Untitled
unknown
plain_text
a year ago
2.4 kB
5
Indexable
{ "jid" : "2", "title" : "comments from trustpilot", "start_url" : "https:\/\/www.trustpilot.com\/review\/aardy.com", "test_url" : "https:\/\/www.trustpilot.com\/review\/aardy.com", "only_this_domen" : "0", "depth" : "0", "parse_limit" : "0", "white_list" : "", "black_list" : "*.gif\r\n*.zip\r\n*.rar\r\n*.pdf\r\n*.doc\r\n*.xls\r\n*.txt", "save_url" : "0", "no_update" : "0", "site_charset" : "auto", "charset_fix" : "0", "entity_type" : "node", "bundle" : "page", "headers" : "", "force_download" : "0", "force_download_list" : "", "sleep" : "1", "run_period" : "0", "last_run" : "0", "code" : {"check":"return ($doc-\u003Efind(\u0027body\u0027)-\u003Elength() \u003E 0);","remote_id":"","fields":{"title":"return array(\r\n \u0027value\u0027 =\u003E $doc_element-\u003Efind(\u0027[name=\u0022consumer-profile\u0022] span[class^=\u0022typography_heading-xxs\u0022]\u0027)-\u003Etext(),\r\n);","author":"return 1;","body":"$element = $doc_element-\u003Efind(\u0027[data-service-review-text-typography]\u0027);\r\n\r\n\/\/ \u041f\u043e\u043b\u0443\u0447\u0430\u0435\u043c \u0432\u043d\u0435\u0448\u043d\u0438\u0439 HTML-\u043a\u043e\u0434 \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u0430\r\n$htmlOuter = $element-\u003EhtmlOuter();\r\n\r\n\/\/ \u0410\u043d\u043e\u043d\u0438\u043c\u043d\u0430\u044f \u0444\u0443\u043d\u043a\u0446\u0438\u044f \u0434\u043b\u044f \u0443\u0434\u0430\u043b\u0435\u043d\u0438\u044f \u0430\u0442\u0440\u0438\u0431\u0443\u0442\u043e\u0432 \u0438\u0437 HTML-\u0442\u0435\u0433\u043e\u0432\r\n$removeAttributes = function($html) {\r\n return preg_replace(\u0027\/\u003C([a-z][a-z0-9]*)[^\u003E]*?(\\\/?)\u003E\/i\u0027, \u0027\u003C$1$2\u003E\u0027, $html);\r\n};\r\n\r\n\/\/ \u041f\u0440\u0438\u043c\u0435\u043d\u044f\u0435\u043c \u0444\u0443\u043d\u043a\u0446\u0438\u044e \u043a \u043f\u043e\u043b\u0443\u0447\u0435\u043d\u043d\u043e\u043c\u0443 HTML\r\n$cleanHtml = $removeAttributes($htmlOuter);\r\n\r\nreturn array(\r\n \u0027value\u0027 =\u003E $cleanHtml,\r\n \u0027format\u0027 =\u003E \u0027filtered_html\u0027,\r\n);"},"list":"$elements = array();\r\nforeach ($doc-\u003Efind(\u0027[class^=\u0022styles_reviewContentwrapper__\u0022]\u0027) as $element) {\r\n $elements[] = pq($element)-\u003EhtmlOuter();\r\n}\r\nreturn $elements;","init":"","prepare":""}, "options" : {"resume_errors":0,"clear_watchdog":0,"reparse_entities":0}, "rdf_mapping" : [] }
Editor is loading...
Leave a Comment