1
|
|
|
<?php |
2
|
|
|
/** |
3
|
|
|
* This file is part of dispositif/wikibot application |
4
|
|
|
* 2019 : Philippe M. <[email protected]> |
5
|
|
|
* For the full copyright and MIT license information, please view the LICENSE file. |
6
|
|
|
*/ |
7
|
|
|
|
8
|
|
|
declare(strict_types=1); |
9
|
|
|
|
10
|
|
|
namespace App\Application\Examples; |
11
|
|
|
|
12
|
|
|
use App\Application\WikiBotConfig; |
13
|
|
|
use App\Application\WikiPageAction; |
14
|
|
|
use App\Domain\Utils\TemplateParser; |
15
|
|
|
use App\Infrastructure\DbAdapter; |
16
|
|
|
use App\Infrastructure\ServiceFactory; |
17
|
|
|
use Exception; |
18
|
|
|
|
19
|
|
|
//use App\Application\CLI; |
20
|
|
|
|
21
|
|
|
include __DIR__.'/../myBootstrap.php'; |
22
|
|
|
|
23
|
|
|
/** |
24
|
|
|
* From json list of articles => add to SQL page_ouvrages |
25
|
|
|
*/ |
26
|
|
|
$process = new PageScan(); |
27
|
|
|
|
28
|
|
|
$articles = file(__DIR__.'/../resources/importISBN_nov.txt'); |
29
|
|
|
|
30
|
|
|
foreach ($articles as $article) { |
31
|
|
|
$article = trim($article); |
32
|
|
|
if (empty($article)) { |
33
|
|
|
continue; |
34
|
|
|
} |
35
|
|
|
$process->pageScan($article, 0); |
36
|
|
|
sleep(4); |
37
|
|
|
} |
38
|
|
|
|
39
|
|
|
class PageScan |
40
|
|
|
{ |
41
|
|
|
private $wiki; |
42
|
|
|
private $db; |
43
|
|
|
private $bot; |
44
|
|
|
|
45
|
|
|
public function __construct() |
46
|
|
|
{ |
47
|
|
|
$this->wiki = ServiceFactory::wikiApi(); |
48
|
|
|
$this->db = new DbAdapter(); |
49
|
|
|
$this->bot = new WikiBotConfig(); |
50
|
|
|
} |
51
|
|
|
|
52
|
|
|
public function pageScan(string $title, ?int $priority = 0): bool |
53
|
|
|
{ |
54
|
|
|
sleep(2); |
55
|
|
|
echo "\n-------------------------------------\n\n"; |
56
|
|
|
echo date("Y-m-d H:i:s")."\n"; |
57
|
|
|
echo $title."\n"; |
58
|
|
|
|
59
|
|
|
$page = new WikiPageAction($this->wiki, $title); |
60
|
|
|
$ns = $page->getNs(); |
61
|
|
|
if ($ns !== 0) { |
62
|
|
|
echo "SKIP : namespace $ns"; |
63
|
|
|
|
64
|
|
|
return false; |
65
|
|
|
} |
66
|
|
|
$text = $page->getText(); |
67
|
|
|
if (empty($text)) { |
68
|
|
|
echo "SKIP : texte vide\n"; |
69
|
|
|
|
70
|
|
|
return false; |
71
|
|
|
} |
72
|
|
|
|
73
|
|
|
try { |
74
|
|
|
$parse = TemplateParser::parseAllTemplateByName('ouvrage', $text); |
75
|
|
|
} catch (Exception $e) { |
76
|
|
|
dump($e); |
77
|
|
|
|
78
|
|
|
return false; |
79
|
|
|
} |
80
|
|
|
|
81
|
|
|
if (empty($parse)) { |
82
|
|
|
return false; |
83
|
|
|
} |
84
|
|
|
$data = []; |
85
|
|
|
foreach ($parse['ouvrage'] as $res) { |
86
|
|
|
$thisdata = [ |
87
|
|
|
'page' => $title, |
88
|
|
|
'raw' => $res['raw'], |
89
|
|
|
'priority' => $priority, |
90
|
|
|
]; |
91
|
|
|
// filtre doublon |
92
|
|
|
if (!in_array($thisdata, $data)) { |
93
|
|
|
$data[] = $thisdata; |
94
|
|
|
} |
95
|
|
|
} |
96
|
|
|
|
97
|
|
|
$result = $this->db->insertPageOuvrages($data); |
98
|
|
|
dump($result); |
99
|
|
|
|
100
|
|
|
return !empty($result); |
101
|
|
|
} |
102
|
|
|
|
103
|
|
|
} |
104
|
|
|
|