|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* Copyright (c) 2015-2015 Andreas Heigl<[email protected]> |
|
4
|
|
|
* |
|
5
|
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy |
|
6
|
|
|
* of this software and associated documentation files (the "Software"), to deal |
|
7
|
|
|
* in the Software without restriction, including without limitation the rights |
|
8
|
|
|
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
|
9
|
|
|
* copies of the Software, and to permit persons to whom the Software is |
|
10
|
|
|
* furnished to do so, subject to the following conditions: |
|
11
|
|
|
* |
|
12
|
|
|
* The above copyright notice and this permission notice shall be included in |
|
13
|
|
|
* all copies or substantial portions of the Software. |
|
14
|
|
|
* |
|
15
|
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
|
16
|
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
|
17
|
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE |
|
18
|
|
|
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
|
19
|
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
|
20
|
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN |
|
21
|
|
|
* THE SOFTWARE. |
|
22
|
|
|
* |
|
23
|
|
|
* @author Andreas Heigl<[email protected]> |
|
24
|
|
|
* @copyright 2015-2015 Andreas Heigl/callingallpapers.com |
|
25
|
|
|
* @license http://www.opensource.org/licenses/mit-license.php MIT-License |
|
26
|
|
|
* @version 0.0 |
|
27
|
|
|
* @since 06.03.2012 |
|
28
|
|
|
* @link http://github.com/joindin/callingallpapers |
|
29
|
|
|
*/ |
|
30
|
|
|
namespace Callingallpapers\Parser\PapercallIo; |
|
31
|
|
|
|
|
32
|
|
|
use Callingallpapers\Entity\Cfp; |
|
33
|
|
|
use Callingallpapers\Service\TimezoneService; |
|
34
|
|
|
use GuzzleHttp\Client; |
|
35
|
|
|
|
|
36
|
|
|
class Entry |
|
37
|
|
|
{ |
|
38
|
|
|
/** @var Cfp */ |
|
39
|
|
|
protected $cfp; |
|
40
|
|
|
|
|
41
|
|
|
/** @var Client */ |
|
42
|
|
|
protected $client; |
|
43
|
|
|
|
|
44
|
|
|
public function __construct(Cfp $cfp, Client $client, TimezoneService $timezoneService) |
|
45
|
|
|
{ |
|
46
|
|
|
$this->cfp = $cfp; |
|
47
|
|
|
$this->client = $client; |
|
48
|
|
|
$this->tzService = $timezoneService; |
|
|
|
|
|
|
49
|
|
|
} |
|
50
|
|
|
|
|
51
|
|
View Code Duplication |
public function parse($uri) |
|
|
|
|
|
|
52
|
|
|
{ |
|
53
|
|
|
$cfp = clone($this->cfp); |
|
54
|
|
|
try { |
|
55
|
|
|
$dom = new \DOMDocument('1.0', 'UTF-8'); |
|
56
|
|
|
|
|
57
|
|
|
$content = file_Get_contents($uri); |
|
58
|
|
|
$content = mb_convert_encoding($content, 'UTF-8'); |
|
59
|
|
|
$dom->loadHTML('<?xml version="1.0" charset="UTF-8" ?>' . $content); |
|
60
|
|
|
$dom->preserveWhiteSpace = false; |
|
61
|
|
|
|
|
62
|
|
|
$timezone = 'UTC'; |
|
63
|
|
|
$xpath = new \DOMXPath($dom); |
|
64
|
|
|
|
|
65
|
|
|
$eventLocation = new Location(); |
|
66
|
|
|
$cfp->location = $eventLocation->parse($dom, $xpath); |
|
67
|
|
|
|
|
68
|
|
|
try { |
|
69
|
|
|
$location = $this->getLatLonForLocation($cfp->location); |
|
70
|
|
|
$cfp->latitude = $location[0]; |
|
|
|
|
|
|
71
|
|
|
$cfp->longitude = $location[1]; |
|
|
|
|
|
|
72
|
|
|
$timezone = $this->tzService->getTimezoneForLocation($location[0], $location[1]); |
|
73
|
|
|
} catch (\UnexpectedValueException $e) { |
|
74
|
|
|
error_log($e->getMessage()); |
|
75
|
|
|
} |
|
76
|
|
|
$cfp->timezone = $timezone; |
|
77
|
|
|
|
|
78
|
|
|
|
|
79
|
|
|
$closingDateParser = new ClosingDate($timezone); |
|
80
|
|
|
$cfp->dateEnd = $closingDateParser->parse($dom, $xpath); |
|
|
|
|
|
|
81
|
|
|
|
|
82
|
|
|
$eventPageDom = $this->getEventPage($xpath); |
|
83
|
|
|
$eventXpath = new \DOMXPath(($eventPageDom)); |
|
84
|
|
|
|
|
85
|
|
|
$descriptionParser = new Description(); |
|
86
|
|
|
$cfp->description = $descriptionParser->parse($dom, $xpath); |
|
87
|
|
|
|
|
88
|
|
|
$openingDateParser = new OpeningDate($timezone); |
|
89
|
|
|
try { |
|
90
|
|
|
$cfp->dateStart = $openingDateParser->parse($dom, $xpath); |
|
91
|
|
|
} catch (\Exception $e) {} |
|
|
|
|
|
|
92
|
|
|
|
|
93
|
|
|
$cfpUriParser = new Uri(); |
|
94
|
|
|
$cfp->uri = $cfpUriParser->parse($dom, $xpath); |
|
95
|
|
|
|
|
96
|
|
|
$confNameParser = new EventName(); |
|
97
|
|
|
$cfp->conferenceName = $confNameParser->parse($dom, $xpath); |
|
98
|
|
|
|
|
99
|
|
|
$confUriParser = new EventUri(); |
|
100
|
|
|
$cfp->conferenceUri = $confUriParser->parse($eventPageDom, $eventXpath); |
|
101
|
|
|
|
|
102
|
|
|
$eventStartDate = new EventStartDate($timezone); |
|
103
|
|
|
$cfp->eventStartDate = $eventStartDate->parse($dom, $xpath); |
|
104
|
|
|
|
|
105
|
|
|
try { |
|
106
|
|
|
$eventEndDate = new EventEndDate($timezone); |
|
107
|
|
|
$cfp->eventEndDate = $eventEndDate->parse($dom, $xpath); |
|
108
|
|
|
} catch (\InvalidArgumentException $e) { |
|
109
|
|
|
$cfp->eventEndDate = $cfp->eventStartDate; |
|
110
|
|
|
} |
|
111
|
|
|
|
|
112
|
|
|
$eventLocation = new Location(); |
|
113
|
|
|
$cfp->location = $eventLocation->parse($dom, $xpath); |
|
114
|
|
|
|
|
115
|
|
|
try { |
|
116
|
|
|
$location = $this->getLatLonForLocation($cfp->location); |
|
117
|
|
|
$cfp->latitude = $location[0]; |
|
118
|
|
|
$cfp->longitude = $location[1]; |
|
119
|
|
|
} catch (\UnexpectedValueException $e) { |
|
120
|
|
|
error_log($e->getMessage()); |
|
121
|
|
|
} |
|
122
|
|
|
|
|
123
|
|
|
try { |
|
124
|
|
|
$tags = new Tags(); |
|
125
|
|
|
$cfp->tags = $tags->parse($eventPageDom, $eventXpath); |
|
126
|
|
|
} catch (\InvalidArgumentException $e) { |
|
127
|
|
|
$cfp->tags = []; |
|
128
|
|
|
} |
|
129
|
|
|
|
|
130
|
|
|
return $cfp; |
|
131
|
|
|
} catch (\Exception $e) { |
|
132
|
|
|
throw $e; |
|
133
|
|
|
} |
|
134
|
|
|
} |
|
135
|
|
|
|
|
136
|
|
View Code Duplication |
protected function getLatLonForLocation($location) |
|
|
|
|
|
|
137
|
|
|
{ |
|
138
|
|
|
$result = $this->client->get(sprintf( |
|
139
|
|
|
'https://nominatim.openstreetmap.org/search?q=%1$s&format=json', |
|
140
|
|
|
urlencode($location) |
|
141
|
|
|
)); |
|
142
|
|
|
|
|
143
|
|
|
$locations = json_decode($result->getBody()->getContents()); |
|
144
|
|
|
|
|
145
|
|
|
if (empty($locations)) { |
|
146
|
|
|
return [0, 0]; |
|
147
|
|
|
} |
|
148
|
|
|
$location = $locations[0]; |
|
149
|
|
|
|
|
150
|
|
|
return [$location->lat, $location->lon]; |
|
151
|
|
|
} |
|
152
|
|
|
|
|
153
|
|
|
public function getEventPage($xpath) |
|
154
|
|
|
{ |
|
155
|
|
|
$confPath = $xpath->query("//h3/a[contains(@class, 'summary')]"); |
|
156
|
|
|
|
|
157
|
|
|
if (! $confPath || $confPath->length == 0) { |
|
158
|
|
|
throw new \InvalidArgumentException('We can\'t find an EventPage'); |
|
159
|
|
|
} |
|
160
|
|
|
|
|
161
|
|
|
$dom = new \DOMDocument('1.0', 'UTF-8'); |
|
162
|
|
|
|
|
163
|
|
|
$content = file_get_contents('https://lanyrd.com' . $confPath->item(0)->attributes->getNamedItem('href')->textContent); |
|
164
|
|
|
$content = mb_convert_encoding($content, 'UTF-8'); |
|
165
|
|
|
$dom->loadHTML('<?xml version="1.0" charset="UTF-8" ?>' . $content); |
|
166
|
|
|
$dom->preserveWhiteSpace = false; |
|
167
|
|
|
|
|
168
|
|
|
return $dom; |
|
169
|
|
|
} |
|
170
|
|
|
} |
|
171
|
|
|
|
In PHP it is possible to write to properties without declaring them. For example, the following is perfectly valid PHP code:
Generally, it is a good practice to explictly declare properties to avoid accidental typos and provide IDE auto-completion: