blob: e5b9817feaab500a96b9c5affc74f7abef19b15f (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
|
<?php
namespace PicoFeed\Scraper;
use PicoFeed\Base;
use PicoFeed\Client\Client;
use PicoFeed\Client\ClientException;
use PicoFeed\Client\Url;
use PicoFeed\Encoding\Encoding;
use PicoFeed\Filter\Filter;
use PicoFeed\Logging\Logger;
use PicoFeed\Parser\XmlParser;
/**
* Scraper class.
*
* @author Frederic Guillot
*/
class Scraper extends Base
{
/**
* URL.
*
* @var string
*/
private $url = '';
/**
* Relevant content.
*
* @var string
*/
private $content = '';
/**
* HTML content.
*
* @var string
*/
private $html = '';
/**
* HTML content encoding.
*
* @var string
*/
private $encoding = '';
/**
* Flag to enable candidates parsing.
*
* @var bool
*/
private $enableCandidateParser = true;
/**
* Disable candidates parsing.
*
* @return Scraper
*/
public function disableCandidateParser()
{
$this->enableCandidateParser = false;
return $this;
}
/**
* Get encoding.
*
* @return string
*/
public function getEncoding()
{
return $this->encoding;
}
/**
* Set encoding.
*
* @param string $encoding
*
* @return Scraper
*/
public function setEncoding($encoding)
{
$this->encoding = $encoding;
return $this;
}
/**
* Get URL to download.
*
* @return string
*/
public function getUrl()
{
return $this->url;
}
/**
* Set URL to download.
*
* @param string $url URL
*
* @return Scraper
*/
public function setUrl($url)
{
$this->url = $url;
return $this;
}
/**
* Return true if the scraper found relevant content.
*
* @return bool
*/
public function hasRelevantContent()
{
return !empty($this->content);
}
/**
* Get relevant content.
*
* @return string
*/
public function getRelevantContent()
{
return $this->content;
}
/**
* Get raw content (unfiltered).
*
* @return string
*/
public function getRawContent()
{
return $this->html;
}
/**
* Set raw content (unfiltered).
*
* @param string $html
*
* @return Scraper
*/
public function setRawContent($html)
{
$this->html = $html;
return $this;
}
/**
* Get filtered relevant content.
*
* @return string
*/
public function getFilteredContent()
{
$filter = Filter::html($this->content, $this->url);
$filter->setConfig($this->config);
return $filter->execute();
}
/**
* Download the HTML content.
*
* @return bool
*/
public function download()
{
if (!empty($this->url)) {
// Clear everything
$this->html = '';
$this->content = '';
$this->encoding = '';
try {
$client = Client::getInstance();
$client->setConfig($this->config);
$client->setTimeout($this->config->getGrabberTimeout());
$client->setUserAgent($this->config->getGrabberUserAgent());
$client->execute($this->url);
$this->url = $client->getUrl();
$this->html = $client->getContent();
$this->encoding = $client->getEncoding();
return true;
} catch (ClientException $e) {
Logger::setMessage(get_called_class().': '.$e->getMessage());
}
}
return false;
}
/**
* Execute the scraper.
*/
public function execute($pageContent = '', $recursionDepth = 0)
{
$this->html = '';
$this->encoding = '';
$this->content = '';
$this->download();
$this->prepareHtml();
$parser = $this->getParser();
if ($parser !== null) {
$maxRecursions = $this->config->getMaxRecursions();
if(!isset($maxRecursions)){
$maxRecursions = 25;
}
$pageContent .= $parser->execute();
// check if there is a link to next page and recursively get content (max 25 pages)
if((($nextLink = $parser->findNextLink()) !== null) && $recursionDepth < $maxRecursions){
$nextLink = Url::resolve($nextLink,$this->url);
$this->setUrl($nextLink);
$this->execute($pageContent,$recursionDepth+1);
}
else{
$this->content = $pageContent;
}
Logger::setMessage(get_called_class().': Content length: '.strlen($this->content).' bytes');
}
}
/**
* Get the parser.
*
* @return ParserInterface
*/
public function getParser()
{
$ruleLoader = new RuleLoader($this->config);
$rules = $ruleLoader->getRules($this->url);
if (!empty($rules['grabber'])) {
Logger::setMessage(get_called_class().': Parse content with rules');
foreach ($rules['grabber'] as $pattern => $rule) {
$url = new Url($this->url);
$sub_url = $url->getFullPath();
if (preg_match($pattern, $sub_url)) {
Logger::setMessage(get_called_class().': Matched url '.$sub_url);
return new RuleParser($this->html, $rule);
}
}
} elseif ($this->enableCandidateParser) {
Logger::setMessage(get_called_class().': Parse content with candidates');
}
return new CandidateParser($this->html);
}
/**
* Normalize encoding and strip head tag.
*/
public function prepareHtml()
{
$html_encoding = XmlParser::getEncodingFromMetaTag($this->html);
$this->html = Encoding::convert($this->html, $html_encoding ?: $this->encoding);
$this->html = Filter::stripHeadTags($this->html);
Logger::setMessage(get_called_class().': HTTP Encoding "'.$this->encoding.'" ; HTML Encoding "'.$html_encoding.'"');
}
}
|
