![PHP (2007)$url = "http://www.nfl.com/teams/sandiegochargers/roster?team=SD";$raw = file_get_contents($url);$newlines = array("\t","\n","\r","\x20\x20","\0","\x0B");$content = str_replace($newlines, "", html_entity_decode($raw));$start = strpos($content,'<table cellpadding="2" class="standard_table"');$end = strpos($content,'</table>',$start) + 8;$table = substr($content,$start,$end-$start);preg_match_all("|<tr(.*)</tr>|U",$table,$rows);foreach ($rows[0] as $row){ if ((strpos($row,'<th')===false)){ preg_match_all("|<td(.*)</td>|U",$row,$cells); $number = strip_tags($cells[0][0]); $name = strip_tags($cells[0][1]); $position = strip_tags($cells[0][2]); echo "{$position} - {$name} - Number {$number} <br>\n"; }}$url = "http://www.nfl.com/teams/sandiegochargers/roster?team=SD";$raw = file_get_contents($url);$newlines = array("\t","\n","\r","\x20\x20","\0","\x0B");$content = str_replace($newlines, "", html_entity_decode($raw));$start = strpos($content,'<table cellpadding="2" class="standard_table"');$end = strpos($content,'</table>',$start) + 8;$table = substr($content,$start,$end-$start);preg_match_all("|<tr(.*)</tr>|U",$table,$rows);foreach ($rows[0] as $row){ if ((strpos($row,'<th')===false)){ preg_match_all("|<td(.*)</td>|U",$row,$cells); $number = strip_tags($cells[0][0]); $name = strip_tags($cells[0][1]); $position = strip_tags($cells[0][2]); echo "{$position} - {$name} - Number {$number} <br>\n"; }}source: http://www.bradino.com/php/screen-scraping/](https://image.slidesharecdn.com/xquerymeetupwebscrapingslideshare-110926133325-phpapp02/85/London-XQuery-Meetup-Querying-the-World-Web-Scraping-3-320.jpg)
![PHP (June 2011)$url="http://www.rtu.ac.in/results/reformat.php";$post="rollnumber=08epccs060&filename=fetchmodulesem_4_btech410m.php&button=Submit";$ch=curl_init();curl_setopt($ch,CURLOPT_URL,$url);curl_setopt($ch,CURLOPT_POST,1);curl_setopt($ch,CURLOPT_POSTFIELDS,$post);curl_setopt($ch,CURLOPT_FOLLOWLOCATION,1);curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);$content=curl_exec($ch);curl_close($ch);$totalPath="html/body/table[4]/tbody/tr[3]/td[4]";$page=new DOMDocument();$xpath=new DOMXPath($page);$page->loadHTML($content);$page->saveHTML(); // this shows the page contents$total=$xpath->query($totalPath);echo $total->length; //shows 0echo $total->item(0)->nodeValue; //shows nothing$url="http://www.rtu.ac.in/results/reformat.php";$post="rollnumber=08epccs060&filename=fetchmodulesem_4_btech410m.php&button=Submit";$ch=curl_init();curl_setopt($ch,CURLOPT_URL,$url);curl_setopt($ch,CURLOPT_POST,1);curl_setopt($ch,CURLOPT_POSTFIELDS,$post);curl_setopt($ch,CURLOPT_FOLLOWLOCATION,1);curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);$content=curl_exec($ch);curl_close($ch);$totalPath="html/body/table[4]/tbody/tr[3]/td[4]";$page=new DOMDocument();$xpath=new DOMXPath($page);$page->loadHTML($content);$page->saveHTML(); // this shows the page contents$total=$xpath->query($totalPath);echo $total->length; //shows 0echo $total->item(0)->nodeValue; //shows nothing!!source: http://stackoverflow.com/questions/6283361/unable-to-get-table-data-from-a-html-page](https://image.slidesharecdn.com/xquerymeetupwebscrapingslideshare-110926133325-phpapp02/85/London-XQuery-Meetup-Querying-the-World-Web-Scraping-4-320.jpg)
London XQuery Meetup: Querying the World (Web Scraping)
- 1. XQuery: Querying the World(formerly known as Web Scraping)Dennis Knochenwefel <dennis.knochenwefel@28msec.com>
- 3. PHP (2007)$url = "http://www.nfl.com/teams/sandiegochargers/roster?team=SD";$raw = file_get_contents($url);$newlines = array("\t","\n","\r","\x20\x20","\0","\x0B");$content = str_replace($newlines, "", html_entity_decode($raw));$start = strpos($content,'<table cellpadding="2" class="standard_table"');$end = strpos($content,'</table>',$start) + 8;$table = substr($content,$start,$end-$start);preg_match_all("|<tr(.*)</tr>|U",$table,$rows);foreach ($rows[0] as $row){ if ((strpos($row,'<th')===false)){ preg_match_all("|<td(.*)</td>|U",$row,$cells); $number = strip_tags($cells[0][0]); $name = strip_tags($cells[0][1]); $position = strip_tags($cells[0][2]); echo "{$position} - {$name} - Number {$number} <br>\n"; }}$url = "http://www.nfl.com/teams/sandiegochargers/roster?team=SD";$raw = file_get_contents($url);$newlines = array("\t","\n","\r","\x20\x20","\0","\x0B");$content = str_replace($newlines, "", html_entity_decode($raw));$start = strpos($content,'<table cellpadding="2" class="standard_table"');$end = strpos($content,'</table>',$start) + 8;$table = substr($content,$start,$end-$start);preg_match_all("|<tr(.*)</tr>|U",$table,$rows);foreach ($rows[0] as $row){ if ((strpos($row,'<th')===false)){ preg_match_all("|<td(.*)</td>|U",$row,$cells); $number = strip_tags($cells[0][0]); $name = strip_tags($cells[0][1]); $position = strip_tags($cells[0][2]); echo "{$position} - {$name} - Number {$number} <br>\n"; }}source: http://www.bradino.com/php/screen-scraping/
- 4. PHP (June 2011)$url="http://www.rtu.ac.in/results/reformat.php";$post="rollnumber=08epccs060&filename=fetchmodulesem_4_btech410m.php&button=Submit";$ch=curl_init();curl_setopt($ch,CURLOPT_URL,$url);curl_setopt($ch,CURLOPT_POST,1);curl_setopt($ch,CURLOPT_POSTFIELDS,$post);curl_setopt($ch,CURLOPT_FOLLOWLOCATION,1);curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);$content=curl_exec($ch);curl_close($ch);$totalPath="html/body/table[4]/tbody/tr[3]/td[4]";$page=new DOMDocument();$xpath=new DOMXPath($page);$page->loadHTML($content);$page->saveHTML(); // this shows the page contents$total=$xpath->query($totalPath);echo $total->length; //shows 0echo $total->item(0)->nodeValue; //shows nothing$url="http://www.rtu.ac.in/results/reformat.php";$post="rollnumber=08epccs060&filename=fetchmodulesem_4_btech410m.php&button=Submit";$ch=curl_init();curl_setopt($ch,CURLOPT_URL,$url);curl_setopt($ch,CURLOPT_POST,1);curl_setopt($ch,CURLOPT_POSTFIELDS,$post);curl_setopt($ch,CURLOPT_FOLLOWLOCATION,1);curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);$content=curl_exec($ch);curl_close($ch);$totalPath="html/body/table[4]/tbody/tr[3]/td[4]";$page=new DOMDocument();$xpath=new DOMXPath($page);$page->loadHTML($content);$page->saveHTML(); // this shows the page contents$total=$xpath->query($totalPath);echo $total->length; //shows 0echo $total->item(0)->nodeValue; //shows nothing!!source: http://stackoverflow.com/questions/6283361/unable-to-get-table-data-from-a-html-page
- 5. XQuery
- 7. awesome siteawesome datano API
- 9. Need to emulate setting options
- 10. Different NotionsPublisher <=> Consumer
- 11. JSON ?XML ?CSV !HTML !XLS !Zip !AppWebsite
- 12. Stateless REST API ?JSON ?XML ?CSV !HTML !XLS !Zip !Session!AppWebsite
- 13. Stateless REST API ?JSON ?XML ?CSV !HTML !XLS !Zip !Session!AppWebsiteCustomize with URL ParamsHTML Forms
- 14. Stateless REST API ?JSON ?XML ?CSV !HTML !XLS !Zip !Session!AppWebsiteCustomize with URL ParamsHTML Forms
- 15. CSV !HTML !XLS !Zip !HTML !Session!Session!AppWebsiteXQuery !HTML FormsHTML Forms
- 16. Summary
- 17. Session handlingForms!!XQuery Web Data ProcessingA browser can do it? XQuery can do it!
Editor's Notes
- #4: http://stackoverflow.com/questions/6283361/unable-to-get-table-data-from-a-html-page
- #5: http://stackoverflow.com/questions/6283361/unable-to-get-table-data-from-a-html-page
- #6: http://stackoverflow.com/questions/6283361/unable-to-get-table-data-from-a-html-page