1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
declare(strict_types=1); |
4
|
|
|
|
5
|
|
|
/* |
6
|
|
|
* (c) Christian Gripp <[email protected]> |
7
|
|
|
* |
8
|
|
|
* For the full copyright and license information, please view the LICENSE |
9
|
|
|
* file that was distributed with this source code. |
10
|
|
|
*/ |
11
|
|
|
|
12
|
|
|
namespace Core23\LastFm\Crawler; |
13
|
|
|
|
14
|
|
|
use Core23\LastFm\Connection\ConnectionInterface; |
15
|
|
|
use Core23\LastFm\Exception\CrawlException; |
16
|
|
|
use Core23\LastFm\Model\Event; |
17
|
|
|
use Core23\LastFm\Model\Image; |
18
|
|
|
use DateTime; |
19
|
|
|
use Symfony\Component\DomCrawler\Crawler; |
20
|
|
|
|
21
|
|
|
abstract class AbstractCrawler |
22
|
|
|
{ |
23
|
|
|
public const URL_PREFIX = 'http://last.fm'; |
24
|
|
|
|
25
|
|
|
public const NEWLINE = "\n"; |
26
|
|
|
|
27
|
|
|
/** |
28
|
|
|
* @var ConnectionInterface |
29
|
|
|
*/ |
30
|
|
|
private $connection; |
31
|
|
|
|
32
|
|
|
/** |
33
|
|
|
* @param ConnectionInterface $connection |
34
|
|
|
*/ |
35
|
|
|
public function __construct(ConnectionInterface $connection) |
36
|
|
|
{ |
37
|
|
|
$this->connection = $connection; |
38
|
|
|
} |
39
|
|
|
|
40
|
|
|
/** |
41
|
|
|
* @param Crawler|null $node |
42
|
|
|
* |
43
|
|
|
* @return array |
44
|
|
|
*/ |
45
|
|
|
final protected function crawlEventList(Crawler $node): array |
46
|
|
|
{ |
47
|
|
|
$resultList = []; |
48
|
|
|
|
49
|
|
|
$node->filter('.page-content section')->each(function (Crawler $node) use (&$resultList) { |
50
|
|
|
$headingNode = $node->filter('.group-heading'); |
51
|
|
|
|
52
|
|
|
$datetime = new DateTime(trim($headingNode->text())); |
53
|
|
|
|
54
|
|
|
$resultList = array_merge($resultList, $this->crawlEventListGroup($node, $datetime)); |
55
|
|
|
}); |
56
|
|
|
|
57
|
|
|
return $resultList; |
58
|
|
|
} |
59
|
|
|
|
60
|
|
|
/** |
61
|
|
|
* @param Crawler $node |
62
|
|
|
* @param DateTime $datetime |
63
|
|
|
* |
64
|
|
|
* @return array |
65
|
|
|
*/ |
66
|
|
|
protected function crawlEventListGroup(Crawler $node, DateTime $datetime): array |
67
|
|
|
{ |
68
|
|
|
return $node->filter('.events-list-item')->each( |
69
|
|
|
function (Crawler $node) use ($datetime): Event { |
|
|
|
|
70
|
|
|
$eventNode = $node->filter('.events-list-item-event--title a'); |
71
|
|
|
|
72
|
|
|
$url = $this->parseUrl($eventNode); |
73
|
|
|
|
74
|
|
|
if (null === $url) { |
75
|
|
|
throw new CrawlException('Error parsing event id.'); |
76
|
|
|
} |
77
|
|
|
|
78
|
|
|
$id = (int) preg_replace('/.*\/(\d+)+.*/', '$1', $url); |
79
|
|
|
|
80
|
|
|
if (0 === $id) { |
81
|
|
|
throw new CrawlException('Error parsing event id.'); |
82
|
|
|
} |
83
|
|
|
|
84
|
|
|
return new Event( |
85
|
|
|
$id, |
86
|
|
|
$this->parseString($eventNode) ?? '', |
87
|
|
|
$datetime, |
88
|
|
|
$url |
89
|
|
|
); |
90
|
|
|
} |
91
|
|
|
); |
92
|
|
|
} |
93
|
|
|
|
94
|
|
|
/** |
95
|
|
|
* Crawles a url. |
96
|
|
|
* |
97
|
|
|
* @param string $url |
98
|
|
|
* |
99
|
|
|
* @return Crawler|null |
100
|
|
|
*/ |
101
|
|
|
final protected function crawl(string $url): ?Crawler |
102
|
|
|
{ |
103
|
|
|
if ($content = $this->connection->getPageBody($url)) { |
104
|
|
|
return new Crawler($content); |
105
|
|
|
} |
106
|
|
|
|
107
|
|
|
return null; |
108
|
|
|
} |
109
|
|
|
|
110
|
|
|
/** |
111
|
|
|
* Parses a url node. |
112
|
|
|
* |
113
|
|
|
* @param Crawler $node |
114
|
|
|
* @param string $attr |
115
|
|
|
* |
116
|
|
|
* @return string|null |
117
|
|
|
*/ |
118
|
|
|
final protected function parseUrl(Crawler $node, string $attr = 'href'): ?string |
119
|
|
|
{ |
120
|
|
|
if (0 === $node->count()) { |
121
|
|
|
return null; |
122
|
|
|
} |
123
|
|
|
|
124
|
|
|
if ($url = $node->attr($attr)) { |
125
|
|
|
return preg_replace('/^\//', static::URL_PREFIX.'/', $url); |
126
|
|
|
} |
127
|
|
|
|
128
|
|
|
return null; |
129
|
|
|
} |
130
|
|
|
|
131
|
|
|
/** |
132
|
|
|
* Parses an image node. |
133
|
|
|
* |
134
|
|
|
* @param Crawler $node |
135
|
|
|
* |
136
|
|
|
* @return Image|null |
137
|
|
|
*/ |
138
|
|
|
final protected function parseImage(Crawler $node): ?Image |
139
|
|
|
{ |
140
|
|
|
$src = $this->parseUrl($node, 'src'); |
141
|
|
|
|
142
|
|
|
if (!$src) { |
|
|
|
|
143
|
|
|
return null; |
144
|
|
|
} |
145
|
|
|
|
146
|
|
|
return new Image($src); |
147
|
|
|
} |
148
|
|
|
|
149
|
|
|
/** |
150
|
|
|
* Parses a string node. |
151
|
|
|
* |
152
|
|
|
* @param Crawler $node |
153
|
|
|
* @param bool $multiline |
154
|
|
|
* |
155
|
|
|
* @return string|null |
156
|
|
|
*/ |
157
|
|
|
final protected function parseString(Crawler $node, bool $multiline = false): ?string |
158
|
|
|
{ |
159
|
|
|
if (0 === $node->count()) { |
160
|
|
|
return null; |
161
|
|
|
} |
162
|
|
|
|
163
|
|
|
$content = $node->attr('content'); |
164
|
|
|
|
165
|
|
|
if (null === $content) { |
166
|
|
|
if ($multiline) { |
167
|
|
|
$content = $node->html(); |
168
|
|
|
$content = (string) preg_replace('/<p[^>]*?>/', '', $content); |
169
|
|
|
$content = str_replace('</p>', static::NEWLINE, $content); |
170
|
|
|
$content = (string) preg_replace('/<br\s?\/?>/i', static::NEWLINE, $content); |
171
|
|
|
} else { |
172
|
|
|
$content = $node->text(); |
173
|
|
|
} |
174
|
|
|
} |
175
|
|
|
|
176
|
|
|
return trim(strip_tags($content)); |
177
|
|
|
} |
178
|
|
|
|
179
|
|
|
/** |
180
|
|
|
* Parses a date note. |
181
|
|
|
* |
182
|
|
|
* @param Crawler $node |
183
|
|
|
* |
184
|
|
|
* @return \DateTime|null |
185
|
|
|
*/ |
186
|
|
|
final protected function parseDate(Crawler $node): ?\DateTime |
187
|
|
|
{ |
188
|
|
|
$content = $this->parseString($node); |
189
|
|
|
|
190
|
|
|
if (null !== $content) { |
191
|
|
|
return new \DateTime($content); |
192
|
|
|
} |
193
|
|
|
|
194
|
|
|
return null; |
195
|
|
|
} |
196
|
|
|
} |
197
|
|
|
|