aboutsummaryrefslogtreecommitdiffhomepage
path: root/src/Wallabag/CoreBundle/Helper/ContentProxy.php
blob: 076135c7ff96872011a3d6b80861adafd4903641 (plain) (blame)
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
<?php

namespace Wallabag\CoreBundle\Helper;

use Graby\Graby;
use Psr\Log\LoggerInterface;
use Symfony\Component\EventDispatcher\EventDispatcher;
use Wallabag\CoreBundle\Entity\Entry;
use Wallabag\CoreBundle\Tools\Utils;
use Symfony\Component\HttpFoundation\File\MimeType\MimeTypeExtensionGuesser;

/**
 * This kind of proxy class take care of getting the content from an url
 * and update the entry with what it found.
 */
class ContentProxy
{
    protected $graby;
    protected $tagger;
    protected $logger;
    protected $mimeGuesser;
    protected $fetchingErrorMessage;
    protected $eventDispatcher;

    public function __construct(Graby $graby, RuleBasedTagger $tagger, LoggerInterface $logger, $fetchingErrorMessage)
    {
        $this->graby = $graby;
        $this->tagger = $tagger;
        $this->logger = $logger;
        $this->mimeGuesser = new MimeTypeExtensionGuesser();
        $this->fetchingErrorMessage = $fetchingErrorMessage;
    }

    /**
     * Fetch content using graby and hydrate given entry with results information.
     * In case we couldn't find content, we'll try to use Open Graph data.
     *
     * We can also force the content, in case of an import from the v1 for example, so the function won't
     * fetch the content from the website but rather use information given with the $content parameter.
     *
     * @param Entry  $entry   Entry to update
     * @param string $url     Url to grab content for
     * @param array  $content An array with AT LEAST keys title, html, url, language & content_type to skip the fetchContent from the url
     *
     * @return Entry
     */
    public function updateEntry(Entry $entry, $url, array $content = [])
    {
        // do we have to fetch the content or the provided one is ok?
        if (empty($content) || false === $this->validateContent($content)) {
            $fetchedContent = $this->graby->fetchContent($url);

            // when content is imported, we have information in $content
            // in case fetching content goes bad, we'll keep the imported information instead of overriding them
            if (empty($content) || $fetchedContent['html'] !== $this->fetchingErrorMessage) {
                $content = $fetchedContent;
            }
        }

        $title = $content['title'];
        if (!$title && isset($content['open_graph']['og_title'])) {
            $title = $content['open_graph']['og_title'];
        }

        $html = $content['html'];
        if (false === $html) {
            $html = $this->fetchingErrorMessage;

            if (isset($content['open_graph']['og_description'])) {
                $html .= '<p><i>But we found a short description: </i></p>';
                $html .= $content['open_graph']['og_description'];
            }
        }

        $entry->setUrl($content['url'] ?: $url);
        $entry->setTitle($title);
        $entry->setContent($html);
        $entry->setHttpStatus(isset($content['status']) ? $content['status'] : '');

        if (isset($content['date']) && null !== $content['date'] && '' !== $content['date']) {
            $entry->setPublishedAt(new \DateTime($content['date']));
        }

        if (!empty($content['authors'])) {
            $entry->setPublishedBy($content['authors']);
        }

        if (!empty($content['all_headers'])) {
            $entry->setHeaders($content['all_headers']);
        }

        $entry->setLanguage(isset($content['language']) ? $content['language'] : '');
        $entry->setMimetype(isset($content['content_type']) ? $content['content_type'] : '');
        $entry->setReadingTime(Utils::getReadingTime($html));

        $domainName = parse_url($entry->getUrl(), PHP_URL_HOST);
        if (false !== $domainName) {
            $entry->setDomainName($domainName);
        }

        if (isset($content['open_graph']['og_image']) && $content['open_graph']['og_image']) {
            $entry->setPreviewPicture($content['open_graph']['og_image']);
        }

        // if content is an image define as a preview too
        if (isset($content['content_type']) && in_array($this->mimeGuesser->guess($content['content_type']), ['jpeg', 'jpg', 'gif', 'png'], true)) {
            $entry->setPreviewPicture($content['url']);
        }

        try {
            $this->tagger->tag($entry);
        } catch (\Exception $e) {
            $this->logger->error('Error while trying to automatically tag an entry.', [
                'entry_url' => $url,
                'error_msg' => $e->getMessage(),
            ]);
        }

        return $entry;
    }

    /**
     * Validate that the given content as enough value to be used
     * instead of fetch the content from the url.
     *
     * @param array $content
     *
     * @return bool true if valid otherwise false
     */
    private function validateContent(array $content)
    {
        return isset($content['title']) && isset($content['html']) && isset($content['url']) && isset($content['language']) && isset($content['content_type']);
    }
}