|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/** |
|
4
|
|
|
* Rss/Atom Bundle for Symfony. |
|
5
|
|
|
* |
|
6
|
|
|
* |
|
7
|
|
|
* @license http://opensource.org/licenses/lgpl-3.0.html LGPL |
|
8
|
|
|
* @copyright (c) 2013, Alexandre Debril |
|
9
|
|
|
*/ |
|
10
|
|
|
namespace Debril\RssAtomBundle\Protocol; |
|
11
|
|
|
|
|
12
|
|
|
use Debril\RssAtomBundle\Protocol\Filter\ModifiedSince; |
|
13
|
|
|
use Debril\RssAtomBundle\Protocol\Parser\XmlParser; |
|
14
|
|
|
use SimpleXMLElement; |
|
15
|
|
|
use Debril\RssAtomBundle\Driver\HttpDriverInterface; |
|
16
|
|
|
use Debril\RssAtomBundle\Driver\HttpDriverResponse; |
|
17
|
|
|
use Debril\RssAtomBundle\Protocol\Parser\Factory; |
|
18
|
|
|
use Debril\RssAtomBundle\Exception\ParserException; |
|
19
|
|
|
use Debril\RssAtomBundle\Exception\FeedException\FeedCannotBeReadException; |
|
20
|
|
|
use Debril\RssAtomBundle\Exception\FeedException\FeedNotFoundException; |
|
21
|
|
|
use Debril\RssAtomBundle\Exception\FeedException\FeedNotModifiedException; |
|
22
|
|
|
use Debril\RssAtomBundle\Exception\FeedException\FeedServerErrorException; |
|
23
|
|
|
use Debril\RssAtomBundle\Exception\FeedException\FeedForbiddenException; |
|
24
|
|
|
|
|
25
|
|
|
/** |
|
26
|
|
|
* Class to read any kind of supported feeds (RSS, ATOM, and more if you need). |
|
27
|
|
|
* |
|
28
|
|
|
* FeedReader uses an HttpDriverInterface to pull feeds and one more Parser instances to |
|
29
|
|
|
* parse them. For each feed, FeedReader automatically chooses the accurate |
|
30
|
|
|
* Parser and use it to return a FeedContent instance. |
|
31
|
|
|
* |
|
32
|
|
|
* <code> |
|
33
|
|
|
* // HttpDriverInterface and Factory instances are required to construct a FeedReader. |
|
34
|
|
|
* // Here we use the HttpCurlDriver (recommanded) |
|
35
|
|
|
* $reader = new FeedReader(new HttpCurlDriver(), new Factory()); |
|
36
|
|
|
* |
|
37
|
|
|
* // now we add the parsers |
|
38
|
|
|
* $reader->addParser(new AtomParser()); |
|
39
|
|
|
* $reader->addParser(new RssParser()); |
|
40
|
|
|
* |
|
41
|
|
|
* // $url is obviously the feed you want to read |
|
42
|
|
|
* // $dateTime is the last moment you read the feed |
|
43
|
|
|
* $content = $reader->getFeedContent($url, $dateTime); |
|
44
|
|
|
* |
|
45
|
|
|
* // now we can display the feed's content |
|
46
|
|
|
* echo $feed->getTitle(); |
|
47
|
|
|
* |
|
48
|
|
|
* // each |
|
49
|
|
|
* foreach( $content->getItems() as $item ) |
|
50
|
|
|
* { |
|
51
|
|
|
* echo $item->getTitle(); |
|
52
|
|
|
* echo $item->getSummary(); |
|
53
|
|
|
* } |
|
54
|
|
|
* </code> |
|
55
|
|
|
*/ |
|
56
|
|
|
class FeedReader |
|
57
|
|
|
{ |
|
58
|
|
|
/** |
|
59
|
|
|
* @var Parser[] |
|
60
|
|
|
*/ |
|
61
|
|
|
protected $parsers = array(); |
|
62
|
|
|
|
|
63
|
|
|
/** |
|
64
|
|
|
* @var HttpDriverInterface |
|
65
|
|
|
*/ |
|
66
|
|
|
protected $driver = null; |
|
67
|
|
|
|
|
68
|
|
|
/** |
|
69
|
|
|
* @var Factory |
|
70
|
|
|
*/ |
|
71
|
|
|
protected $factory = null; |
|
72
|
|
|
|
|
73
|
|
|
/** |
|
74
|
|
|
* @var XmlParser |
|
75
|
|
|
*/ |
|
76
|
|
|
protected $xmlParser = null; |
|
77
|
|
|
|
|
78
|
|
|
/** |
|
79
|
|
|
* @param HttpDriverInterface $driver |
|
80
|
|
|
* @param Factory $factory |
|
81
|
|
|
*/ |
|
82
|
2 |
|
public function __construct(HttpDriverInterface $driver, Factory $factory, XmlParser $xmlParser) |
|
83
|
|
|
{ |
|
84
|
2 |
|
$this->driver = $driver; |
|
85
|
2 |
|
$this->factory = $factory; |
|
86
|
2 |
|
$this->xmlParser = $xmlParser; |
|
87
|
2 |
|
} |
|
88
|
|
|
|
|
89
|
|
|
/** |
|
90
|
|
|
* Add a Parser. |
|
91
|
|
|
* |
|
92
|
|
|
* @param Parser $parser |
|
93
|
|
|
* |
|
94
|
|
|
* @return FeedReader |
|
95
|
|
|
*/ |
|
96
|
2 |
|
public function addParser(Parser $parser) |
|
97
|
|
|
{ |
|
98
|
2 |
|
$parser->setFactory($this->factory); |
|
99
|
2 |
|
$this->parsers[] = $parser; |
|
100
|
|
|
|
|
101
|
2 |
|
return $this; |
|
102
|
|
|
} |
|
103
|
|
|
|
|
104
|
|
|
/** |
|
105
|
|
|
* @return HttpDriverInterface |
|
106
|
|
|
*/ |
|
107
|
2 |
|
public function getDriver() |
|
108
|
|
|
{ |
|
109
|
2 |
|
return $this->driver; |
|
110
|
|
|
} |
|
111
|
|
|
|
|
112
|
|
|
/** |
|
113
|
|
|
* Read a feed using its url and create a FeedInInterface instance |
|
114
|
|
|
* Second parameter can be either a \DateTime instance or a numeric limit. |
|
115
|
|
|
* |
|
116
|
|
|
* @param string $url |
|
117
|
|
|
* @param \DateTime $arg |
|
118
|
|
|
* |
|
119
|
|
|
* @return FeedInInterface|FeedContent |
|
120
|
|
|
*/ |
|
121
|
4 |
|
public function getFeedContent($url, $arg = null) |
|
122
|
|
|
{ |
|
123
|
4 |
|
if (is_numeric($arg)) { |
|
124
|
|
|
return $this->getFilteredContent($url, array( |
|
125
|
|
|
new Filter\Limit($arg), |
|
126
|
|
|
)); |
|
127
|
|
|
} |
|
128
|
4 |
|
if ($arg instanceof \DateTime) { |
|
129
|
4 |
|
return $this->getFeedContentSince($url, $arg); |
|
130
|
|
|
} |
|
131
|
|
|
|
|
132
|
|
|
return $this->getFilteredContent($url, array()); |
|
133
|
|
|
} |
|
134
|
|
|
|
|
135
|
|
|
/** |
|
136
|
|
|
* @param string $url |
|
137
|
|
|
* @param array $filters |
|
138
|
|
|
* @param \DateTime $modifiedSince |
|
139
|
|
|
* |
|
140
|
|
|
* @return FeedInInterface |
|
141
|
|
|
*/ |
|
142
|
1 |
|
public function getFilteredContent($url, array $filters, \DateTime $modifiedSince = null) |
|
143
|
|
|
{ |
|
144
|
1 |
|
$response = $this->getResponse($url, $modifiedSince); |
|
145
|
|
|
|
|
146
|
1 |
|
return $this->parseBody($response, $this->factory->newFeed(), $filters); |
|
147
|
|
|
} |
|
148
|
|
|
|
|
149
|
|
|
/** |
|
150
|
|
|
* @param string $url |
|
151
|
|
|
* @param \DateTime $modifiedSince |
|
152
|
|
|
* |
|
153
|
|
|
* @return FeedInInterface |
|
154
|
|
|
*/ |
|
155
|
1 |
|
public function getFeedContentSince($url, \DateTime $modifiedSince) |
|
156
|
|
|
{ |
|
157
|
|
|
$filters = array( |
|
158
|
1 |
|
new Filter\ModifiedSince($modifiedSince), |
|
159
|
1 |
|
); |
|
160
|
|
|
|
|
161
|
1 |
|
return $this->getFilteredContent($url, $filters); |
|
162
|
|
|
} |
|
163
|
|
|
|
|
164
|
|
|
/** |
|
165
|
|
|
* Read a feed using its url and hydrate the given FeedInInterface instance. |
|
166
|
|
|
* |
|
167
|
|
|
* @param string $url |
|
168
|
|
|
* @param FeedInInterface $feed |
|
169
|
|
|
* @param \DateTime $modifiedSince |
|
170
|
|
|
* |
|
171
|
|
|
* @return FeedInInterface |
|
172
|
|
|
*/ |
|
173
|
1 |
|
public function readFeed($url, FeedInInterface $feed, \DateTime $modifiedSince) |
|
174
|
|
|
{ |
|
175
|
1 |
|
$response = $this->getResponse($url, $modifiedSince); |
|
176
|
|
|
|
|
177
|
|
|
$filters = array( |
|
178
|
1 |
|
new ModifiedSince($modifiedSince), |
|
179
|
1 |
|
); |
|
180
|
|
|
|
|
181
|
1 |
|
return $this->parseBody($response, $feed, $filters); |
|
182
|
|
|
} |
|
183
|
|
|
|
|
184
|
|
|
/** |
|
185
|
|
|
* Read the XML stream hosted at $url. |
|
186
|
|
|
* |
|
187
|
|
|
* @param $url |
|
188
|
|
|
* @param \Datetime $modifiedSince |
|
189
|
|
|
* |
|
190
|
|
|
* @return HttpDriverResponse |
|
191
|
|
|
*/ |
|
192
|
2 |
|
public function getResponse($url, \Datetime $modifiedSince = null) |
|
193
|
|
|
{ |
|
194
|
2 |
|
if (is_null($modifiedSince)) { |
|
195
|
1 |
|
$modifiedSince = new \DateTime('@0'); |
|
196
|
1 |
|
} |
|
197
|
|
|
|
|
198
|
2 |
|
return $this->getDriver()->getResponse($url, $modifiedSince); |
|
199
|
|
|
} |
|
200
|
|
|
|
|
201
|
|
|
/** |
|
202
|
|
|
* Parse the body of a feed and write it into the FeedInInterface instance. |
|
203
|
|
|
* |
|
204
|
|
|
* @param HttpDriverResponse $response |
|
205
|
|
|
* @param FeedInInterface $feed |
|
206
|
|
|
* @param array $filters |
|
207
|
|
|
* |
|
208
|
|
|
* @return FeedInInterface |
|
209
|
|
|
*/ |
|
210
|
10 |
|
public function parseBody(HttpDriverResponse $response, FeedInInterface $feed, array $filters = array()) |
|
211
|
|
|
{ |
|
212
|
10 |
|
if ($response->getHttpCodeIsOk() |
|
213
|
10 |
|
|| $response->getHttpCodeIsRedirection()) { |
|
214
|
5 |
|
$xmlBody = $this->xmlParser->parseString($response->getBody()); |
|
215
|
5 |
|
$parser = $this->getAccurateParser($xmlBody); |
|
216
|
|
|
|
|
217
|
5 |
|
return $parser->parse($xmlBody, $feed, $filters); |
|
|
|
|
|
|
218
|
|
|
} |
|
219
|
|
|
|
|
220
|
5 |
|
switch ($response->getHttpCode()) { |
|
221
|
5 |
|
case HttpDriverResponse::HTTP_CODE_NOT_FOUND: |
|
222
|
1 |
|
throw new FeedNotFoundException($response->getHttpMessage()); |
|
223
|
4 |
|
case HttpDriverResponse::HTTP_CODE_NOT_MODIFIED: |
|
224
|
1 |
|
throw new FeedNotModifiedException($response->getHttpMessage()); |
|
225
|
3 |
|
case HttpDriverResponse::HTTP_CODE_SERVER_ERROR: |
|
226
|
1 |
|
throw new FeedServerErrorException($response->getHttpMessage()); |
|
227
|
2 |
|
case HttpDriverResponse::HTTP_CODE_FORBIDDEN: |
|
228
|
1 |
|
throw new FeedForbiddenException($response->getHttpMessage()); |
|
229
|
1 |
|
default: |
|
230
|
1 |
|
throw new FeedCannotBeReadException($response->getHttpMessage(), $response->getHttpCode()); |
|
231
|
1 |
|
} |
|
232
|
|
|
} |
|
233
|
|
|
|
|
234
|
|
|
/** |
|
235
|
|
|
* Choose the accurate Parser for the XML stream. |
|
236
|
|
|
* |
|
237
|
|
|
* @param SimpleXMLElement $xmlBody |
|
238
|
|
|
* |
|
239
|
|
|
* @throws ParserException |
|
240
|
|
|
* |
|
241
|
|
|
* @return Parser |
|
242
|
|
|
*/ |
|
243
|
3 |
|
public function getAccurateParser(SimpleXMLElement $xmlBody) |
|
244
|
|
|
{ |
|
245
|
3 |
|
foreach ($this->parsers as $parser) { |
|
246
|
2 |
|
if ($parser->canHandle($xmlBody)) { |
|
247
|
2 |
|
return $parser; |
|
248
|
|
|
} |
|
249
|
3 |
|
} |
|
250
|
|
|
|
|
251
|
1 |
|
throw new ParserException('No parser can handle this stream'); |
|
252
|
|
|
} |
|
253
|
|
|
} |
|
254
|
|
|
|
This check looks for parameters that are defined as one type in their type hint or doc comment but seem to be used as a narrower type, i.e an implementation of an interface or a subclass.
Consider changing the type of the parameter or doing an instanceof check before assuming your parameter is of the expected type.