Merge pull request titipata#89 from thomascpan/master

Fix subjects xpath in parse_pubmed_xml. Fixes titipata#87
mengysun · Apr 21, 2020 · d958d74 · d958d74
2 parents 1376aa6 + 95cdc51
commit d958d74
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 1 deletion.
diff --git a/pubmed_parser/pubmed_oa_parser.py b/pubmed_parser/pubmed_oa_parser.py
@@ -145,7 +145,7 @@ def parse_pubmed_xml(path, include_path=False, nxml=False):
     pub_day_node = tree.find(".//pub-date/day")
     pub_day = pub_day_node.text if pub_day_node is not None else "01"
 
-    subjects_node = tree.findall(".//article-categories.//subj-group/subject")
+    subjects_node = tree.findall(".//article-categories//subj-group/subject")
     subjects = list()
     if subjects_node is not None:
         for s in subjects_node:

diff --git a/tests/test_pubmed_oa_parser.py b/tests/test_pubmed_oa_parser.py
@@ -14,6 +14,7 @@ def test_parse_pubmed_xml():
     assert len(parsed_xml.get("full_title")) > 0
     assert parsed_xml.get("pmc") == "3460867"
     assert parsed_xml.get("doi") == "10.1371/journal.pone.0046493"
+    assert parsed_xml.get("subjects") == "Research Article; Biology; Biochemistry; Enzymes; Enzyme Metabolism; Lipids; Fatty Acids; Glycerides; Lipid Metabolism; Neutral Lipids; Metabolism; Lipid Metabolism; Proteins; Globular Proteins; Protein Classes; Recombinant Proteins; Biotechnology; Microbiology; Bacterial Pathogens; Bacteriology; Emerging Infectious Diseases; Host-Pathogen Interaction; Microbial Growth and Development; Microbial Metabolism; Microbial Pathogens; Microbial Physiology; Proteomics; Sequence Analysis; Spectrometric Identification of Proteins"
 
 
 def test_parse_pubmed_paragraph():