Capture the title, content, and source image code of an article using the CI framework

This is a code for capturing pages and backing up the pages for future calls. you can view the code and share it with friends. If you have any comments, log on and leave a message. this is a code that captures the page and makes a backup so that you can call it later. you can check the code again, so you can share it with friends. Post-logon messages with comments

Public function snatch () {set_time_limit (0); $ this-> benchmark-> mark ('code _ start '); /* get second-hand car news of different categories */for ($ I = 1; $ I <= 4; $ I ++) {$ url = 'http: // news.2sche.cn/list.asp? Stype = '. $ I; $ result = $ this-> curl_snatch ($ url); preg_match_all ('/\ D \/(.*?) <\/Strong>/', $ result, $ page_news); // print_r ($ page_news); // echo ''; /* obtain the news list of all pages in a single category */for ($ j = 1; $ j <= $ page_news [1]; $ j ++) {if (1 = $ j) {$ url_news = 'http: // news.2sche.cn/list.asp? Stype = '. $ I;} else {$ url_news = 'http: // news.2sche.cn/list.asp? Page = '. $ j.' & stype = '. $ I;} $ result_news = $ this-> curl_snatch ($ url_news); preg_match_all ('/.*? <\/A> <\/td>/sim ', $ result_news, $ url_newslist); // print_r ($ url_newslist ); /* traverse each url on the list page */foreach ($ url_newslist [1] as $ url_newslists) {$ url_newsinfo = 'http: // news.2sche.cn/'.w.url_newslists; $ result_newsinfo = $ this-> curl_snatch ($ url_newsinfo);/* obtain the title */preg_match_all ('/(.*?) <\/Strong> <\/h3>/sim ', $ result_newsinfo, $ title); // print_r ($ title [1]); /* obtain the source */preg_match_all ('/[Source :(.*?) ] <\/Span> <\/td>/sim ', $ result_newsinfo, $ source); // print_r ($ source [1]); /* get content */preg_match_all ('/(.*?) <\/Td>/sim ', $ result_newsinfo, $ content); // print_r ($ content [1] [0]); /* get all image URLs * // preg_match_all ('// sim', $ content [1] [0], $ img ); preg_match_all ('// sim', $ content [1] [0], $ img); // echo 'ddddd '; // print_r ($ img [1]); // echo 'dddd
'; // Exit; $ picture = ''; foreach ($ img [1] as $ imgs) {// echo $ imgs; // echo'
'; If (strpos ($ imgs, 'http: //') ===false) {continue;} $ img_source = file_get_contents ($ imgs ); /* obtain the name of a single image */$ img_names = trim (strrchr ($ imgs, '/'), '/'); // print_r ($ img_name ); // echo $ img_names; // exit; $ picture. = $ img_names. ':'; file_put_contents (". /static/uploads/news /". $ img_names, $ img_source); // replace the image path with $ img_path = '/static/uploads/news /'. $ img_names; $ content [1] [0] = str_replace ($ imgs, $ img_path, $ content [1] [0]);} // print_r ($ picture ); // echo 'hhhh
'; // Print_r ($ content [1] [0]); // echo'
'; $ Data = array ('title' => $ title [1] [0], 'source' => $ source [1] [0], 'contents' => trim ($ content [1] [0]), 'Picture '=> $ picture, 'Style' => $ I, 'create _ time' => time (),); if (! $ This-> News_model-> add ($ data) {continue;} // print_r ($ data); exit;} echo '';}} $ this-> benchmark-> mark ('code _ end'); echo $ this-> benchmark-> elapsed_time ('code _ start', 'Code _ end ');} function curl_snatch ($ url =' http://www.2sche.cn/buy.asp ') {$ Url = trim ($ url); $ content = ''; if (extension_loaded ('curl') {$ ch = curl_init (); // 2. set options, including URL curl_setopt ($ ch, CURLOPT_URL, $ url); curl_setopt ($ ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt ($ ch, CURLOPT_FOLLOWLOCATION, 1 ); curl_setopt ($ ch, CURLOPT_HEADER, 0); // 3. execute and get the HTML document content $ output = curl_exec ($ ch); $ content = iconv ("GBK", "UTF-8", $ output ); if ($ output = FALSE) {echo "cURL Error :". curl_error ($ ch);} // $ info = curl_getinfo ($ ch); // echo 'get '. $ info ['URL']. 'consumed time '. $ info ['total _ time']. 'second'; // 4. release curl handle curl_close ($ ch);} else {$ content = file_get_contents ($ url);} return trim ($ content );}

Author: Li Jiashun