как преобразовать файл XML в кадр данных в R

Question

У меня есть этот XML-файл, который я хотел бы, чтобы преобразовать его в кадр данных:

data.xml

<?xml version="1.0" encoding="UTF-8" standalone="yes" ?> 
- <graph_data xmlns:ns2="http://www.w3.org/2005/Atom"> 
    <graph_property name="calculation_method" value="Geo Mean" /> 
    <graph_property name="graph_type" value="TIME" /> 
- <measurement id="521406"> 
    <alias>site4</alias> 
- <bucket_data> 
- <bucket id="1" name="2013-MAY-14 07:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="21" /> 
    <perf_data unit="seconds" value="3.102" /> 
    </bucket> 
- <bucket id="2" name="2013-MAY-14 08:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="13" /> 
    <perf_data unit="seconds" value="3.052" /> 
    </bucket> 
- <bucket id="3" name="2013-MAY-14 09:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="3.387" /> 
    </bucket> 
- <bucket id="4" name="2013-MAY-14 10:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="3.338" /> 
    </bucket> 
- <bucket id="5" name="2013-MAY-14 11:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="2.149" /> 
    </bucket> 
- <bucket id="6" name="2013-MAY-14 12:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="13" /> 
    <perf_data unit="seconds" value="3.202" /> 
    </bucket> 
- <bucket id="7" name="2013-MAY-14 01:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="2.883" /> 
    </bucket> 
- <bucket id="8" name="2013-MAY-14 02:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="2.582" /> 
    </bucket> 
- <bucket id="9" name="2013-MAY-14 03:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="2.769" /> 
    </bucket> 
- <bucket id="10" name="2013-MAY-14 04:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="2.669" /> 
    </bucket> 
- <bucket id="11" name="2013-MAY-14 05:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="2.830" /> 
    </bucket> 
- <bucket id="12" name="2013-MAY-14 06:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="2.591" /> 
    </bucket> 
- <bucket id="13" name="2013-MAY-14 07:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="3.213" /> 
    </bucket> 
- <bucket id="14" name="2013-MAY-14 08:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="2.653" /> 
    </bucket> 
- <bucket id="15" name="2013-MAY-14 09:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="2.935" /> 
    </bucket> 
- <bucket id="16" name="2013-MAY-14 10:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="2.495" /> 
    </bucket> 
- <bucket id="17" name="2013-MAY-14 11:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="3.169" /> 
    </bucket> 
- <bucket id="18" name="2013-MAY-15 12:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="16" /> 
    <perf_data unit="seconds" value="2.789" /> 
    </bucket> 
- <bucket id="19" name="2013-MAY-15 01:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="16" /> 
    <perf_data unit="seconds" value="3.245" /> 
    </bucket> 
- <bucket id="20" name="2013-MAY-15 02:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="3.281" /> 
    </bucket> 
- <bucket id="21" name="2013-MAY-15 03:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="3.773" /> 
    </bucket> 
- <bucket id="22" name="2013-MAY-15 04:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="21" /> 
    <perf_data unit="seconds" value="2.648" /> 
    </bucket> 
- <bucket id="23" name="2013-MAY-15 05:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="3.291" /> 
    </bucket> 
- <bucket id="24" name="2013-MAY-15 06:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="3.084" /> 
    </bucket> 
    </bucket_data> 
- <graph_option> 
    <data_cell name="perfwarning" unit="seconds" value="-" /> 
    <data_cell name="perfcritical" unit="seconds" value="-" /> 
    <data_cell name="availwarning" unit="percent" value="-" /> 
    <data_cell name="availcritical" unit="percent" value="-" /> 
    <data_cell name="bucketsize" unit="seconds" value="3600" /> 
    <data_cell name="rows" unit="#" value="24" /> 
    <data_cell name="pagecomponent" unit="seconds" value="Total Time" /> 
    <data_cell name="avg_perf" unit="seconds" value="2.949" /> 
    <data_cell name="avg_avail" unit="percent" value="100.00" /> 
    <data_cell name="total_datapoint_count" unit="#" value="347" /> 
    <data_cell /> 
    </graph_option> 
    </measurement> 
- <measurement id="521406"> 
    <alias>Site3</alias> 
- <bucket_data> 
- <bucket id="1" name="2013-MAY-14 07:00 AM"> 
    <avail_data unit="percent" value="85.71" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="6.503" /> 
    </bucket> 
- <bucket id="2" name="2013-MAY-14 08:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="13" /> 
    <perf_data unit="seconds" value="6.330" /> 
    </bucket> 
- <bucket id="3" name="2013-MAY-14 09:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="7.242" /> 
    </bucket> 
- <bucket id="4" name="2013-MAY-14 10:00 AM"> 
    <avail_data unit="percent" value="93.33" /> 
    <data_count unit="#" value="14" /> 
    <perf_data unit="seconds" value="7.083" /> 
    </bucket> 
- <bucket id="5" name="2013-MAY-14 11:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="7.087" /> 
    </bucket> 
- <bucket id="6" name="2013-MAY-14 12:00 PM"> 
    <avail_data unit="percent" value="76.92" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="6.197" /> 
    </bucket> 
- <bucket id="7" name="2013-MAY-14 01:00 PM"> 
    <avail_data unit="percent" value="83.33" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="6.772" /> 
    </bucket> 
- <bucket id="8" name="2013-MAY-14 02:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="5.832" /> 
    </bucket> 
- <bucket id="9" name="2013-MAY-14 03:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="8.513" /> 
    </bucket> 
- <bucket id="10" name="2013-MAY-14 04:00 PM"> 
    <avail_data unit="percent" value="91.67" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="7.190" /> 
    </bucket> 
- <bucket id="11" name="2013-MAY-14 05:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="6.373" /> 
    </bucket> 
- <bucket id="12" name="2013-MAY-14 06:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="8.440" /> 
    </bucket> 
- <bucket id="13" name="2013-MAY-14 07:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="6.318" /> 
    </bucket> 
- <bucket id="14" name="2013-MAY-14 08:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="6.374" /> 
    </bucket> 
- <bucket id="15" name="2013-MAY-14 09:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="6.773" /> 
    </bucket> 
- <bucket id="16" name="2013-MAY-14 10:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="6.274" /> 
    </bucket> 
- <bucket id="17" name="2013-MAY-14 11:00 PM"> 
    <avail_data unit="percent" value="90.00" /> 
    <data_count unit="#" value="9" /> 
    <perf_data unit="seconds" value="5.881" /> 
    </bucket> 
- <bucket id="18" name="2013-MAY-15 12:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="16" /> 
    <perf_data unit="seconds" value="5.630" /> 
    </bucket> 
- <bucket id="19" name="2013-MAY-15 01:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="16" /> 
    <perf_data unit="seconds" value="6.585" /> 
    </bucket> 
- <bucket id="20" name="2013-MAY-15 02:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="7.394" /> 
    </bucket> 
- <bucket id="21" name="2013-MAY-15 03:00 AM"> 
    <avail_data unit="percent" value="91.67" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="6.427" /> 
    </bucket> 
- <bucket id="22" name="2013-MAY-15 04:00 AM"> 
    <avail_data unit="percent" value="95.24" /> 
    <data_count unit="#" value="20" /> 
    <perf_data unit="seconds" value="7.140" /> 
    </bucket> 
- <bucket id="23" name="2013-MAY-15 05:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="7.152" /> 
    </bucket> 
- <bucket id="24" name="2013-MAY-15 06:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="6.474" /> 
    </bucket> 
    </bucket_data> 
- <graph_option> 
    <data_cell name="perfwarning" unit="seconds" value="-" /> 
    <data_cell name="perfcritical" unit="seconds" value="-" /> 
    <data_cell name="availwarning" unit="percent" value="-" /> 
    <data_cell name="availcritical" unit="percent" value="-" /> 
    <data_cell name="bucketsize" unit="seconds" value="3600" /> 
    <data_cell name="rows" unit="#" value="24" /> 
    <data_cell name="pagecomponent" unit="seconds" value="Total Time" /> 
    <data_cell name="avg_perf" unit="seconds" value="6.729" /> 
    <data_cell name="avg_avail" unit="percent" value="95.97" /> 
    <data_cell name="total_datapoint_count" unit="#" value="347" /> 
    <data_cell /> 
    </graph_option> 
    </measurement> 
- <measurement id="521406"> 
    <alias>Site2</alias> 
- <bucket_data> 
- <bucket id="1" name="2013-MAY-14 07:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="2.247" /> 
    </bucket> 
- <bucket id="2" name="2013-MAY-14 08:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="13" /> 
    <perf_data unit="seconds" value="2.382" /> 
    </bucket> 
- <bucket id="3" name="2013-MAY-14 09:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="2.232" /> 
    </bucket> 
- <bucket id="4" name="2013-MAY-14 10:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="14" /> 
    <perf_data unit="seconds" value="2.223" /> 
    </bucket> 
- <bucket id="5" name="2013-MAY-14 11:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="2.265" /> 
    </bucket> 
- <bucket id="6" name="2013-MAY-14 12:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="2.130" /> 
    </bucket> 
- <bucket id="7" name="2013-MAY-14 01:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="2.153" /> 
    </bucket> 
- <bucket id="8" name="2013-MAY-14 02:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="2.005" /> 
    </bucket> 
- <bucket id="9" name="2013-MAY-14 03:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="2.322" /> 
    </bucket> 
- <bucket id="10" name="2013-MAY-14 04:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="1.918" /> 
    </bucket> 
- <bucket id="11" name="2013-MAY-14 05:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="1.992" /> 
    </bucket> 
- <bucket id="12" name="2013-MAY-14 06:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="2.423" /> 
    </bucket> 
- <bucket id="13" name="2013-MAY-14 07:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="2.327" /> 
    </bucket> 
- <bucket id="14" name="2013-MAY-14 08:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="2.605" /> 
    </bucket> 
- <bucket id="15" name="2013-MAY-14 09:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="2.533" /> 
    </bucket> 
- <bucket id="16" name="2013-MAY-14 10:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="2.077" /> 
    </bucket> 
- <bucket id="17" name="2013-MAY-14 11:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="9" /> 
    <perf_data unit="seconds" value="2.356" /> 
    </bucket> 
- <bucket id="18" name="2013-MAY-15 12:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="16" /> 
    <perf_data unit="seconds" value="2.506" /> 
    </bucket> 
- <bucket id="19" name="2013-MAY-15 01:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="16" /> 
    <perf_data unit="seconds" value="2.422" /> 
    </bucket> 
- <bucket id="20" name="2013-MAY-15 02:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="2.220" /> 
    </bucket> 
- <bucket id="21" name="2013-MAY-15 03:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="2.669" /> 
    </bucket> 
- <bucket id="22" name="2013-MAY-15 04:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="20" /> 
    <perf_data unit="seconds" value="2.274" /> 
    </bucket> 
- <bucket id="23" name="2013-MAY-15 05:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="2.277" /> 
    </bucket> 
- <bucket id="24" name="2013-MAY-15 06:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="2.180" /> 
    </bucket> 
    </bucket_data> 
- <graph_option> 
    <data_cell name="perfwarning" unit="seconds" value="-" /> 
    <data_cell name="perfcritical" unit="seconds" value="-" /> 
    <data_cell name="availwarning" unit="percent" value="-" /> 
    <data_cell name="availcritical" unit="percent" value="-" /> 
    <data_cell name="bucketsize" unit="seconds" value="3600" /> 
    <data_cell name="rows" unit="#" value="24" /> 
    <data_cell name="pagecomponent" unit="seconds" value="Total Time" /> 
    <data_cell name="avg_perf" unit="seconds" value="2.269" /> 
    <data_cell name="avg_avail" unit="percent" value="100.00" /> 
    <data_cell name="total_datapoint_count" unit="#" value="333" /> 
    <data_cell /> 
    </graph_option> 
    </measurement> 
- <measurement id="521406"> 
    <alias>Site1</alias> 
- <bucket_data> 
- <bucket id="1" name="2013-MAY-14 07:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="1.431" /> 
    </bucket> 
- <bucket id="2" name="2013-MAY-14 08:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="13" /> 
    <perf_data unit="seconds" value="1.559" /> 
    </bucket> 
- <bucket id="3" name="2013-MAY-14 09:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="1.378" /> 
    </bucket> 
- <bucket id="4" name="2013-MAY-14 10:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="14" /> 
    <perf_data unit="seconds" value="1.307" /> 
    </bucket> 
- <bucket id="5" name="2013-MAY-14 11:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="1.458" /> 
    </bucket> 
- <bucket id="6" name="2013-MAY-14 12:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="1.345" /> 
    </bucket> 
- <bucket id="7" name="2013-MAY-14 01:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="1.317" /> 
    </bucket> 
- <bucket id="8" name="2013-MAY-14 02:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="1.465" /> 
    </bucket> 
- <bucket id="9" name="2013-MAY-14 03:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="1.398" /> 
    </bucket> 
- <bucket id="10" name="2013-MAY-14 04:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="1.509" /> 
    </bucket> 
- <bucket id="11" name="2013-MAY-14 05:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="1.284" /> 
    </bucket> 
- <bucket id="12" name="2013-MAY-14 06:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="1.759" /> 
    </bucket> 
- <bucket id="13" name="2013-MAY-14 07:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="1.434" /> 
    </bucket> 
- <bucket id="14" name="2013-MAY-14 08:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="1.402" /> 
    </bucket> 
- <bucket id="15" name="2013-MAY-14 09:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="1.452" /> 
    </bucket> 
- <bucket id="16" name="2013-MAY-14 10:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="1.216" /> 
    </bucket> 
- <bucket id="17" name="2013-MAY-14 11:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="9" /> 
    <perf_data unit="seconds" value="1.381" /> 
    </bucket> 
- <bucket id="18" name="2013-MAY-15 12:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="16" /> 
    <perf_data unit="seconds" value="1.236" /> 
    </bucket> 
- <bucket id="19" name="2013-MAY-15 01:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="16" /> 
    <perf_data unit="seconds" value="1.327" /> 
    </bucket> 
- <bucket id="20" name="2013-MAY-15 02:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="17" /> 
    <perf_data unit="seconds" value="1.465" /> 
    </bucket> 
- <bucket id="21" name="2013-MAY-15 03:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="1.529" /> 
    </bucket> 
- <bucket id="22" name="2013-MAY-15 04:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="20" /> 
    <perf_data unit="seconds" value="1.354" /> 
    </bucket> 
- <bucket id="23" name="2013-MAY-15 05:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="11" /> 
    <perf_data unit="seconds" value="1.372" /> 
    </bucket> 
- <bucket id="24" name="2013-MAY-15 06:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="12" /> 
    <perf_data unit="seconds" value="1.219" /> 
    </bucket> 
    </bucket_data> 
- <graph_option> 
    <data_cell name="perfwarning" unit="seconds" value="-" /> 
    <data_cell name="perfcritical" unit="seconds" value="-" /> 
    <data_cell name="availwarning" unit="percent" value="-" /> 
    <data_cell name="availcritical" unit="percent" value="-" /> 
    <data_cell name="bucketsize" unit="seconds" value="3600" /> 
    <data_cell name="rows" unit="#" value="24" /> 
    <data_cell name="pagecomponent" unit="seconds" value="Total Time" /> 
    <data_cell name="avg_perf" unit="seconds" value="1.387" /> 
    <data_cell name="avg_avail" unit="percent" value="100.00" /> 
    <data_cell name="total_datapoint_count" unit="#" value="333" /> 
    <data_cell /> 
    </graph_option> 
    </measurement> 
    <ns2:link href="www.example.com" rel="slotmetadata" type="application/xml" /> 
    </graph_data> 

мой кадр данных должен выглядеть следующим образом:

alias bucket_name avail_data perf_data 

Я попытался это:

doc1 = xmlParse("data.xml") 
df<-xmlToDataFrame(nodes = getNodeSet(doc1, "//alias")) 

Я получаю только псевдонимы в одном столбце. Какие-нибудь идеи, что еще мне здесь не хватает?

есть файл

Answer 1

Похоже, ваш XML имеет некоторые проблемы. Я мог только получить его на работу, исключив следующее:

Line 58: <measurement id="521406"> 
Line 107: <measurement id="521406"> 

Итак:

xml_file <- '<?xml version="1.0" encoding="UTF-8" standalone="yes" ?> 
    <graph_data xmlns:ns2="http://www.w3.org/2005/Atom"> 
    <graph_property name="calculation_method" value="Geo Mean" /> 
    <graph_property name="graph_type" value="TIME" /> <measurement id="521406"> 
    <alias>example1.com</alias> 
    <bucket_data> 
    <bucket id="1" name="2013-MAY-14 07:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="21" /> 
    <perf_data unit="seconds" value="3.102" /> 
    </bucket> 
    <bucket id="2" name="2013-MAY-14 08:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="13" /> 
    <perf_data unit="seconds" value="3.052" /> 
    </bucket> 
    <bucket id="3" name="2013-MAY-14 09:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="3.387" /> 
    </bucket> 
    <bucket id="4" name="2013-MAY-14 10:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="3.338" /> 
    </bucket> 
    <bucket id="5" name="2013-MAY-14 11:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="2.149" /> 
    </bucket> 
    <bucket id="6" name="2013-MAY-14 12:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="13" /> 
    <perf_data unit="seconds" value="3.202" /> 
    </bucket> 
    <bucket id="7" name="2013-MAY-14 01:00 PM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="2.883" /> 
    </bucket> 
    </bucket_data> 
    <graph_option> 
    <data_cell name="perfwarning" unit="seconds" value="-" /> 
    <data_cell name="perfcritical" unit="seconds" value="-" /> 
    <data_cell name="availwarning" unit="percent" value="-" /> 
    <data_cell name="availcritical" unit="percent" value="-" /> 
    <data_cell name="bucketsize" unit="seconds" value="3600" /> 
    <data_cell name="rows" unit="#" value="24" /> 
    <data_cell name="pagecomponent" unit="seconds" value="Total Time" /> 
    <data_cell name="avg_perf" unit="seconds" value="2.949" /> 
    <data_cell name="avg_avail" unit="percent" value="100.00" /> 
    <data_cell name="total_datapoint_count" unit="#" value="347" /> 
    <data_cell /> 
    </graph_option> 
    </measurement> 
    <measurement id="521406"> 
    <alias>example2.com</alias> 
    <bucket_data> 
    <bucket id="1" name="2013-MAY-14 07:00 AM"> 
    <avail_data unit="percent" value="85.71" /> 
    <data_count unit="#" value="18" /> 
    <perf_data unit="seconds" value="6.503" /> 
    </bucket> 
    <bucket id="2" name="2013-MAY-14 08:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="13" /> 
    <perf_data unit="seconds" value="6.330" /> 
    </bucket> 
    <bucket id="3" name="2013-MAY-14 09:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="15" /> 
    <perf_data unit="seconds" value="7.242" /> 
    </bucket> 
    <bucket id="4" name="2013-MAY-14 10:00 AM"> 
    <avail_data unit="percent" value="93.33" /> 
    <data_count unit="#" value="14" /> 
    <perf_data unit="seconds" value="7.083" /> 
    </bucket> 
    <bucket id="5" name="2013-MAY-14 11:00 AM"> 
    <avail_data unit="percent" value="100.00" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="7.087" /> 
    </bucket> 
    <bucket id="6" name="2013-MAY-14 12:00 PM"> 
    <avail_data unit="percent" value="76.92" /> 
    <data_count unit="#" value="10" /> 
    <perf_data unit="seconds" value="6.197" /> 
    </bucket> 
    </bucket_data> 
    <graph_option> 
    <data_cell name="perfwarning" unit="seconds" value="-" /> 
    <data_cell name="perfcritical" unit="seconds" value="-" /> 
    <data_cell name="availwarning" unit="percent" value="-" /> 
    <data_cell name="availcritical" unit="percent" value="-" /> 
    <data_cell name="bucketsize" unit="seconds" value="3600" /> 
    <data_cell name="rows" unit="#" value="24" /> 
    <data_cell name="pagecomponent" unit="seconds" value="Total Time" /> 
    <data_cell name="avg_perf" unit="seconds" value="6.729" /> 
    <data_cell name="avg_avail" unit="percent" value="95.97" /> 
    <data_cell name="total_datapoint_count" unit="#" value="347" /> 
    <data_cell /> 
    </graph_option> 
    </measurement> 
    </graph_data>' 

xml_file <- xmlParse(xml_file) # Parse the XML 
xml_file <- xmlToList(xml_file) # Convert the XML to a list 

Я превращал его в список вместо фрейма данных, так как XML, кажется, не следовать структуре который легко преобразуется в строки и столбцы. После этого, основываясь на ваш вопрос, я вытащил только информацию, содержащуюся в «псевдоним» или «bucket_data» частями «измерения» узлов:

xml_file <- xml_file[names(xml_file) == "measurement"] 
xml_file <- lapply(xml_file, function(x) x[grep("alias|bucket", names(x))]) 

Тогда я пошел через каждый узел измерения, отложите в сторону alias, превратил список ведер в именованный вектор, а затем связал псевдоним и ведра вместе в столбцы. Наконец, я привязал измерительные узлы к строкам и преобразовал все это в кадр данных.

xml_file <- lapply(xml_file, function(x) { 
    alias <- x$alias 
    buckets <- t(sapply(x$bucket_data, unlist)) 
    cbind("alias" = alias, buckets) 
}) 

xml_file <- do.call("rbind", xml_file) 

xml_file <- data.frame(xml_file, stringsAsFactors = FALSE) 
Warning message: 
In data.row.names(row.names, rowsi, i) : 
    some row.names duplicated: 2,3,4,5,6,7,8,9,10,11,12,13 --> row.names NOT used 

str(xml_file) 
'data.frame': 13 obs. of 9 variables: 
$ alias   : chr "example1.com" "example1.com" "example1.com" "example1.com" ... 
$ avail_data.unit : chr "percent" "percent" "percent" "percent" ... 
$ avail_data.value: chr "100.00" "100.00" "100.00" "100.00" ... 
$ data_count.unit : chr "#" "#" "#" "#" ... 
$ data_count.value: chr "21" "13" "15" "15" ... 
$ perf_data.unit : chr "seconds" "seconds" "seconds" "seconds" ... 
$ perf_data.value : chr "3.102" "3.052" "3.387" "3.338" ... 
$ .attrs.id  : chr "1" "2" "3" "4" ... 
$ .attrs.name  : chr "2013-MAY-14 07:00 AM" "2013-MAY-14 08:00 AM" "2013-MAY-14 09:00 AM" "2013-MAY-14 10:00 AM" ... 

Вам все еще нужно, чтобы очистить имена столбцов и преобразовать столбцы в соответствующие классы, но он получает данные в кадр данных.