|
|
|
} |
|
164
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
165
|
|
|
$success = (bool) preg_match('/^(?:v[0-9a-zA-Z]+\/)?c[0-9\.]+$/', $chapter); |
|
166
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (MangaFox): '.$chapter); |
|
167
|
|
|
return $success; |
|
168
|
|
|
} |
|
169
|
|
|
|
|
170
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
171
|
|
|
return [ |
|
172
|
|
|
'url' => "http://mangafox.me/manga/{$title_url}/{$chapter}/", |
|
173
|
|
|
'number' => $chapter |
|
174
|
|
|
]; |
|
175
|
|
|
} |
|
176
|
|
|
|
|
177
|
2 |
|
public function getTitleData(string $title_url) { |
|
178
|
2 |
|
$titleData = []; |
|
179
|
|
|
|
|
180
|
2 |
|
$fullURL = $this->getFullTitleURL($title_url); |
|
181
|
2 |
|
$content = $this->get_content($fullURL); |
|
182
|
|
|
|
|
183
|
2 |
|
$data = $this->parseTitleDataDOM( |
|
184
|
|
|
$content, |
|
185
|
2 |
|
'MangaFox', |
|
186
|
|
|
$title_url, |
|
187
|
2 |
|
"//meta[@property='og:title']/@content", |
|
188
|
2 |
|
"//body/div[@id='page']/div[@class='left']/div[@id='chapters']/ul[1]/li[1]", |
|
189
|
2 |
|
"div/span[@class='date']", |
|
190
|
2 |
|
"div/h3/a" |
|
191
|
|
|
); |
|
192
|
2 |
|
if($data) { |
|
193
|
1 |
|
$titleData['title'] = html_entity_decode(substr($data['nodes_title']->textContent, 0, -6)); |
|
194
|
|
|
|
|
195
|
1 |
|
$link = preg_replace('/^(.*\/)(?:[0-9]+\.html)?$/', '$1', (string) $data['nodes_chapter']->getAttribute('href')); |
|
|
|
|
|
|
196
|
1 |
|
$chapterURLSegments = explode('/', $link); |
|
|
|
|
|
|
197
|
1 |
|
$titleData['latest_chapter'] = $chapterURLSegments[5] . (isset($chapterURLSegments[6]) && !empty($chapterURLSegments[6]) ? "/{$chapterURLSegments[6]}" : ""); |
|
198
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) $data['nodes_latest']->nodeValue)); |
|
|
|
|
|
|
199
|
|
|
} |
|
200
|
|
|
|
|
201
|
2 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
202
|
|
|
} |
|
203
|
|
|
} |
|
204
|
|
|
|
|
205
|
|
|
class MangaHere extends Site_Model { |
|
206
|
2 |
|
public function getFullTitleURL(string $title_url) : string { |
|
207
|
2 |
|
return "http://www.mangahere.co/manga/{$title_url}/"; |
|
208
|
|
|
} |
|
209
|
|
|
|
|
210
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
211
|
|
|
$success = (bool) preg_match('/^[a-z0-9_]+$/', $title_url); |
|
212
|
|
|
if(!$success) log_message('error', "Invalid Title URL (MangaFox): {$title_url}"); |
|
213
|
|
|
return $success; |
|
214
|
|
|
} |
|
215
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
216
|
|
|
$success = (bool) preg_match('/^(?:v[0-9]+\/)?c[0-9]+(?:\.[0-9]+)?$/', $chapter); |
|
217
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (MangaFox): '.$chapter); |
|
218
|
|
|
return $success; |
|
219
|
|
|
} |
|
220
|
|
|
|
|
221
|
|
|
public function getChapterData(string $title, string $chapter) : array { |
|
222
|
|
|
return [ |
|
223
|
|
|
'url' => "http://www.mangahere.co/manga/{$title}/{$chapter}/", |
|
224
|
|
|
'number' => $chapter |
|
225
|
|
|
]; |
|
226
|
|
|
} |
|
227
|
|
|
|
|
228
|
2 |
|
public function getTitleData(string $title_url) { |
|
229
|
2 |
|
$titleData = []; |
|
230
|
|
|
|
|
231
|
2 |
|
$fullURL = $this->getFullTitleURL($title_url); |
|
232
|
2 |
|
$content = $this->get_content($fullURL); |
|
233
|
|
|
|
|
234
|
2 |
|
$data = $this->parseTitleDataDOM( |
|
235
|
|
|
$content, |
|
236
|
2 |
|
'MangaHere', |
|
237
|
|
|
$title_url, |
|
238
|
2 |
|
"//meta[@property='og:title']/@content", |
|
239
|
2 |
|
"//body/section/article/div/div[@class='manga_detail']/div[@class='detail_list']/ul[1]/li[1]", |
|
240
|
2 |
|
"span[@class='right']", |
|
241
|
2 |
|
"span[@class='left']/a", |
|
242
|
2 |
|
"<div class=\"error_text\">Sorry, the page you have requested can’t be found." |
|
243
|
|
|
); |
|
244
|
2 |
|
if($data) { |
|
245
|
1 |
|
$titleData['title'] = $data['nodes_title']->textContent; |
|
246
|
|
|
|
|
247
|
1 |
|
$link = preg_replace('/^(.*\/)(?:[0-9]+\.html)?$/', '$1', (string) $data['nodes_chapter']->getAttribute('href')); |
|
|
|
|
|
|
248
|
1 |
|
$chapterURLSegments = explode('/', $link); |
|
|
|
|
|
|
249
|
1 |
|
$titleData['latest_chapter'] = $chapterURLSegments[5] . (isset($chapterURLSegments[6]) && !empty($chapterURLSegments[6]) ? "/{$chapterURLSegments[6]}" : ""); |
|
250
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) $data['nodes_latest']->nodeValue)); |
|
|
|
|
|
|
251
|
|
|
} |
|
252
|
|
|
|
|
253
|
2 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
254
|
|
|
} |
|
255
|
|
|
} |
|
256
|
|
|
|
|
257
|
|
|
class Batoto extends Site_Model { |
|
258
|
|
|
//Batoto is a bit tricky to track. Unlike MangaFox and MangaHere, it doesn't store anything in the title_url, which means we have to get the data via other methods. |
|
259
|
|
|
//One problem we have though, is the tracker must support multiple sites, so this means we need to do some weird things to track Batoto. |
|
260
|
|
|
//title_url is stored like: "TITLE_URL:--:LANGUAGE" |
|
261
|
|
|
//chapter_urls are stored like "CHAPTER_ID:--:CHAPTER_NUMBER" |
|
262
|
|
|
|
|
263
|
1 |
|
public function getFullTitleURL(string $title_string) : string { |
|
264
|
|
|
//FIXME: This does not point to the language specific title page. Should ask if it is possible to set LANG as arg? |
|
265
|
|
|
//FIXME: This points to a generic URL which will redirect according to the ID. Preferably we'd try and get the exact URL from the title, but we can't pass it here. |
|
266
|
1 |
|
$title_parts = explode(':--:', $title_string); |
|
267
|
1 |
|
return "http://bato.to/comic/_/comics/-r".$title_parts[0]; |
|
268
|
|
|
} |
|
269
|
|
|
|
|
270
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
271
|
|
|
$success = (bool) preg_match('/^[0-9]+:--:(?:English|Spanish|French|German|Portuguese|Turkish|Indonesian|Greek|Filipino|Italian|Polish|Thai|Malay|Hungarian|Romanian|Arabic|Hebrew|Russian|Vietnamese|Dutch)$/', $title_url); |
|
272
|
|
|
if(!$success) log_message('error', "Invalid Title URL (Batoto): {$title_url}"); |
|
273
|
|
|
return $success; |
|
274
|
|
|
} |
|
275
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
276
|
|
|
//FIXME: We're not validating the chapter name since we don't know what all the possible valid characters can be |
|
277
|
|
|
// Preferably we'd just use /^[0-9a-z]+:--:(v[0-9]+\/)?c[0-9]+(\.[0-9]+)?$/ |
|
278
|
|
|
|
|
279
|
|
|
$success = (bool) preg_match('/^[0-9a-z]+:--:.+$/', $chapter); |
|
280
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (Batoto): '.$chapter); |
|
281
|
|
|
return $success; |
|
282
|
|
|
} |
|
283
|
|
|
|
|
284
|
|
View Code Duplication |
public function getChapterData(string $title_string, string $chapter) : array { |
|
285
|
|
|
//$title_string isn't used here. |
|
286
|
|
|
|
|
287
|
|
|
$chapter_parts = explode(':--:', $chapter); |
|
288
|
|
|
return [ |
|
289
|
|
|
'url' => "http://bato.to/reader#" . $chapter_parts[0], |
|
290
|
|
|
'number' => $chapter_parts[1] |
|
291
|
|
|
]; |
|
292
|
|
|
} |
|
293
|
|
|
|
|
294
|
1 |
|
public function getTitleData(string $title_url) { |
|
295
|
1 |
|
$titleData = []; |
|
296
|
|
|
|
|
297
|
1 |
|
$title_parts = explode(':--:', $title_url); |
|
298
|
1 |
|
$fullURL = $this->getFullTitleURL($title_url); |
|
299
|
1 |
|
$lang = $title_parts[1]; //TODO: Validate title_lang from array? |
|
300
|
|
|
|
|
301
|
|
|
|
|
302
|
|
|
//Bato.to is annoying and locks stuff behind auth. See: https://github.com/DakuTree/manga-tracker/issues/14#issuecomment-233830855 |
|
303
|
|
|
$cookies = [ |
|
304
|
1 |
|
"lang_option={$lang}", |
|
305
|
1 |
|
"member_id={$this->config->item('batoto_cookie_member_id')}", |
|
306
|
1 |
|
"pass_hash={$this->config->item('batoto_cookie_pass_hash')}" |
|
307
|
|
|
]; |
|
308
|
1 |
|
$content = $this->get_content($fullURL, implode("; ", $cookies), "", TRUE); |
|
309
|
|
|
|
|
310
|
1 |
|
$data = $this->parseTitleDataDOM( |
|
311
|
|
|
$content, |
|
312
|
1 |
|
'Batoto', |
|
313
|
|
|
$title_url, |
|
314
|
1 |
|
"//h1[@class='ipsType_pagetitle']", |
|
315
|
1 |
|
"//table[contains(@class, 'chapters_list')]/tbody/tr[2]", |
|
316
|
1 |
|
"td[last()]", |
|
317
|
1 |
|
"td/a[contains(@href,'reader')]", |
|
318
|
1 |
|
">Register now<" |
|
319
|
|
|
); |
|
320
|
1 |
|
if($data) { |
|
321
|
|
|
$titleData['title'] = html_entity_decode(trim($data['nodes_title']->textContent)); |
|
322
|
|
|
|
|
323
|
|
|
///^(?:Vol\.(?<volume>\S+) )?(?:Ch.(?<chapter>[^\s:]+)(?:\s?-\s?(?<extra>[0-9]+))?):?.*/ |
|
324
|
|
|
preg_match('/^(?:Vol\.(?<volume>\S+) )?(?:Ch.(?<chapter>[^\s:]+)(?:\s?-\s?(?<extra>[0-9]+))?):?.*/', trim($data['nodes_chapter']->nodeValue), $text); |
|
325
|
|
|
$titleData['latest_chapter'] = substr($data['nodes_chapter']->getAttribute('href'), 22) . ':--:' . ((!empty($text['volume']) ? 'v'.$text['volume'].'/' : '') . 'c'.$text['chapter'] . (!empty($text['extra']) ? '-'.$text['extra'] : '')); |
|
326
|
|
|
|
|
327
|
|
|
$dateString = $data['nodes_latest']->nodeValue; |
|
328
|
|
|
if($dateString == 'An hour ago') { |
|
329
|
|
|
$dateString = '1 hour ago'; |
|
330
|
|
|
} |
|
331
|
|
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime(preg_replace('/ (-|\[A\]).*$/', '', $dateString))); |
|
|
|
|
|
|
332
|
|
|
} |
|
333
|
|
|
|
|
334
|
1 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
335
|
|
|
} |
|
336
|
|
|
|
|
337
|
|
|
public function cleanTitleDataDOM(string $data) : string { |
|
338
|
|
|
$data = preg_replace('/^[\s\S]+<!-- ::: CONTENT ::: -->/', '<!-- ::: CONTENT ::: -->', $data); |
|
339
|
|
|
$data = preg_replace('/<!-- end mainContent -->[\s\S]+$/', '<!-- end mainContent -->', $data); |
|
340
|
|
|
$data = preg_replace('/<div id=\'commentsStart\' class=\'ipsBox\'>[\s\S]+$/', '</div></div><!-- end mainContent -->', $data); |
|
341
|
|
|
|
|
342
|
|
|
return $data; |
|
343
|
|
|
} |
|
344
|
|
|
} |
|
345
|
|
|
|
|
346
|
|
|
//FIXME: Convert DynastyScans to new format. |
|
347
|
|
|
class DynastyScans extends Site_Model { |
|
348
|
|
|
//FIXME: This has some major issues. SEE: https://github.com/DakuTree/manga-tracker/issues/58 |
|
349
|
|
|
public function getFullTitleURL(string $title_string) : string { |
|
350
|
|
|
$title_parts = explode(':--:', $title_string); |
|
351
|
|
|
$url_type = ($title_parts[1] == '0' ? 'series' : 'chapters'); |
|
|
|
|
|
|
352
|
|
|
|
|
353
|
|
|
return 'http://dynasty-scans.com/'.$url_type.'/'.$title_parts[0]; |
|
354
|
|
|
} |
|
355
|
|
|
|
|
356
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
357
|
|
|
$success = (bool) preg_match('/^[a-z0-9_]+:--:(?:0|1)$/', $title_url); |
|
358
|
|
|
if(!$success) log_message('error', "Invalid Title URL (DynastyScans): {$title_url}"); |
|
359
|
|
|
return $success; |
|
360
|
|
|
} |
|
361
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
362
|
|
|
$success = (bool) preg_match('/^[0-9a-z_]+$/', $chapter); |
|
363
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (DynastyScans): '.$chapter); |
|
364
|
|
|
return $success; |
|
365
|
|
|
} |
|
366
|
|
|
|
|
367
|
|
|
public function getChapterData(string $title_string, string $chapter) : array { |
|
368
|
|
|
$title_parts = explode(':--:', $title_string); |
|
369
|
|
|
/* Known chapter url formats (# is numbers): |
|
370
|
|
|
chapters_#A_#B - Ch#A-#B |
|
371
|
|
|
ch_#A - Ch#A |
|
372
|
|
|
ch_#A_#B - Ch#A.#B |
|
373
|
|
|
<NOTHING> - Oneshot (This is passed as "oneshot") |
|
374
|
|
|
*/ |
|
375
|
|
|
|
|
376
|
|
|
$chapterData = [ |
|
377
|
|
|
'url' => 'http://dynasty-scans.com/chapters/' . $title_parts[0].'_'.$chapter, |
|
378
|
|
|
'number' => '' |
|
379
|
|
|
]; |
|
380
|
|
|
|
|
381
|
|
|
if($chapter == 'oneshot') { |
|
382
|
|
|
$chapterData['number'] = 'oneshot'; |
|
383
|
|
|
} else { |
|
384
|
|
|
$chapter = preg_replace("/^([a-zA-Z]+)/", '$1_', $chapter); |
|
|
|
|
|
|
385
|
|
|
$chapterSegments = explode('_', $chapter); |
|
386
|
|
|
switch($chapterSegments[0]) { |
|
387
|
|
|
case 'ch': |
|
388
|
|
|
$chapterData['number'] = 'c'.$chapterSegments[1].(isset($chapterSegments[2]) && !empty($chapterSegments[2]) ? '.'.$chapterSegments[2] : ''); |
|
389
|
|
|
break; |
|
390
|
|
|
|
|
391
|
|
|
case 'chapters': |
|
392
|
|
|
//This is barely ever used, but I have seen it. |
|
393
|
|
|
$chapterData['number'] = 'c'.$chapterSegments[1].'-'.$chapterSegments[2]; |
|
394
|
|
|
break; |
|
395
|
|
|
|
|
396
|
|
|
default: |
|
397
|
|
|
//TODO: FALLBACK, ALERT ADMIN? |
|
398
|
|
|
$chapterData['number'] = $chapter; |
|
399
|
|
|
break; |
|
400
|
|
|
} |
|
401
|
|
|
} |
|
402
|
|
|
return $chapterData; |
|
403
|
|
|
} |
|
404
|
|
|
|
|
405
|
1 |
|
public function getTitleData(string $title_string) { |
|
406
|
1 |
|
$title_parts = explode(':--:', $title_string); |
|
407
|
1 |
|
$title_url = $title_parts[0]; |
|
408
|
|
|
|
|
409
|
1 |
|
$titleData = []; |
|
410
|
|
|
//FIXME: Using regex here is probably a terrible idea, but we're doing it anyway.... |
|
411
|
|
|
//FIXME (ASAP): All the regex here should be checked to see if it even returns something, and we should probably error if possible. |
|
412
|
1 |
|
if($title_parts[1] == '0') { |
|
413
|
1 |
|
$content = $this->get_content('http://dynasty-scans.com/series/'.$title_url); |
|
414
|
1 |
|
$data = $content['body']; |
|
|
|
|
|
|
415
|
|
|
|
|
416
|
1 |
|
preg_match('/<b>.*<\/b>/', $data, $matchesT); |
|
417
|
1 |
|
preg_match('/\/doujins\/[^"]+">(.+)?(?=<\/a>)<\/a>/', $data, $matchesD); |
|
418
|
1 |
|
$titleData['title'] = (!empty($matchesD) ? (substr($matchesD[1], 0, -7) !== 'Original' ? substr($matchesD[1], 0, -7).' - ' : '') : '') . substr($matchesT[0], 3, -4); |
|
419
|
|
|
|
|
420
|
1 |
|
$data = preg_replace('/^[\S\s]*(<dl class=\'chapter-list\'>[\S\s]*<\/dl>)[\S\s]*$/', '$1', $data); |
|
421
|
1 |
|
preg_match_all('/<dd>[\s\S]+?(?=<\/dd>)<\/dd>/', $data, $matches); |
|
422
|
1 |
|
$latest_chapter_html = array_pop($matches[0]); |
|
423
|
|
|
|
|
424
|
1 |
|
preg_match('/\/chapters\/([^"]+)/', $latest_chapter_html, $matches); |
|
425
|
1 |
|
$titleData['latest_chapter'] = substr($matches[1], strlen($title_url)+1); |
|
426
|
|
|
//FIXME: THIS IS A TEMP FIX, SEE https://github.com/DakuTree/manga-tracker/issues/58 |
|
427
|
1 |
|
if(!$titleData['latest_chapter']) { |
|
428
|
|
|
log_message('error', 'DynastyScans::getTitleData cannot parse title properly as it contains oneshot. || URL: '.$title_url); |
|
429
|
|
|
return NULL; |
|
430
|
|
|
} |
|
431
|
|
|
|
|
432
|
1 |
|
preg_match('/<small>released (.*)<\/small>/', $latest_chapter_html, $matches); |
|
433
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime(str_replace('\'', '', $matches[1]))); |
|
|
|
|
|
|
434
|
|
|
} elseif($title_parts[1] == '1') { |
|
435
|
|
|
$content = $this->get_content('http://dynasty-scans.com/chapters/'.$title_url); |
|
436
|
|
|
$data = $content['body']; |
|
|
|
|
|
|
437
|
|
|
|
|
438
|
|
|
preg_match('/<b>.*<\/b>/', $data, $matchesT); |
|
439
|
|
|
preg_match('/\/doujins\/[^"]+">(.+)?(?=<\/a>)<\/a>/', $data, $matchesD); |
|
440
|
|
|
$titleData['title'] = (!empty($matchesD) ? ($matchesD[1] !== 'Original' ? $matchesD[1].' - ' : '') : '') . substr($matchesT[0], 3, -4); |
|
441
|
|
|
|
|
442
|
|
|
$titleData['latest_chapter'] = 'oneshot'; //This will never change |
|
443
|
|
|
|
|
444
|
|
|
preg_match('/<i class="icon-calendar"><\/i> (.*)<\/span>/', $data, $matches); |
|
445
|
|
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime($matches[1])); |
|
|
|
|
|
|
446
|
|
|
|
|
447
|
|
|
//Oneshots are special, and really shouldn't need to be re-tracked |
|
448
|
|
|
//FIXME: We need to have a specific "no-track" complete param. |
|
449
|
|
|
$titleData['complete'] = 'Y'; |
|
450
|
|
|
} else { |
|
|
|
|
|
|
451
|
|
|
//FIXME: WTF? |
|
452
|
|
|
} |
|
453
|
1 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
454
|
|
|
} |
|
455
|
|
|
} |
|
456
|
|
|
|
|
457
|
|
|
class MangaPanda extends Site_Model { |
|
458
|
2 |
|
public function getFullTitleURL(string $title_url) : string { |
|
459
|
2 |
|
return "http://www.mangapanda.com/{$title_url}"; |
|
460
|
|
|
} |
|
461
|
|
|
|
|
462
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
463
|
|
|
return [ |
|
464
|
|
|
'url' => "http://www.mangapanda.com/{$title_url}/{$chapter}/", |
|
465
|
|
|
'number' => 'c'.$chapter |
|
466
|
|
|
]; |
|
467
|
|
|
} |
|
468
|
|
|
|
|
469
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
470
|
|
|
//NOTE: MangaPanda has manga pages under the root URL, so we need to filter out pages we know that aren't manga. |
|
471
|
|
|
$success = (bool) preg_match('/^(?!(?:latest|search|popular|random|alphabetical|privacy)$)([a-z0-9-]+)$/', $title_url); |
|
472
|
|
|
if(!$success) log_message('error', "Invalid Title URL (MangaPanda): {$title_url}"); |
|
473
|
|
|
return $success; |
|
474
|
|
|
} |
|
475
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
476
|
|
|
$success = (bool) preg_match('/^[0-9]+$/', $chapter); |
|
477
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (MangaPanda): '.$chapter); |
|
478
|
|
|
return $success; |
|
479
|
|
|
} |
|
480
|
|
|
|
|
481
|
2 |
|
public function getTitleData(string $title_url) { |
|
482
|
2 |
|
$titleData = []; |
|
483
|
|
|
|
|
484
|
2 |
|
$fullURL = $this->getFullTitleURL($title_url); |
|
485
|
2 |
|
$content = $this->get_content($fullURL); |
|
486
|
|
|
|
|
487
|
2 |
|
$data = $this->parseTitleDataDOM( |
|
488
|
|
|
$content, |
|
489
|
2 |
|
'MangaPanda', |
|
490
|
|
|
$title_url, |
|
491
|
2 |
|
"//h2[@class='aname']", |
|
492
|
2 |
|
"(//table[@id='listing']/tr)[last()]", |
|
493
|
2 |
|
"td[2]", |
|
494
|
2 |
|
"td[1]/a" |
|
495
|
|
|
); |
|
496
|
2 |
|
if($data) { |
|
497
|
1 |
|
$titleData['title'] = $data['nodes_title']->textContent; |
|
498
|
|
|
|
|
499
|
1 |
|
$titleData['latest_chapter'] = preg_replace('/^.*\/([0-9]+)$/', '$1', (string) $data['nodes_chapter']->getAttribute('href')); |
|
500
|
|
|
|
|
501
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) $data['nodes_latest']->nodeValue)); |
|
502
|
|
|
} |
|
503
|
|
|
|
|
504
|
|
|
|
|
505
|
2 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
506
|
|
|
} |
|
507
|
|
|
} |
|
508
|
|
|
|
|
509
|
|
|
class MangaStream extends Site_Model { |
|
510
|
|
|
public function getFullTitleURL(string $title_url) : string { |
|
511
|
|
|
return "https://mangastream.com/manga/{$title_url}/"; |
|
512
|
|
|
} |
|
513
|
|
|
|
|
514
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
515
|
|
|
$success = (bool) preg_match('/^[a-z0-9_]+$/', $title_url); |
|
516
|
|
|
if(!$success) log_message('error', "Invalid Title URL (MangaStream): {$title_url}"); |
|
517
|
|
|
return $success; |
|
518
|
|
|
} |
|
519
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
520
|
|
|
$success = (bool) preg_match('/^(.*?)\/[0-9]+$/', $chapter); |
|
521
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (MangaStream): '.$chapter); |
|
522
|
|
|
return $success; |
|
523
|
|
|
} |
|
524
|
|
|
|
|
525
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
526
|
|
|
return [ |
|
527
|
|
|
'url' => "https://mangastream.com/r/{$title_url}/{$chapter}", |
|
528
|
|
|
'number' => 'c'.explode('/', $chapter)[0] |
|
529
|
|
|
]; |
|
530
|
|
|
} |
|
531
|
|
|
|
|
532
|
|
|
public function getTitleData(string $title_url) { |
|
533
|
|
|
$titleData = []; |
|
534
|
|
|
|
|
535
|
|
|
$fullURL = $this->getFullTitleURL($title_url); |
|
536
|
|
|
|
|
537
|
|
|
$content = $this->get_content($fullURL); |
|
538
|
|
|
$data = $content['body']; |
|
|
|
|
|
|
539
|
|
|
if($data !== 'Can\'t find the manga series.') { //FIXME: We should check for he proper error here. |
|
540
|
|
|
//$data = preg_replace('/^[\S\s]*(<body id="body">[\S\s]*<\/body>)[\S\s]*$/', '$1', $data); |
|
541
|
|
|
|
|
542
|
|
|
$dom = new DOMDocument(); |
|
543
|
|
|
libxml_use_internal_errors(true); |
|
544
|
|
|
$dom->loadHTML($data); |
|
545
|
|
|
libxml_use_internal_errors(false); |
|
546
|
|
|
|
|
547
|
|
|
$xpath = new DOMXPath($dom); |
|
548
|
|
|
|
|
549
|
|
|
$nodes_title = $xpath->query("//div[contains(@class, 'content')]/div[1]/h1"); |
|
550
|
|
|
$nodes_row = $xpath->query("//div[contains(@class, 'content')]/div[1]/table/tr[2]"); //Missing tbody here.. |
|
551
|
|
|
if($nodes_title->length === 1 && $nodes_row->length === 1) { |
|
552
|
|
|
$titleData['title'] = $nodes_title->item(0)->nodeValue; |
|
553
|
|
|
|
|
554
|
|
|
$firstRow = $nodes_row->item(0); |
|
555
|
|
|
$nodes_latest = $xpath->query("td[2]", $firstRow); |
|
556
|
|
|
$nodes_chapter = $xpath->query("td[1]/a", $firstRow); |
|
557
|
|
|
|
|
558
|
|
|
$titleData['latest_chapter'] = preg_replace('/^.*\/(.*?\/[0-9]+)\/[0-9]+$/', '$1', (string) $nodes_chapter->item(0)->getAttribute('href')); |
|
559
|
|
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) $nodes_latest->item(0)->nodeValue)); |
|
|
|
|
|
|
560
|
|
|
} |
|
561
|
|
|
} else { |
|
562
|
|
|
log_message('error', "Series missing? (MangaStream): {$title_url}"); |
|
563
|
|
|
return NULL; |
|
564
|
|
|
} |
|
565
|
|
|
|
|
566
|
|
|
return (!empty($titleData) ? $titleData : NULL); |
|
567
|
|
|
} |
|
568
|
|
|
} |
|
569
|
|
|
|
|
570
|
|
|
class WebToons extends Site_Model { |
|
571
|
|
|
/* Webtoons.com has a very weird and pointless URL format. |
|
572
|
|
|
TITLE URL: /#LANG#/#GENRE#/#TITLE#/list?title_no=#TITLEID# |
|
573
|
|
|
RSS URL: /#LANG#/#GENRE#/#TITLE#/rss?title_no=#TITLEID# |
|
574
|
|
|
CHAPTER URL: /#LANG#/#GENRE#/#TITLE#/#CHAPTER#/viewer?title_no=#TITLEID#&episode_no=#CHAPTERID# |
|
575
|
|
|
|
|
576
|
|
|
For both the title and chapter URLs, only the TITLEID and CHAPTERID are needed. Everything else can be anything at all (Well, alphanumeric at least). |
|
577
|
|
|
The RSS URL however, requires everything to be exactly correct. I have no idea why this is, but it does mean we need to store all that info too. |
|
578
|
|
|
We <could> not use the RSS url, and just parse via the title url, but rss is much better in the long run as it shouldn't change much. |
|
579
|
|
|
|
|
580
|
|
|
FORMATS: |
|
581
|
|
|
TITLE_URL: ID:--:LANG:--:TITLE:--:GENRE |
|
582
|
|
|
CHAPTER: ID:--:CHAPTER_N |
|
583
|
|
|
*/ |
|
584
|
|
|
//private $validLang = ['en', 'zh-hant', 'zh-hans', 'th', 'id']; |
|
585
|
|
|
|
|
586
|
|
|
public function getFullTitleURL(string $title_url) : string { |
|
587
|
|
|
$title_parts = explode(':--:', $title_url); |
|
588
|
|
|
return "http://www.webtoons.com/{$title_parts[1]}/{$title_parts[3]}/{$title_parts[2]}/list?title_no={$title_parts[0]}/"; |
|
589
|
|
|
} |
|
590
|
|
|
|
|
591
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
592
|
|
|
$success = (bool) preg_match('/^[0-9]+:--:(?:en|zh-hant|zh-hans|th|id):--:[a-z0-9-]+:--:(?:drama|fantasy|comedy|action|slice-of-life|romance|superhero|thriller|sports|sci-fi)$/', $title_url); |
|
593
|
|
|
if(!$success) log_message('error', "Invalid Title URL (WebToons): {$title_url}"); |
|
594
|
|
|
return $success; |
|
595
|
|
|
} |
|
596
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
597
|
|
|
$success = (bool) preg_match('/^[0-9]+:--:.*$/', $chapter); |
|
598
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (WebToons): '.$chapter); |
|
599
|
|
|
return $success; |
|
600
|
|
|
} |
|
601
|
|
|
|
|
602
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
603
|
|
|
$title_parts = explode(':--:', $title_url); |
|
604
|
|
|
$chapter_parts = explode(':--:', $chapter); |
|
605
|
|
|
|
|
606
|
|
|
return [ |
|
607
|
|
|
'url' => "http://www.webtoons.com/{$title_parts[1]}/{$title_parts[3]}/{$title_parts[2]}/{$chapter_parts[1]}/viewer?title_no={$title_parts[0]}&episode_no={$chapter_parts[0]}", |
|
608
|
|
|
'number' => $chapter_parts[1] //TODO: Possibly replace certain formats in here? Since webtoons doesn't have a standard chapter format |
|
609
|
|
|
]; |
|
610
|
|
|
} |
|
611
|
|
|
|
|
612
|
1 |
|
public function getTitleData(string $title_url) { |
|
613
|
1 |
|
$titleData = []; |
|
614
|
|
|
|
|
615
|
1 |
|
$title_parts = explode(':--:', $title_url); |
|
616
|
1 |
|
$fullURL = "http://www.webtoons.com/{$title_parts[1]}/{$title_parts[3]}/{$title_parts[2]}/rss?title_no={$title_parts[0]}"; |
|
|
|
|
|
|
617
|
|
|
|
|
618
|
1 |
|
$content = $this->get_content($fullURL); |
|
619
|
1 |
|
$data = $content['body']; |
|
|
|
|
|
|
620
|
1 |
|
if($data !== 'Can\'t find the manga series.') { //FIXME: We should check for he proper error here. |
|
621
|
1 |
|
$xml = simplexml_load_string($data) or die("Error: Cannot create object"); |
|
622
|
1 |
|
if(isset($xml->{'channel'}->item[0])) { |
|
623
|
1 |
|
$titleData['title'] = trim((string) $xml->{'channel'}->title); |
|
624
|
|
|
|
|
625
|
1 |
|
$chapterURLSegments = explode('/', ((string) $xml->{'channel'}->item[0]->link)); |
|
|
|
|
|
|
626
|
1 |
|
$titleData['latest_chapter'] = preg_replace('/^.*?([0-9]+)$/', '$1', $chapterURLSegments[7]) . ':--:' . $chapterURLSegments[6]; |
|
627
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) $xml->{'channel'}->item[0]->pubDate)); |
|
|
|
|
|
|
628
|
|
|
} |
|
629
|
|
|
} else { |
|
630
|
|
|
log_message('error', "Series missing? (WebToons): {$title_url}"); |
|
631
|
|
|
return NULL; |
|
632
|
|
|
} |
|
633
|
|
|
|
|
634
|
1 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
635
|
|
|
} |
|
636
|
|
|
} |
|
637
|
|
|
|
|
638
|
|
|
class KissManga extends Site_Model { |
|
639
|
|
|
/* This site is a massive pain in the ass. The only reason I'm supporting it is it's one of the few aggregator sites which actually support more risqué manga. |
|
640
|
|
|
The main problem with this site is it has some form of bot protection. To view any part of the site normally, you need a cookie set by the bot protection. |
|
641
|
|
|
|
|
642
|
|
|
To generate this cookie, we need three variables. Two are static, but the other is generated by randomly generated JS on the page. |
|
643
|
|
|
The randomly generated JS is the troublesome part. We can't easily parse this with PHP. Both V8JS & SpiderMonkey refuse to build properly for me, so that rules that out. |
|
644
|
|
|
The other option is using regex, but that is a rabbit hole I don't want to touch with a ten-foot pole. |
|
645
|
|
|
|
|
646
|
|
|
To make the entire site work, I've built a python script to handle grabbing this cookie. This is grabbed & updated at the same time the manga are updated. The script saves the cookiejar which the PHP later reads. |
|
647
|
|
|
The cookie has a length of 1 year, but I don't think it actually lasts that long, so we update every 6hours instead. |
|
648
|
|
|
I should probably also mention that the cookie generated also uses your user-agent, so if it changes the cookie will break. |
|
649
|
|
|
*/ |
|
650
|
|
|
|
|
651
|
|
|
public function getFullTitleURL(string $title_url) : string { |
|
652
|
|
|
return "http://kissmanga.com/Manga/{$title_url}"; |
|
653
|
|
|
} |
|
654
|
|
|
|
|
655
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
656
|
|
|
$success = (bool) preg_match('/^[A-Za-z0-9-]+/', $title_url); |
|
657
|
|
|
if(!$success) log_message('error', "Invalid Title URL (KissManga): {$title_url}"); |
|
658
|
|
|
return $success; |
|
659
|
|
|
} |
|
660
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
661
|
|
|
$success = (bool) preg_match('/^.*?:--:[0-9]+$/', $chapter); |
|
662
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (KissManga): '.$chapter); |
|
663
|
|
|
return $success; |
|
664
|
|
|
} |
|
665
|
|
|
|
|
666
|
|
View Code Duplication |
public function getChapterData(string $title_url, string $chapter) : array { |
|
667
|
|
|
$chapter_parts = explode(':--:', $chapter); |
|
668
|
|
|
|
|
669
|
|
|
return [ |
|
670
|
|
|
'url' => "http://kissmanga.com/Manga/{$title_url}/{$chapter_parts[0]}?id={$chapter_parts[1]}", |
|
671
|
|
|
//FIXME: KM has an extremely inconsistant chapter format which makes it difficult to parse. |
|
672
|
|
|
'number' => /*preg_replace('/--.*?$/', '', */$chapter_parts[0]/*)*/ |
|
673
|
|
|
]; |
|
674
|
|
|
} |
|
675
|
|
|
|
|
676
|
|
|
public function getTitleData(string $title_url) { |
|
677
|
|
|
$titleData = []; |
|
678
|
|
|
|
|
679
|
|
|
//Check if cookiejar is a day old (so we can know if something went wrong) |
|
680
|
|
|
$cookiejar_path = str_replace("public/", "_scripts/cookiejar", FCPATH); |
|
|
|
|
|
|
681
|
|
|
$cookie_last_updated = filemtime($cookiejar_path); |
|
682
|
|
|
if($cookie_last_updated && ((time() - 86400) < $cookie_last_updated)) { |
|
683
|
|
|
|
|
684
|
|
|
$fullURL = $this->getFullTitleURL($title_url); |
|
685
|
|
|
|
|
686
|
|
|
$content = $this->get_content($fullURL, '', $cookiejar_path); |
|
687
|
|
|
$data = $content['body']; |
|
|
|
|
|
|
688
|
|
|
if(strpos($data, 'containerRoot') !== FALSE) { |
|
689
|
|
|
//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us |
|
690
|
|
|
$data = preg_replace('/^[\S\s]*(<div id="leftside">[\S\s]*)<div id="rightside">[\S\s]*$/', '$1', $data); |
|
691
|
|
|
|
|
692
|
|
|
$dom = new DOMDocument(); |
|
693
|
|
|
libxml_use_internal_errors(true); |
|
694
|
|
|
$dom->loadHTML($data); |
|
695
|
|
|
libxml_use_internal_errors(false); |
|
696
|
|
|
|
|
697
|
|
|
$xpath = new DOMXPath($dom); |
|
698
|
|
|
|
|
699
|
|
|
$nodes_title = $xpath->query("//a[@class='bigChar']"); |
|
700
|
|
|
$nodes_row = $xpath->query("//table[@class='listing']/tr[3]"); |
|
701
|
|
|
if($nodes_title->length === 1 && $nodes_row->length === 1) { |
|
702
|
|
|
$titleData['title'] = $nodes_title->item(0)->textContent; |
|
703
|
|
|
|
|
704
|
|
|
$firstRow = $nodes_row->item(0); |
|
705
|
|
|
$nodes_latest = $xpath->query("td[2]", $firstRow); |
|
706
|
|
|
$nodes_chapter = $xpath->query("td[1]/a", $firstRow); |
|
707
|
|
|
|
|
708
|
|
|
$link = (string) $nodes_chapter->item(0)->getAttribute('href'); |
|
|
|
|
|
|
709
|
|
|
$chapterURLSegments = explode('/', preg_replace('/\?.*$/', '', $link)); |
|
|
|
|
|
|
710
|
|
|
$titleData['latest_chapter'] = $chapterURLSegments[3] . ':--:' . preg_replace('/.*?([0-9]+)$/', '$1', $link); |
|
711
|
|
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) $nodes_latest->item(0)->textContent)); |
|
|
|
|
|
|
712
|
|
|
} |
|
713
|
|
|
} else { |
|
|
|
|
|
|
714
|
|
|
//TODO: Throw ERRORS; |
|
715
|
|
|
} |
|
716
|
|
|
} else { |
|
|
|
|
|
|
717
|
|
|
//Do nothing, wait until next update. |
|
718
|
|
|
//TODO: NAG ADMIN?? |
|
719
|
|
|
} |
|
720
|
|
|
|
|
721
|
|
|
return (!empty($titleData) ? $titleData : NULL); |
|
722
|
|
|
} |
|
723
|
|
|
} |
|
724
|
|
|
|
|
725
|
|
|
class KireiCake extends Site_Model { |
|
726
|
1 |
|
public function getFullTitleURL(string $title_url) : string { |
|
727
|
1 |
|
return "https://reader.kireicake.com/series/{$title_url}"; |
|
728
|
|
|
} |
|
729
|
|
|
|
|
730
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
731
|
|
|
$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url); |
|
732
|
|
|
if(!$success) log_message('error', "Invalid Title URL (KireiCake): {$title_url}"); |
|
733
|
|
|
return $success; |
|
734
|
|
|
} |
|
735
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
736
|
|
|
$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter); |
|
737
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (KireiCake): '.$chapter); |
|
738
|
|
|
return $success; |
|
739
|
|
|
} |
|
740
|
|
|
|
|
741
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
742
|
|
|
//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/) |
|
743
|
|
|
$chapter_parts = explode('/', $chapter); |
|
744
|
|
|
return [ |
|
745
|
|
|
'url' => "https://reader.kireicake.com/read/{$title_url}/{$chapter}/", |
|
746
|
|
|
'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/*)*/ |
|
747
|
|
|
]; |
|
748
|
|
|
} |
|
749
|
|
|
|
|
750
|
1 |
|
public function getTitleData(string $title_url) { |
|
751
|
1 |
|
$titleData = []; |
|
752
|
|
|
|
|
753
|
1 |
|
$fullURL = $this->getFullTitleURL($title_url); |
|
754
|
|
|
|
|
755
|
1 |
|
$content = $this->get_content($fullURL); |
|
756
|
1 |
|
$data = $content['body']; |
|
|
|
|
|
|
757
|
1 |
|
if(strpos($data, '404 Page Not Found') === FALSE) { |
|
758
|
|
|
//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us |
|
759
|
1 |
|
$data = preg_replace('/^[\S\s]*(<article>[\S\s]*)<\/article>[\S\s]*$/', '$1', $data); |
|
760
|
|
|
|
|
761
|
1 |
|
$dom = new DOMDocument(); |
|
762
|
1 |
|
libxml_use_internal_errors(true); |
|
763
|
1 |
|
$dom->loadHTML($data); |
|
764
|
1 |
|
libxml_use_internal_errors(false); |
|
765
|
|
|
|
|
766
|
1 |
|
$xpath = new DOMXPath($dom); |
|
767
|
|
|
|
|
768
|
1 |
|
$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']"); |
|
769
|
1 |
|
$nodes_row = $xpath->query("//div[@class='list']/div[@class='element'][1]"); |
|
770
|
1 |
|
if($nodes_title->length === 1 && $nodes_row->length === 1) { |
|
771
|
1 |
|
$titleData['title'] = trim($nodes_title->item(0)->textContent); |
|
772
|
|
|
|
|
773
|
1 |
|
$firstRow = $nodes_row->item(0); |
|
774
|
1 |
|
$nodes_latest = $xpath->query("div[@class='meta_r']", $firstRow); |
|
775
|
1 |
|
$nodes_chapter = $xpath->query("div[@class='title']/a", $firstRow); |
|
776
|
|
|
|
|
777
|
1 |
|
$link = (string) $nodes_chapter->item(0)->getAttribute('href'); |
|
|
|
|
|
|
778
|
1 |
|
$titleData['latest_chapter'] = preg_replace('/.*\/read\/.*?\/(.*?)\/$/', '$1', $link); |
|
779
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest->item(0)->textContent)[1]))); |
|
|
|
|
|
|
780
|
|
|
} |
|
781
|
|
|
} else { |
|
|
|
|
|
|
782
|
|
|
//TODO: Throw ERRORS; |
|
783
|
|
|
} |
|
784
|
|
|
|
|
785
|
1 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
786
|
|
|
} |
|
787
|
|
|
} |
|
788
|
|
|
|
|
789
|
|
|
class GameOfScanlation extends Site_Model { |
|
790
|
|
|
public function getFullTitleURL(string $title_url) : string { |
|
791
|
|
|
return "https://gameofscanlation.moe/forums/{$title_url}/"; |
|
792
|
|
|
} |
|
793
|
|
|
|
|
794
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
795
|
|
|
$success = (bool) preg_match('/^[a-z0-9-]+/', $title_url); |
|
796
|
|
|
if(!$success) log_message('error', "Invalid Title URL (GameOfScanlation): {$title_url}"); |
|
797
|
|
|
return $success; |
|
798
|
|
|
} |
|
799
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
800
|
|
|
$success = (bool) preg_match('/^[a-z0-9\.-]+$/', $chapter); |
|
801
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (GameOfScanlation): '.$chapter); |
|
802
|
|
|
return $success; |
|
803
|
|
|
} |
|
804
|
|
|
|
|
805
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
806
|
|
|
return [ |
|
807
|
|
|
'url' => "https://gameofscanlation.moe/projects/".preg_replace("/\\.[0-9]+$/", "", $title_url).'/'.$chapter.'/', |
|
808
|
|
|
'number' => preg_replace("/chapter-/", "c", preg_replace("/\\.[0-9]+$/", "", $chapter)) |
|
809
|
|
|
]; |
|
810
|
|
|
} |
|
811
|
|
|
|
|
812
|
|
|
public function getTitleData(string $title_url) { |
|
813
|
|
|
$titleData = []; |
|
814
|
|
|
|
|
815
|
|
|
$fullURL = $this->getFullTitleURL($title_url); |
|
816
|
|
|
|
|
817
|
|
|
$content = $this->get_content($fullURL); |
|
818
|
|
|
$data = $content['body']; |
|
|
|
|
|
|
819
|
|
|
if(strpos($data, '404 Page Not Found') === FALSE) { |
|
820
|
|
|
//$data = preg_replace('/^[\S\s]*(<ol[\S\s]*)<\/ol>[\S\s]*$/', '$1', $data); |
|
821
|
|
|
|
|
822
|
|
|
$dom = new DOMDocument(); |
|
823
|
|
|
libxml_use_internal_errors(true); |
|
824
|
|
|
$dom->loadHTML($data); |
|
825
|
|
|
libxml_use_internal_errors(false); |
|
826
|
|
|
|
|
827
|
|
|
$xpath = new DOMXPath($dom); |
|
828
|
|
|
|
|
829
|
|
|
$nodes_title = $xpath->query("//meta[@property='og:title']"); |
|
830
|
|
|
$nodes_row = $xpath->query("//ol[@class='discussionListItems']/li[1]/div[@class='home_list']/ul/li/div[@class='list_press_text']"); |
|
831
|
|
|
if($nodes_title->length === 1 && $nodes_row->length === 1) { |
|
832
|
|
|
$titleData['title'] = html_entity_decode($nodes_title->item(0)->getAttribute('content')); |
|
833
|
|
|
|
|
834
|
|
|
$firstRow = $nodes_row->item(0); |
|
835
|
|
|
$nodes_latest = $xpath->query("p[@class='author']/span|p[@class='author']/abbr", $firstRow); |
|
836
|
|
|
$nodes_chapter = $xpath->query("p[@class='text_work']/a", $firstRow); |
|
837
|
|
|
|
|
838
|
|
|
$link = (string) $nodes_chapter->item(0)->getAttribute('href'); |
|
|
|
|
|
|
839
|
|
|
$titleData['latest_chapter'] = preg_replace('/^projects\/.*?\/(.*?)\/$/', '$1', $link); |
|
840
|
|
|
$titleData['last_updated'] = date("Y-m-d H:i:s", (int) $nodes_latest->item(0)->getAttribute('data-time')); |
|
|
|
|
|
|
841
|
|
|
} else { |
|
842
|
|
|
log_message('error', "GameOfScanlation: Unable to find nodes."); |
|
843
|
|
|
return NULL; |
|
844
|
|
|
} |
|
845
|
|
|
} else { |
|
|
|
|
|
|
846
|
|
|
//TODO: Throw ERRORS; |
|
847
|
|
|
} |
|
848
|
|
|
|
|
849
|
|
|
return (!empty($titleData) ? $titleData : NULL); |
|
850
|
|
|
} |
|
851
|
|
|
} |
|
852
|
|
|
|
|
853
|
|
|
class MangaCow extends Site_Model { |
|
854
|
1 |
|
public function getFullTitleURL(string $title_url) : string { |
|
855
|
1 |
|
return "http://mngcow.co/{$title_url}/"; |
|
856
|
|
|
} |
|
857
|
|
|
|
|
858
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
859
|
|
|
$success = (bool) preg_match('/^[a-zA-Z0-9_]+/', $title_url); |
|
860
|
|
|
if(!$success) log_message('error', "Invalid Title URL (MangaCow): {$title_url}"); |
|
861
|
|
|
return $success; |
|
862
|
|
|
} |
|
863
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
864
|
|
|
$success = (bool) preg_match('/^[0-9]+$/', $chapter); |
|
865
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (MangaCow): '.$chapter); |
|
866
|
|
|
return $success; |
|
867
|
|
|
} |
|
868
|
|
|
|
|
869
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
870
|
|
|
return [ |
|
871
|
|
|
'url' => $this->getFullTitleURL($title_url).$chapter.'/', |
|
872
|
|
|
'number' => "c{$chapter}" |
|
873
|
|
|
]; |
|
874
|
|
|
} |
|
875
|
|
|
|
|
876
|
1 |
|
public function getTitleData(string $title_url) { |
|
877
|
1 |
|
$titleData = []; |
|
878
|
|
|
|
|
879
|
1 |
|
$fullURL = $this->getFullTitleURL($title_url); |
|
880
|
|
|
|
|
881
|
1 |
|
$content = $this->get_content($fullURL); |
|
882
|
1 |
|
$data = $content['body']; |
|
|
|
|
|
|
883
|
1 |
|
if(strpos($data, '404 Page Not Found') === FALSE) { |
|
884
|
1 |
|
$dom = new DOMDocument(); |
|
885
|
1 |
|
libxml_use_internal_errors(true); |
|
886
|
1 |
|
$dom->loadHTML($data); |
|
887
|
1 |
|
libxml_use_internal_errors(false); |
|
888
|
|
|
|
|
889
|
1 |
|
$xpath = new DOMXPath($dom); |
|
890
|
|
|
|
|
891
|
1 |
|
$nodes_title = $xpath->query("//h4"); |
|
892
|
1 |
|
$nodes_row = $xpath->query("//ul[contains(@class, 'mng_chp')]/li[1]/a[1]"); |
|
893
|
1 |
|
if($nodes_title->length === 1 && $nodes_row->length === 1) { |
|
894
|
1 |
|
$titleData['title'] = trim($nodes_title->item(0)->nodeValue); |
|
895
|
|
|
|
|
896
|
1 |
|
$nodes_chapter = $nodes_row; |
|
897
|
1 |
|
$nodes_latest = $xpath->query("b[@class='dte']", $nodes_row->item(0)); |
|
898
|
|
|
|
|
899
|
1 |
|
$link = (string) $nodes_chapter->item(0)->getAttribute('href'); |
|
|
|
|
|
|
900
|
1 |
|
$titleData['latest_chapter'] = preg_replace('/^.*\/([0-9]+)\/$/', '$1', $link); |
|
901
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) substr($nodes_latest->item(0)->getAttribute('title'), 13))); |
|
|
|
|
|
|
902
|
|
|
} else { |
|
903
|
|
|
log_message('error', "MangaCow: Unable to find nodes."); |
|
904
|
1 |
|
return NULL; |
|
905
|
|
|
} |
|
906
|
|
|
} else { |
|
|
|
|
|
|
907
|
|
|
//TODO: Throw ERRORS; |
|
908
|
|
|
} |
|
909
|
|
|
|
|
910
|
1 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
911
|
|
|
} |
|
912
|
|
|
} |
|
913
|
|
|
|
|
914
|
|
View Code Duplication |
class SeaOtterScans extends Site_Model { |
|
|
|
|
|
|
915
|
1 |
|
public function getFullTitleURL(string $title_url) : string { |
|
916
|
1 |
|
return "http://reader.seaotterscans.com/series/{$title_url}"; |
|
917
|
|
|
} |
|
918
|
|
|
|
|
919
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
920
|
|
|
$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url); |
|
921
|
|
|
if(!$success) log_message('error', "Invalid Title URL (SeaOtterScans): {$title_url}"); |
|
922
|
|
|
return $success; |
|
923
|
|
|
} |
|
924
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
925
|
|
|
$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter); |
|
926
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (SeaOtterScans): '.$chapter); |
|
927
|
|
|
return $success; |
|
928
|
|
|
} |
|
929
|
|
|
|
|
930
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
931
|
|
|
//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/) |
|
932
|
|
|
$chapter_parts = explode('/', $chapter); |
|
933
|
|
|
return [ |
|
934
|
|
|
'url' => "https://reader.seaotterscans.com/read/{$title_url}/{$chapter}/", |
|
935
|
|
|
'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/*)*/ |
|
936
|
|
|
]; |
|
937
|
|
|
} |
|
938
|
|
|
|
|
939
|
1 |
|
public function getTitleData(string $title_url) { |
|
940
|
1 |
|
$titleData = []; |
|
941
|
|
|
|
|
942
|
1 |
|
$fullURL = $this->getFullTitleURL($title_url); |
|
943
|
|
|
|
|
944
|
1 |
|
$content = $this->get_content($fullURL); |
|
945
|
1 |
|
$data = $content['body']; |
|
|
|
|
|
|
946
|
1 |
|
if(strpos($data, '404 Page Not Found') === FALSE) { |
|
947
|
|
|
//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us |
|
948
|
1 |
|
$data = preg_replace('/^[\S\s]*(<article[\S\s]*)<\/article>[\S\s]*$/', '$1', $data); |
|
949
|
|
|
|
|
950
|
1 |
|
$dom = new DOMDocument(); |
|
951
|
1 |
|
libxml_use_internal_errors(true); |
|
952
|
1 |
|
$dom->loadHTML($data); |
|
953
|
1 |
|
libxml_use_internal_errors(false); |
|
954
|
|
|
|
|
955
|
1 |
|
$xpath = new DOMXPath($dom); |
|
956
|
|
|
|
|
957
|
1 |
|
$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']"); |
|
958
|
|
|
|
|
959
|
|
|
//SOO sometimes uses volume groups which are above recent chapters (if they haven't been grouped yet), so make sure we check for both. |
|
960
|
1 |
|
$nodes_row = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]"); |
|
|
|
|
|
|
961
|
1 |
|
if($nodes_row->length !== 1) { |
|
962
|
1 |
|
$nodes_row = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]"); |
|
|
|
|
|
|
963
|
|
|
} |
|
964
|
1 |
|
if($nodes_title->length === 1 && $nodes_row->length === 1) { |
|
965
|
1 |
|
$titleData['title'] = trim($nodes_title->item(0)->textContent); |
|
966
|
|
|
|
|
967
|
1 |
|
$firstRow = $nodes_row->item(0); |
|
|
|
|
|
|
968
|
1 |
|
$nodes_latest = $xpath->query("div[@class='meta_r']", $firstRow); |
|
969
|
1 |
|
$nodes_chapter = $xpath->query("div[@class='title']/a", $firstRow); |
|
970
|
|
|
|
|
971
|
1 |
|
$link = (string) $nodes_chapter->item(0)->getAttribute('href'); |
|
|
|
|
|
|
972
|
1 |
|
$titleData['latest_chapter'] = preg_replace('/.*\/read\/.*?\/(.*?)\/$/', '$1', $link); |
|
973
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest[0]->textContent)[1]))); |
|
|
|
|
|
|
974
|
|
|
} |
|
975
|
|
|
} else { |
|
|
|
|
|
|
976
|
|
|
//TODO: Throw ERRORS; |
|
977
|
|
|
} |
|
978
|
|
|
|
|
979
|
1 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
980
|
|
|
} |
|
981
|
|
|
} |
|
982
|
|
|
|
|
983
|
|
View Code Duplication |
class HelveticaScans extends Site_Model { |
|
|
|
|
|
|
984
|
1 |
|
public function getFullTitleURL(string $title_url) : string { |
|
985
|
1 |
|
return "http://helveticascans.com/reader/series/{$title_url}"; |
|
986
|
|
|
} |
|
987
|
|
|
|
|
988
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
989
|
|
|
$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url); |
|
990
|
|
|
if(!$success) log_message('error', "Invalid Title URL (HelveticaScans): {$title_url}"); |
|
991
|
|
|
return $success; |
|
992
|
|
|
} |
|
993
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
994
|
|
|
$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter); |
|
995
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (HelveticaScans): '.$chapter); |
|
996
|
|
|
return $success; |
|
997
|
|
|
} |
|
998
|
|
|
|
|
999
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
1000
|
|
|
//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/) |
|
1001
|
|
|
$chapter_parts = explode('/', $chapter); |
|
1002
|
|
|
return [ |
|
1003
|
|
|
'url' => "http://helveticascans.com/reader/read/{$title_url}/{$chapter}/", |
|
1004
|
|
|
'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/*)*/ |
|
1005
|
|
|
]; |
|
1006
|
|
|
} |
|
1007
|
|
|
|
|
1008
|
1 |
|
public function getTitleData(string $title_url) { |
|
1009
|
1 |
|
$titleData = []; |
|
1010
|
|
|
|
|
1011
|
1 |
|
$fullURL = $this->getFullTitleURL($title_url); |
|
1012
|
|
|
|
|
1013
|
1 |
|
$content = $this->get_content($fullURL); |
|
1014
|
1 |
|
$data = $content['body']; |
|
|
|
|
|
|
1015
|
1 |
|
if(strpos($data, '404 Page Not Found') === FALSE) { |
|
1016
|
|
|
//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us |
|
1017
|
1 |
|
$data = preg_replace('/^[\S\s]*(<article[\S\s]*)<\/article>[\S\s]*$/', '$1', $data); |
|
1018
|
|
|
|
|
1019
|
1 |
|
$dom = new DOMDocument(); |
|
1020
|
1 |
|
libxml_use_internal_errors(true); |
|
1021
|
1 |
|
$dom->loadHTML($data); |
|
1022
|
1 |
|
libxml_use_internal_errors(false); |
|
1023
|
|
|
|
|
1024
|
1 |
|
$xpath = new DOMXPath($dom); |
|
1025
|
|
|
|
|
1026
|
1 |
|
$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']"); |
|
1027
|
1 |
|
$nodes_row = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]"); |
|
1028
|
1 |
|
if($nodes_row->length !== 1) { |
|
1029
|
|
|
$nodes_row = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]"); |
|
|
|
|
|
|
1030
|
|
|
} |
|
1031
|
1 |
|
if($nodes_title->length === 1 && $nodes_row->length === 1) { |
|
1032
|
1 |
|
$titleData['title'] = trim($nodes_title->item(0)->textContent); |
|
1033
|
|
|
|
|
1034
|
|
|
|
|
1035
|
1 |
|
$nodes_latest = $xpath->query("div[@class='meta_r']", $nodes_row[0]); |
|
1036
|
1 |
|
$nodes_chapter = $xpath->query("div[@class='title']/a", $nodes_row[0]); |
|
1037
|
|
|
|
|
1038
|
1 |
|
$link = (string) $nodes_chapter->item(0)->getAttribute('href'); |
|
|
|
|
|
|
1039
|
1 |
|
$titleData['latest_chapter'] = preg_replace('/.*\/read\/.*?\/(.*?)\/$/', '$1', $link); |
|
1040
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest->item(0)->textContent)[1]))); |
|
|
|
|
|
|
1041
|
|
|
} |
|
1042
|
|
|
} else { |
|
|
|
|
|
|
1043
|
|
|
//TODO: Throw ERRORS; |
|
1044
|
|
|
} |
|
1045
|
|
|
|
|
1046
|
1 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
1047
|
|
|
} |
|
1048
|
|
|
} |
|
1049
|
|
|
|
|
1050
|
|
View Code Duplication |
class SenseScans extends Site_Model { |
|
|
|
|
|
|
1051
|
1 |
|
public function getFullTitleURL(string $title_url) : string { |
|
1052
|
1 |
|
return "http://reader.sensescans.com/series/{$title_url}"; |
|
1053
|
|
|
} |
|
1054
|
|
|
|
|
1055
|
|
|
public function isValidTitleURL(string $title_url) : bool { |
|
1056
|
|
|
$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url); |
|
1057
|
|
|
if(!$success) log_message('error', "Invalid Title URL (SenseScans): {$title_url}"); |
|
1058
|
|
|
return $success; |
|
1059
|
|
|
} |
|
1060
|
|
|
public function isValidChapter(string $chapter) : bool { |
|
1061
|
|
|
$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter); |
|
1062
|
|
|
if(!$success) log_message('error', 'Invalid Chapter (SenseScans): '.$chapter); |
|
1063
|
|
|
return $success; |
|
1064
|
|
|
} |
|
1065
|
|
|
|
|
1066
|
|
|
public function getChapterData(string $title_url, string $chapter) : array { |
|
1067
|
|
|
//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/) |
|
1068
|
|
|
$chapter_parts = explode('/', $chapter); |
|
1069
|
|
|
return [ |
|
1070
|
|
|
'url' => "http://reader.sensescans.com/read/{$title_url}/{$chapter}/", |
|
1071
|
|
|
'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/*)*/ |
|
1072
|
|
|
]; |
|
1073
|
|
|
} |
|
1074
|
|
|
|
|
1075
|
1 |
|
public function getTitleData(string $title_url) { |
|
1076
|
1 |
|
$titleData = []; |
|
1077
|
|
|
|
|
1078
|
1 |
|
$fullURL = $this->getFullTitleURL($title_url); |
|
1079
|
|
|
|
|
1080
|
1 |
|
$content = $this->get_content($fullURL); |
|
1081
|
1 |
|
$data = $content['body']; |
|
|
|
|
|
|
1082
|
1 |
|
if(strpos($data, '404 Page Not Found') === FALSE) { |
|
1083
|
|
|
//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us |
|
1084
|
1 |
|
$data = preg_replace('/^[\S\s]*(<article[\S\s]*)<\/article>[\S\s]*$/', '$1', $data); |
|
1085
|
|
|
|
|
1086
|
1 |
|
$dom = new DOMDocument(); |
|
1087
|
1 |
|
libxml_use_internal_errors(true); |
|
1088
|
1 |
|
$dom->loadHTML($data); |
|
1089
|
1 |
|
libxml_use_internal_errors(false); |
|
1090
|
|
|
|
|
1091
|
1 |
|
$xpath = new DOMXPath($dom); |
|
1092
|
|
|
|
|
1093
|
1 |
|
$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']"); |
|
1094
|
1 |
|
$nodes_row = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]"); |
|
1095
|
1 |
|
if($nodes_row->length !== 1) { |
|
1096
|
|
|
$nodes_row = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]"); |
|
|
|
|
|
|
1097
|
|
|
} |
|
1098
|
1 |
|
if($nodes_title->length === 1 && $nodes_row->length === 1) { |
|
1099
|
1 |
|
$titleData['title'] = trim($nodes_title->item(0)->textContent); |
|
1100
|
|
|
|
|
1101
|
1 |
|
$nodes_latest = $xpath->query("div[@class='meta_r']", $nodes_row[0]); |
|
|
|
|
|
|
1102
|
1 |
|
$nodes_chapter = $xpath->query("div[@class='title']/a", $nodes_row[0]); |
|
|
|
|
|
|
1103
|
|
|
|
|
1104
|
1 |
|
$link = (string) $nodes_chapter->item(0)->getAttribute('href'); |
|
|
|
|
|
|
1105
|
1 |
|
$titleData['latest_chapter'] = preg_replace('/.*\/read\/.*?\/(.*?)\/$/', '$1', $link); |
|
1106
|
1 |
|
$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest->item(0)->textContent)[1]))); |
|
|
|
|
|
|
1107
|
|
|
} |
|
1108
|
|
|
} else { |
|
|
|
|
|
|
1109
|
|
|
//TODO: Throw ERRORS; |
|
1110
|
|
|
} |
|
1111
|
|
|
|
|
1112
|
1 |
|
return (!empty($titleData) ? $titleData : NULL); |
|
1113
|
|
|
} |
|
1114
|
|
|
} |
|
1115
|
|
|
|
DakuTree /
manga-tracker
Loading history...
This check looks for variable assignements that are either overwritten by other assignments or where the variable is not used subsequently.
Both the
$myVarassignment in line 1 and the$higherassignment in line 2 are dead. The first because$myVaris never used and the second because$higheris always overwritten for every possible time line.