diff options
Diffstat (limited to 'include')
| -rwxr-xr-x | include/items.php | 36 | ||||
| -rw-r--r-- | include/network.php | 80 |
2 files changed, 85 insertions, 31 deletions
diff --git a/include/items.php b/include/items.php index 30aa30048..a3f423836 100755 --- a/include/items.php +++ b/include/items.php @@ -802,37 +802,6 @@ function import_author_xchan($x) { } /** - * @brief Imports an author from Diaspora. - * - * @param array $x an associative array with - * * \e string \b address - * @return boolean|string false on error, otherwise xchan_hash of the new entry - */ -function import_author_diaspora($x) { - if(! $x['address']) - return false; - - $r = q("select * from xchan where xchan_addr = '%s' limit 1", - dbesc($x['address']) - ); - if($r) { - logger('in_cache: ' . $x['address'], LOGGER_DATA); - return $r[0]['xchan_hash']; - } - - if(discover_by_webbie($x['address'])) { - $r = q("select xchan_hash from xchan where xchan_addr = '%s' limit 1", - dbesc($x['address']) - ); - if($r) - return $r[0]['xchan_hash']; - } - - return false; - -} - -/** * @brief Imports an author from a RSS feed. * * @param array $x an associative array with @@ -889,6 +858,11 @@ function import_author_rss($x) { function import_author_unknown($x) { + $arr = [ 'author' => $x, 'result' => false ]; + call_hooks('import_author', $arr); + if($arr['result']) + return $arr['result']; + if(! $x['url']) return false; diff --git a/include/network.php b/include/network.php index 6cc53e8b5..d4b9e73ee 100644 --- a/include/network.php +++ b/include/network.php @@ -1900,3 +1900,83 @@ function probe_api_path($host) { return ''; } + + +function scrape_vcard($url) { + + require_once('library/HTML5/Parser.php'); + + $ret = array(); + + logger('url=' . $url); + + $x = z_fetch_url($url); + if(! $x['success']) + return $ret; + + $s = $x['body']; + + if(! $s) + return $ret; + + $headers = $x['header']; + $lines = explode("\n",$headers); + if(count($lines)) { + foreach($lines as $line) { + // don't try and run feeds through the html5 parser + if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml')))) + return ret; + } + } + + try { + $dom = HTML5_Parser::parse($s); + } catch (DOMException $e) { + logger('Parse error: ' . $e); + } + + if(! $dom) + return $ret; + + // Pull out hCard profile elements + + $largest_photo = 0; + + $items = $dom->getElementsByTagName('*'); + foreach($items as $item) { + if(attribute_contains($item->getAttribute('class'), 'vcard')) { + $level2 = $item->getElementsByTagName('*'); + foreach($level2 as $x) { + if(attribute_contains($x->getAttribute('id'),'pod_location')) + $ret['pod_location'] = $x->textContent; + if(attribute_contains($x->getAttribute('class'),'fn')) + $ret['fn'] = $x->textContent; + if(attribute_contains($x->getAttribute('class'),'uid')) + $ret['uid'] = $x->textContent; + if(attribute_contains($x->getAttribute('class'),'nickname')) + $ret['nick'] = $x->textContent; + if(attribute_contains($x->getAttribute('class'),'searchable')) + $ret['searchable'] = $x->textContent; + if(attribute_contains($x->getAttribute('class'),'key')) + $ret['public_key'] = $x->textContent; + if(attribute_contains($x->getAttribute('class'),'given_name')) + $ret['given_name'] = $x->textContent; + if(attribute_contains($x->getAttribute('class'),'family_name')) + $ret['family_name'] = $x->textContent; + if(attribute_contains($x->getAttribute('class'),'url')) + $ret['url'] = $x->textContent; + + if((attribute_contains($x->getAttribute('class'),'photo')) + || (attribute_contains($x->getAttribute('class'),'avatar'))) { + $size = intval($x->getAttribute('width')); + if(($size > $largest_photo) || (! $largest_photo)) { + $ret['photo'] = $x->getAttribute('src'); + $largest_photo = $size; + } + } + } + } + } + + return $ret; +} |