{"id":105371,"date":"2025-04-10T06:24:31","date_gmt":"2025-04-10T01:54:31","guid":{"rendered":"https:\/\/nabfollower.com\/blog\/scrape-data-masjid-dengan-multi-threads-8g1\/"},"modified":"2025-04-10T06:24:31","modified_gmt":"2025-04-10T01:54:31","slug":"scrape-data-masjid-dengan-multi-threads-8g1","status":"publish","type":"post","link":"https:\/\/nabfollower.com\/blog\/scrape-data-masjid-dengan-multi-threads-8g1\/","title":{"rendered":"\u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0645\u0633\u062c\u062f \u0631\u0627 \u0628\u0627 \u0686\u0646\u062f \u0645\u0648\u0636\u0648\u0639 \u062e\u0631\u062f \u06a9\u0646\u06cc\u062f"},"content":{"rendered":"
\n

<\/p>\n

\u062f\u0631 \u062a\u0644\u0627\u0634 \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0645\u0633\u062c\u062f \u062f\u0631 Simas Kemenag \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 PHP \u0648 \u0686\u0646\u062f \u0631\u0634\u062a\u0647 \u0628\u0627 \u0686\u0646\u062f \u062d\u0644\u0642\u0647<\/p>\n

Scrape \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0645\u0633\u062c\u062f \u0648 \u0645\u062d\u0644 \u0645\u0633\u062c\u062f \u06cc\u0627 \u0645\u062e\u062a\u0635\u0627\u062a \u0622\u0646 \u0631\u0627 \u062f\u0631 GMAPS \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc \u062f\u0647\u062f.<\/p>\n

\u0641\u06cc\u0644\u0645\u0646\u0627\u0645\u0647:<\/p>\n

\n
\n$startPage<\/span>   =<\/span> 1<\/span>;<\/span>\n$endPage<\/span>     =<\/span> 100<\/span>;<\/span>\n$maxThreads<\/span>  =<\/span> 10<\/span>;<\/span>\n$namaFile<\/span>    =<\/span> \"hasil_masjid_page<\/span>{<\/span>$startPage<\/span>}<\/span>-<\/span>{<\/span>$endPage<\/span>}<\/span>.txt\"<\/span>;<\/span>\n\n\/\/ Buka file dan tulis header<\/span>\n$fp<\/span> =<\/span> fopen<\/span>(<\/span>$namaFile<\/span>,<\/span> 'w'<\/span>);<\/span>\nfwrite<\/span>(<\/span>$fp<\/span>,<\/span> \"<\/span>\\\"<\/span>s_id<\/span>\\\"<\/span>,<\/span>\\\"<\/span>link_detil<\/span>\\\"<\/span>,<\/span>\\\"<\/span>link_peta<\/span>\\\"\\n<\/span>\"<\/span>);<\/span>\n\n\/\/ Ambil banyak halaman secara paralel<\/span>\nfunction<\/span> fetchPagesMultiCurl<\/span>(<\/span>$urls<\/span>)<\/span> {<\/span>\n    $multiHandle<\/span> =<\/span> curl_multi_init<\/span>();<\/span>\n    $curlHandles<\/span> =<\/span> [];<\/span>\n    $results<\/span> =<\/span> [];<\/span>\n\n    foreach<\/span> (<\/span>$urls<\/span> as<\/span> $key<\/span> =><\/span> $url<\/span>)<\/span> {<\/span>\n        $ch<\/span> =<\/span> curl_init<\/span>();<\/span>\n        curl_setopt_array<\/span>(<\/span>$ch<\/span>,<\/span> [<\/span>\n            CURLOPT_URL<\/span> =><\/span> $url<\/span>,<\/span>\n            CURLOPT_RETURNTRANSFER<\/span> =><\/span> true<\/span>,<\/span>\n            CURLOPT_FOLLOWLOCATION<\/span> =><\/span> true<\/span>,<\/span>\n            CURLOPT_USERAGENT<\/span> =><\/span> 'Mozilla\/5.0'<\/span>,<\/span>\n            CURLOPT_TIMEOUT<\/span> =><\/span> 10<\/span>,<\/span>\n        ]);<\/span>\n        curl_multi_add_handle<\/span>(<\/span>$multiHandle<\/span>,<\/span> $ch<\/span>);<\/span>\n        $curlHandles<\/span>[<\/span>$key<\/span>]<\/span> =<\/span> $ch<\/span>;<\/span>\n    }<\/span>\n\n    $running<\/span> =<\/span> null<\/span>;<\/span>\n    do<\/span> {<\/span>\n        curl_multi_exec<\/span>(<\/span>$multiHandle<\/span>,<\/span> $running<\/span>);<\/span>\n        curl_multi_select<\/span>(<\/span>$multiHandle<\/span>,<\/span> 1.0<\/span>);<\/span> \/\/ Optimasi I\/O blocking<\/span>\n    }<\/span> while<\/span> (<\/span>$running<\/span> ><\/span> 0<\/span>);<\/span>\n\n    foreach<\/span> (<\/span>$curlHandles<\/span> as<\/span> $key<\/span> =><\/span> $ch<\/span>)<\/span> {<\/span>\n        $results<\/span>[<\/span>$key<\/span>]<\/span> =<\/span> curl_multi_getcontent<\/span>(<\/span>$ch<\/span>);<\/span>\n        curl_multi_remove_handle<\/span>(<\/span>$multiHandle<\/span>,<\/span> $ch<\/span>);<\/span>\n        curl_close<\/span>(<\/span>$ch<\/span>);<\/span>\n    }<\/span>\n\n    curl_multi_close<\/span>(<\/span>$multiHandle<\/span>);<\/span>\n    return<\/span> $results<\/span>;<\/span>\n}<\/span>\n\n\/\/ Batch processing<\/span>\nfor<\/span> (<\/span>$batchStart<\/span> =<\/span> $startPage<\/span>;<\/span> $batchStart<\/span> <=<\/span> $endPage<\/span>;<\/span> $batchStart<\/span> +=<\/span> $maxThreads<\/span>)<\/span> {<\/span>\n    $batchEnd<\/span> =<\/span> min<\/span>(<\/span>$batchStart<\/span> +<\/span> $maxThreads<\/span> -<\/span> 1<\/span>,<\/span> $endPage<\/span>);<\/span>\n    $urls<\/span> =<\/span> [];<\/span>\n\n    for<\/span> (<\/span>$i<\/span> =<\/span> $batchStart<\/span>;<\/span> $i<\/span> <=<\/span> $batchEnd<\/span>;<\/span> $i<\/span>++<\/span>)<\/span> {<\/span>\n        $urls<\/span>[<\/span>$i<\/span>]<\/span> =<\/span> \"https:\/\/simas.kemenag.go.id\/page\/profilmasjid\/0\/0\/0\/0\/0?page=<\/span>$i<\/span>\"<\/span>;<\/span>\n    }<\/span>\n\n    printf<\/span>(<\/span>\"\ud83d\udd04 Memproses halaman %d - %d<\/span>\\n<\/span>\"<\/span>,<\/span> $batchStart<\/span>,<\/span> $batchEnd<\/span>);<\/span>\n    $responses<\/span> =<\/span> fetchPagesMultiCurl<\/span>(<\/span>$urls<\/span>);<\/span>\n\n    foreach<\/span> (<\/span>$responses<\/span> as<\/span> $page<\/span> =><\/span> $html<\/span>)<\/span> {<\/span>\n        if<\/span> (<\/span>!<\/span>$html<\/span>)<\/span> {<\/span>\n            echo<\/span> \"\u26a0\ufe0f Gagal mengambil halaman <\/span>$page<\/span>\\n<\/span>\"<\/span>;<\/span>\n            continue<\/span>;<\/span>\n        }<\/span>\n\n        libxml_use_internal_errors<\/span>(<\/span>true<\/span>);<\/span> \/\/ suppress warning<\/span>\n        $dom<\/span> =<\/span> new<\/span> DOMDocument<\/span>();<\/span>\n        $dom<\/span>-><\/span>loadHTML<\/span>(<\/span>$html<\/span>,<\/span> LIBXML_NOERROR<\/span> |<\/span> LIBXML_NOWARNING<\/span>);<\/span>\n        libxml_clear_errors<\/span>();<\/span>\n\n        $xpath<\/span> =<\/span> new<\/span> DOMXPath<\/span>(<\/span>$dom<\/span>);<\/span>\n        $linksDetil<\/span> =<\/span> $xpath<\/span>-><\/span>query<\/span>(<\/span>\"\/\/a[contains(text(), 'Lihat Detil')]\"<\/span>);<\/span>\n        $linksPeta<\/span>  =<\/span> $xpath<\/span>-><\/span>query<\/span>(<\/span>\"\/\/a[contains(text(), 'Lihat di Peta')]\"<\/span>);<\/span>\n\n        $limit<\/span> =<\/span> min<\/span>(<\/span>$linksDetil<\/span>-><\/span>length<\/span>,<\/span> $linksPeta<\/span>-><\/span>length<\/span>);<\/span>\n\n        for<\/span> (<\/span>$i<\/span> =<\/span> 0<\/span>;<\/span> $i<\/span> <<\/span> $limit<\/span>;<\/span> $i<\/span>++<\/span>)<\/span> {<\/span>\n            $detilHref<\/span> =<\/span> $linksDetil<\/span>-><\/span>item<\/span>(<\/span>$i<\/span>)<\/span>-><\/span>getAttribute<\/span>(<\/span>'href'<\/span>);<\/span>\n            $petaHref<\/span>  =<\/span> $linksPeta<\/span>-><\/span>item<\/span>(<\/span>$i<\/span>)<\/span>-><\/span>getAttribute<\/span>(<\/span>'href'<\/span>);<\/span>\n\n            $row<\/span> =<\/span> [<\/span>\n                \"<\/span>{<\/span>$page<\/span>}<\/span>-\"<\/span> .<\/span> (<\/span>$i<\/span> +<\/span> 1<\/span>),<\/span>\n                \"https:\/\/simas.kemenag.go.id\"<\/span> .<\/span> $detilHref<\/span>,<\/span>\n                $petaHref<\/span>\n            ];<\/span>\n\n            fwrite<\/span>(<\/span>$fp<\/span>,<\/span> '\"'<\/span> .<\/span> implode<\/span>(<\/span>'\",\"'<\/span>,<\/span> $row<\/span>)<\/span> .<\/span> '\"'<\/span> .<\/span> \"<\/span>\\n<\/span>\"<\/span>);<\/span>\n        }<\/span>\n\n        \/\/ Bebaskan memori DOM<\/span>\n        unset<\/span>(<\/span>$dom<\/span>,<\/span> $xpath<\/span>,<\/span> $linksDetil<\/span>,<\/span> $linksPeta<\/span>);<\/span>\n    }<\/span>\n}<\/span>\n\nfclose<\/span>(<\/span>$fp<\/span>);<\/span>\necho<\/span> \"\ud83c\udf89 Selesai! File berhasil dibuat: <\/span>$namaFile<\/span>\\n<\/span>\"<\/span>;<\/span>\n\n<\/span><\/code><\/pre>\n
\n
\n    \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u0631\u0627 \u0648\u0627\u0631\u062f \u06a9\u0646\u06cc\u062f<\/title>\n    \n<\/svg><\/p>\n
    \u0627\u0632 \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u062e\u0627\u0631\u062c \u0634\u0648\u06cc\u062f<\/title>\n    \n<\/svg><\/p>\n<\/div>\n<\/div>\n<\/div>\n
\u067e\u0633 \u0627\u0632 \u062e\u0631\u0627\u0634 \u062f\u0631 \u0647\u0631 \u062f\u0633\u062a\u0647 \u06a9\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062a\u0646\u0638\u06cc\u0645 \u0634\u0648\u062f \u060c \u0628\u0627 \u0641\u0631\u0645\u062a CSV \u062f\u0631 \u067e\u0631\u0648\u0646\u062f\u0647 TXT \u0630\u062e\u06cc\u0631\u0647 \u0645\u06cc \u0634\u0648\u062f<\/p>\n
\u0646\u062d\u0648\u0647 \u0627\u062c\u0631\u0627\u06cc \u0622\u0646 \u0628\u0631\u0627\u06cc \u0627\u062c\u0631\u0627\u06cc CMD \u06cc\u0627 \u062a\u0631\u0645\u06cc\u0646\u0627\u0644 \u0627\u0633\u062a<\/p>\n
\n
nohup PHP scrape.php\n<\/code><\/pre>\n
\n
\n    \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u0631\u0627 \u0648\u0627\u0631\u062f \u06a9\u0646\u06cc\u062f<\/title>\n    \n<\/svg><\/p>\n
    \u0627\u0632 \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u062e\u0627\u0631\u062c \u0634\u0648\u06cc\u062f<\/title>\n    \n<\/svg><\/p>\n<\/div>\n<\/div>\n<\/div>\n
\u0627\u0645\u06cc\u062f\u0648\u0627\u0631\u0645 \u0645\u0641\u06cc\u062f \u0628\u0627\u0634\u062f<\/p>\n
\"\u0634\u0631\u062d<\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"
\u062f\u0631 \u062a\u0644\u0627\u0634 \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0645\u0633\u062c\u062f \u062f\u0631 Simas Kemenag \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 PHP \u0648 \u0686\u0646\u062f \u0631\u0634\u062a\u0647 \u0628\u0627 \u0686\u0646\u062f \u062d\u0644\u0642\u0647 Scrape \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0645\u0633\u062c\u062f \u0648 \u0645\u062d\u0644 \u0645\u0633\u062c\u062f \u06cc\u0627 \u0645\u062e\u062a\u0635\u0627\u062a \u0622\u0646 \u0631\u0627 \u062f\u0631 GMAPS \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc \u062f\u0647\u062f. \u0641\u06cc\u0644\u0645\u0646\u0627\u0645\u0647: $startPage = 1; $endPage = 100; $maxThreads = 10; $namaFile = “hasil_masjid_page{$startPage}-{$endPage}.txt”; \/\/ Buka file dan tulis header $fp = …<\/p>\n","protected":false},"author":2,"featured_media":105372,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"","fifu_image_alt":"","footnotes":""},"categories":[339],"tags":[],"class_list":["post-105371","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-dev"],"_links":{"self":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/105371","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/comments?post=105371"}],"version-history":[{"count":0,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/105371\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media\/105372"}],"wp:attachment":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media?parent=105371"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/categories?post=105371"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/tags?post=105371"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}