XML File:14065000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14065000.xml", line 166853 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: Year line 65535 and Yuar, line 166853, column 43 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14095000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14095000.xml", line 33036 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: AbstractText line 33036 and ArstractText, line 33036, column 722 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14100000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14100000.xml", line 7841 lxml.etree.XMLSyntaxError: Specification mandates value for attribute PubMode, line 7841, column 25 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14105000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14105000.xml", line 53600 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: DescriptorName line 53600 and DescriptorNamu, line 53600, column 116 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:14115000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14115000.xml", line 17470 lxml.etree.XMLSyntaxError: error parsing attribute name, line 17470, column 26 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 63, in getTerms mesh.append(m.find('NameOfSubstance').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 63, in getTerms mesh.append(m.find('NameOfSubstance').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14120000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14120000.xml", line 46266 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: MeshHeading line 46263 and MeshHeadinw, line 46266, column 37 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14125000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14125000.xml", line 287901 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: RegistryNumber line 65535 and RegistryNumbur, line 287901, column 72 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14130000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14130000.xml", line 343248 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: DescryptorName line 65535 and DescriptorName, line 343248, column 98 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14145000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14145000.xml", line 355597 lxml.etree.XMLSyntaxError: error parsing attribute name, line 355597, column 30 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14150000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14150000.xml", line 309974 lxml.etree.XMLSyntaxError: error parsing attribute name, line 309974, column 18 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:14155000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14155000.xml", line 141978 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: Yeqr line 65535 and Year, line 141978, column 36 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' XML File:14175000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14175000.xml", line 88722 lxml.etree.XMLSyntaxError: error parsing attribute name, line 88722, column 28 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14200000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14200000.xml", line 191435 lxml.etree.XMLSyntaxError: error parsing attribute name, line 191435, column 19 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:14280000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14280000.xml", line 704400 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: PMID line 65535 and PMYD, line 704400, column 51 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14345000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14345000.xml", line 119347 lxml.etree.XMLSyntaxError: error parsing attribute name, line 119347, column 28 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 63, in getTerms mesh.append(m.find('NameOfSubstance').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 63, in getTerms mesh.append(m.find('NameOfSubstance').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14375000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14375000.xml", line 168870 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: Yssue line 65535 and Issue, line 168870, column 37 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14390000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14390000.xml", line 192934 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: Xistory line 65535 and History, line 192934, column 19 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:14395000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14395000.xml", line 30175 lxml.etree.XMLSyntaxError: error parsing attribute name, line 30175, column 30 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14410000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14410000.xml", line 122600 lxml.etree.XMLSyntaxError: error parsing attribute name, line 122600, column 22 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14450000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14450000.xml", line 269344 lxml.etree.XMLSyntaxError: Specification mandates value for attribute ValidY, line 269344, column 31 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14505000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14505000.xml", line 93223 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: PublicationTypu line 65535 and PublicationType, line 93223, column 111 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' XML File:14530000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14530000.xml", line 236288 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: DessriptorName line 65535 and DescriptorName, line 236288, column 92 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14545000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14545000.xml", line 534308 lxml.etree.XMLSyntaxError: AttValue: " or ' expected, line 534308, column 36 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:14550000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14550000.xml", line 68494 lxml.etree.XMLSyntaxError: Specification mandates value for attribute Iss, line 68494, column 26 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 63, in getTerms mesh.append(m.find('NameOfSubstance').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 63, in getTerms mesh.append(m.find('NameOfSubstance').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14610000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14610000.xml", line 295784 lxml.etree.XMLSyntaxError: Specification mandates value for attribute MajorT, line 295784, column 52 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14620000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14620000.xml", line 393322 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: MeshHeqding line 65535 and MeshHeading, line 393322, column 33 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:14660000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14660000.xml", line 431074 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: DescryptorName line 65535 and DescriptorName, line 431074, column 90 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:14670000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/14670000.xml", line 662442 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: RufSource line 65535 and RefSource, line 662442, column 71 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 63, in getTerms mesh.append(m.find('NameOfSubstance').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 63, in getTerms mesh.append(m.find('NameOfSubstance').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:18475000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/18475000.xml", line 29035 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: PMIT line 29035 and PMID, line 29035, column 53 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 84, in parse pmid= elem.find('MedlineCitation').find('PMID').text # First PMID is the right one AttributeError: 'NoneType' object has no attribute 'find' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 84, in parse pmid= elem.find('MedlineCitation').find('PMID').text # First PMID is the right one AttributeError: 'NoneType' object has no attribute 'find' XML File:18810000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/18810000.xml", line 175103 lxml.etree.XMLSyntaxError: AttValue: " or ' expected, line 175103, column 36 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:19125000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/19125000.xml", line 108418 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: DessriptorName line 65535 and DescriptorName, line 108418, column 94 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:21350000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21350000.xml", line 236887 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: DescriptorNamu line 65535 and DescriptorName, line 236887, column 114 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:21355000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21355000.xml", line 96511 lxml.etree.XMLSyntaxError: expected '>', line 96511, column 46 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:21365000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21365000.xml", line 53120 lxml.etree.XMLSyntaxError: error parsing attribute name, line 53120, column 21 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:21370000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21370000.xml", line 135792 lxml.etree.XMLSyntaxError: Specification mandates value for attribute Maj, line 135792, column 49 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 84, in parse pmid= elem.find('MedlineCitation').find('PMID').text # First PMID is the right one AttributeError: 'NoneType' object has no attribute 'find' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 84, in parse pmid= elem.find('MedlineCitation').find('PMID').text # First PMID is the right one AttributeError: 'NoneType' object has no attribute 'find' XML File:21385000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21385000.xml", line 86725 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: TescriptorName line 65535 and DescriptorName, line 86725, column 86 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:21410000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21410000.xml", line 505959 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: Keyword line 65535 and Keywort, line 505959, column 77 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' XML File:21480000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21480000.xml", line 325092 lxml.etree.XMLSyntaxError: AttValue: " or ' expected, line 325092, column 36 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:21810000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21810000.xml", line 206975 lxml.etree.XMLSyntaxError: error parsing attribute name, line 206975, column 28 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:21820000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21820000.xml", line 193310 lxml.etree.XMLSyntaxError: expected '>', line 193310, column 29 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:21825000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21825000.xml", line 1760 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: DescriptorNamu line 1760 and DescriptorName, line 1760, column 102 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:21835000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21835000.xml", line 91615 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: Inityals line 65535 and Initials, line 91615, column 48 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 84, in parse pmid= elem.find('MedlineCitation').find('PMID').text # First PMID is the right one AttributeError: 'NoneType' object has no attribute 'find' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 84, in parse pmid= elem.find('MedlineCitation').find('PMID').text # First PMID is the right one AttributeError: 'NoneType' object has no attribute 'find' XML File:21840000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21840000.xml", line 33762 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: CitationSubsut line 33762 and CitationSubset, line 33762, column 56 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' XML File:21845000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21845000.xml", line 41420 lxml.etree.XMLSyntaxError: error parsing attribute name, line 41420, column 41 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' XML File:21850000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21850000.xml", line 17478 lxml.etree.XMLSyntaxError: expected '>', line 17478, column 82 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 105, in parse years=getYears(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 78, in getYears years.append(child.find('Year').text) AttributeError: 'NoneType' object has no attribute 'text' XML File:21865000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21865000.xml", line 5990 lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: ForeName line 5990 and ForeNamu, line 5990, column 50 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) File "src/lxml/etree.pyx", line 2469, in lxml.etree._Attrib.__getitem__ (src/lxml/etree.c:72092) KeyError: 'UI' XML File:21870000 has a problem. Skipping...Error:Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 92, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 83, in parse for _,elem in context: File "src/lxml/iterparse.pxi", line 208, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155963) File "src/lxml/iterparse.pxi", line 193, in lxml.etree.iterparse.__next__ (src/lxml/etree.c:155671) File "src/lxml/iterparse.pxi", line 228, in lxml.etree.iterparse._read_more_events (src/lxml/etree.c:156298) File "src/lxml/parser.pxi", line 1362, in lxml.etree._FeedParser.feed (src/lxml/etree.c:116552) File "src/lxml/parser.pxi", line 589, in lxml.etree._ParserContext._handleParseResult (src/lxml/etree.c:107619) File "src/lxml/parser.pxi", line 598, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/etree.c:107738) File "src/lxml/parser.pxi", line 709, in lxml.etree._handleParseResult (src/lxml/etree.c:109447) File "src/lxml/parser.pxi", line 638, in lxml.etree._raiseParseError (src/lxml/etree.c:108301) File "/home/stephen/ExtraDrive1/MeSH_V3/21870000.xml", line 4199 lxml.etree.XMLSyntaxError: error parsing attribute name, line 4199, column 18 During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 95, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/stephen/Documents/Projects/MeTeORv2/src/crawlPubMedFiles.py", line 107, in main indicies,pmids,meshids,miss=parse('{}/{}.xml'.format(storagedir,i),enumpmid,enumui,uis,meta,recover=True) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 95, in parse mesh = getTerms(elem) File "/home/stephen/Documents/Projects/MeTeORv2/src/utils.py", line 56, in getTerms mesh.append(m.find('DescriptorName').attrib['UI']) AttributeError: 'NoneType' object has no attribute 'attrib'