A PHP wrapper for Camelot, the python PDF table extraction library
composer require randomstate/camelot-php
The package adheres closely with the camelot CLI API Usage.
Default output is in CSV format as a simple string. If you need to parse CSV strings we recommend the league/csv package (https://csv.thephpleague.com/)
<?php
use RandomState\Camelot\Camelot;
use League\Csv\Reader;
$tables = Camelot::lattice('/path/to/my/file.pdf')
->extract();
$csv = Reader::createFromString($tables[0]);
$allRecords = $csv->getRecords();Note: No Camelot operations are run until one of these methods is run
$camelot->extract(); // uses temporary files and automatically grabs the table contents for you from each
$camelot->save('/path/to/my-file.csv'); // mirrors the behaviour of Camelot and saves files in the format /path/to/my-file-page-*-table-*.csv
$camelot->plot(); // useful for debugging, it will plot it in a separate window (see Visual Debugging below) $camelot->json();
$camelot->csv();
$camelot->html();
$camelot->excel();
$camelot->sqlite();
$camelot->pages('1,2,3-4,8-end')
$camelot->password('my-pass')
$camelot->stream()->processBackgroundLines()
$camelot->plot()
<?php
use RandomState\Camelot\Camelot;
use RandomState\Camelot\Areas;
Camelot::stream('my-file.pdf')
->inAreas(
Areas::from($xTopLeft, $yTopLeft, $xBottomRight, $yBottomRight)
// ->add($xTopLeft2, $yTopLeft2, $xBottomRight2, $yBottomRight2)
// ->add($xTopLeft3, $yTopLeft3, $xBottomRight3, $yBottomRight3)
);<?php
use RandomState\Camelot\Camelot;
use RandomState\Camelot\Areas;
Camelot::stream('my-file.pdf')
->inRegions(
Areas::from($xTopLeft, $yTopLeft, $xBottomRight, $yBottomRight)
// ->add($xTopLeft2, $yTopLeft2, $xBottomRight2, $yBottomRight2)
// ->add($xTopLeft3, $yTopLeft3, $xBottomRight3, $yBottomRight3)
);$camelot->stream()->setColumnSeparators($x1,$x2...)
$camelot->split()
$camelot->flagSize()
$camelot->strip("\n")
$camelot->setEdgeTolerance(500)
$camelot->setRowTolerance(15)
$camelot->lineScale(20)
$camelot->shiftText('r', 'b')
$camelot->copyTextSpanningCells('r', 'b')
MIT. Use at your own risk, we accept no liability for how this code is used.