我正试图从这个网页中提取数据：
https://portal.icuregswe.org/siri/report/corona.vtfstart
我已经确定可以从https://portal.icuregswe.org/siri/api/reports/GenerateHighChart(帖子(。我尝试在PHP中使用cURL的解决方案如下：
$url = 'https://portal.icuregswe.org/siri/api/reports/GenerateHigh';
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_HTTPHEADER, array(
'Host: portal.icuregswe.org',
'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:84.0) Gecko/20100101 Firefox/84.0',
'Accept: application/json, text/plain, */*',
'Accept-Language: sv-SE,sv;q=0.8,en-US;q=0.5,en;q=0.3',
'Accept-Encoding: gzip, deflate, br',
'Content-Type: application/x-www-form-urlencoded',
'Content-Length: 179',
'Origin: https://portal.icuregswe.org',
'Connection: keep-alive',
'Referer: https://portal.icuregswe.org/siri/report/corona.vtfstart',
'Cookie: _ga=GA1.2.1861236498.1591648329; _gid=GA1.2.1182050970.1608386303',
'Pragma: no-cache',
'Cache-Control: no-cache'));
$output = curl_exec ($ch);
print $output;
curl_close ($ch);
我希望检索原始数据，但我得到的却是HTTP错误400。标头是通过访问Firefox中给定的url生成的。如有任何帮助，我们将不胜感激。
没有必要依赖用户代理，他们不会运行用户代理黑名单；但它确实需要一堆POST参数，事实上，你不需要这些头中的任何一个(好吧，除了Content-Type头，但curl会在将CURLOPT_POSTFIELDS设置为字符串时自动为你添加它，所以你不需要自己添加它，因为你可能会有输入错误的风险，而curl不会，所以如果你不添加它会更好(，这个
<?php
declare(strict_types=1);
$ch = curl_init();
curl_setopt_array($ch, array(
CURLOPT_URL => 'https://portal.icuregswe.org/siri/api/reports/GenerateHighChart',
CURLOPT_POST => 1,
CURLOPT_POSTFIELDS => http_build_query(array(
'highChartUrl' => '/api/reports/GenerateHighChart',
'tableUrl' => '/api/reports/GenerateExcel',
'chartWidth' => '900',
'reportName' => 'corona.vtfstart',
'startdat' => '2020-01-01',
'stopdat' => '2020-12-19',
'sasong' =>
array(
0 => '2020',
),
))
));
curl_exec($ch);
输出：
{"ReportName":"Antal nyinskrivna vårdtillfällen med Coronavirus \n Period ###","ChartTitle":"Antal nyinskrivna vårdtillfällen med Coronavirus ","ChartSubTitle":" Period 2020-01-01 - 2020-12-19","ChartColors":["#53a8c3","#ee5773","#f0d86e","#f6854f","#15ceac","#5773ee","#f597a9","#df7f23","#10a085","#986ef0"],"YaxisTitle":"Antal vtf","YaxisTitleColor":"","HasY2Axis":false,"Y2axisTitle":null,"Y2axisTitleColor":null,"XaxisTitle":"Datum","XaxisColors":["","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","",""],"Credits":"Detta är en originalrapport från Svenska Intensivvårdsregistret","SqlString":"<b>-- SQL-sats 1</b><br />SELECT<br /> DATEADD(DAY, 0, DATEDIFF(DAY, 0, Xa.VtfStart)) AS vtfstartdag@0,<br /> SUM(CASE WHEN Xa.InfEnkatSiriLabfyndId=3 THEN 1 ELSE 0 END) AS antalcorona@1,<br /> COUNT(DISTINCT Xa.PersonId) AS antalpersoner@2<br />FROM<br /> vueSiri AS Xa<br />WHERE<br /> (Xa.InfEnkatSiriLabfyndId=3) AND ((Xa.VtfStart>='2020-01-01 00:00:00') AND (Xa.VtfStart<='2020-12-19 23:59:00'))<br />GROUP BY<br /> DATEADD(DAY, 0, DATEDIFF(DAY, 0, Xa.VtfStart))<br />ORDER BY<br /> vtfstartdag@0<br /><br />","ChartSeries":[{"Name":"Antal vtf","Stack":null,"Type":"column","Color":"","Data":[{"Value":1.0,"Name":"2020-03-06 00:00:00","Color":null},{"Value":1.0,"Name":"2020-03-07 00:00:00","Color":null},{"Value":1.0,"Name":"2020-03-08 00:00:00","Color":null},{"Value":1.0,"Name":"2020-03-09 00:00:00","Color":null},{"Value":3.0,"Name":"2020-03-10 00:00:00","Color":null},{"Value":1.0,"Name":"2020-03-11 00:00:00","Color":null},{"Value":3.0,"Name":"2020-03-13 00:00:00","Color":null},{"Value":7.0,"Name":"2020-03-14 00:00:00","Color":null},{"Value":6.0,"Name":"2020-03-15 00:00:00","Color":null},{"Value":6.0,"Name":"2020-03-16 00:00:00","Color":null},{"Value":3.0,"Name":"2020-03-17 00:00:00","Color":null},{"Value":15.0,"Name":"2020-03-18 00:00:00","Color":null},{"Value":13.0,"Name":"2020-03-19 00:00:00","Color":null},{"Value":20.0,"Name":"2020-03-20 00:00:00","Color":null},{"Value":19.0,"Name":"2020-03-21 00:00:00","Color":null},{"Value":33.0,"Name":"2020-03-22 00:00:00","Color":null},{"Value":45.0,"Name":"2020-03-23 00:00:00","Color":null},{"Value":44.0,"Name":"2020-03-24 00:00:00","Color":null},{"Value":43.0,"Name":"2020-03-25 00:00:00","Color":null},{"Value":45.0,"Name":"2020-03-26 00:00:00","Color":null},{"Value":40.0,"Name":"2020-03-27 00:00:00","Color":null},{"Value":34.0,"Name":"2020-03-28 00:00:00","Color":null},{"Value":51.0,"Name":"2020-03-29 00:00:00","Color":null},{"Value":40.0,"Name":"2020-03-30 00:00:00","Color":null},{"Value":44.0,"Name":"2020-03-31 00:00:00","Color":null},{"Value":60.0,"Name":"2020-04-01 00:00:00","Color":null},{"Value":55.0,"Name":"2020-04-02 00:00:00","Color":null},{"Value":54.0,"Name":"2020-04-03 00:00:00","Color":null},{"Value":49.0,"Name":"2020-04-04 00:00:00","Color":null},{"Value":56.0,"Name":"2020-04-05 00:00:00","Color":null},{"Value":59.0,"Name":"2020-04-06 00:00:00","Color":null},{"Value":58.0,"Name":"2020-04-07 00:00:00","Color":null},{"Value":62.0,"Name":"2020-04-08 00:00:00","Color":null},{"Value":52.0,"Name":"2020-04-09 00:00:00","Color":null},{"Value":45.0,"Name":"2020-04-10 00:00:00","Color":null},{"Value":61.0,"Name":"2020-04-11 00:00:00","Color":null},{"Value":45.0,"Name":"2020-04-12 00:00:00","Color":null},{"Value":59.0,"Name":"2020-04-13 00:00:00","Color":null},{"Value":56.0,"Name":"2020-04-14 00:00:00","Color":null},{"Value":45.0,"Name":"2020-04-15 00:00:00","Color":null},{"Value":51.0,"Name":"2020-04-16 00:00:00","Color":null},{"Value":54.0,"Name":"2020-04-17 00:00:00","Color":null},{"Value":43.0,"Name":"2020-04-18 00:00:00","Color":null},{"Value":42.0,"Name":"2020-04-19 00:00:00","Color":null},{"Value":37.0,"Name":"2020-04-20 00:00:00","Color":null},{"Value":52.0,"Name":"2020-04-21 00:00:00","Color":null},{"Value":64.0,"Name":"2020-04-22 00:00:00","Color":null},{"Value":44.0,"Name":"2020-04-23 00:00:00","Color":null},{"Value":66.0,"Name":"2020-04-24 00:00:00","Color":null},{"Value":37.0,"Name":"2020-04-25 00:00:00","Color":null},{"Value":33.0,"Name":"2020-04-26 00:00:00","Color":null},{"Value":38.0,"Name":"2020-04-27 00:00:00","Color":null},{"Value":40.0,"Name":"2020-04-28 00:00:00","Color":null},{"Value":35.0,"Name":"2020-04-29 00:00:00","Color":null},{"Value":53.0,"Name":"2020-04-30 00:00:00","Color":null},{"Value":30.0,"Name":"2020-05-01 00:00:00","Color":null},{"Value":43.0,"Name":"2020-05-02 00:00:00","Color":null},{"Value":36.0,"Name":"2020-05-03 00:00:00","Color":null},{"Value":33.0,"Name":"2020-05-04 00:00:00","Color":null},}
(…有上限，但你明白了(
您只需复制并粘贴即可查看结果。我还保存了饼干，以备以后需要。
$end_date= date('Y-m-d');//You dont have to use like this, you can write directly the date in the array below.
$start_date = date("Y-m-d", strtotime("-91 day"));
$data = array(
'highChartUrl'=> '/api/reports/GenerateHighChart',
'tableUrl'=> '/api/reports/GenerateExcel',
'chartWidth'=> '900',
'reportName'=> 'corona.vtfstart',
'startdat'=> $start_date,
'stopdat'=> $end_date,
'sasong[0]'=> '2020'
);
$url = 'https://portal.icuregswe.org/siri/api/reports/GenerateHighChart';
$ch = CURL_INIT();
CURL_SETOPT($ch, CURLOPT_URL, $url);
CURL_SETOPT($ch, CURLOPT_POST, true); //Post request
CURL_SETOPT($ch, CURLOPT_PROXYTYPE,CURLPROXY_SOCKS5);
CURL_SETOPT($ch, CURLOPT_POSTFIELDS, $data);
CURL_SETOPT($ch, CURLOPT_RETURNTRANSFER,True);
CURL_SETOPT($ch, CURLOPT_FOLLOWLOCATION,True);
CURL_SETOPT($ch, CURLOPT_COOKIEJAR, dirname(__FILE__) ."/cookie.txt");
CURL_SETOPT($ch, CURLOPT_COOKIEFILE, dirname(__FILE__) ."/cookie.txt");
CURL_SETOPT($ch, CURLOPT_FOLLOWLOCATION, true); //ALLOW REDIRECTION
CURL_SETOPT($ch, CURLOPT_CONNECTTIMEOUT,90);
CURL_SETOPT($ch, CURLOPT_TIMEOUT,90);
$result = CURL_EXEC($ch);
echo $result;