#110 Parse text inside journal-title nodes.

titipata · Jun 2, 2024 · d255a2f · d255a2f
1 parent f0bc9d2
commit d255a2f
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
@@ -156,7 +156,7 @@ def parse_pubmed_xml(path, include_path=False, nxml=False):
 
     journal_node = tree.findall(".//journal-title")
     if journal_node is not None:
-        journal = " ".join([j.text for j in journal_node])
+        journal = " ".join(["".join(node.itertext()) for node in journal_node])
     else:
         journal = ""
 

diff --git a/tests/test_pubmed_oa_parser.py b/tests/test_pubmed_oa_parser.py
@@ -39,6 +39,7 @@ def test_parse_pubmed_xml():
     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"  # noqa
     assert "Competing Interests: " in parsed_xml.get("coi_statement")
+    assert parsed_xml.get("journal") == "PLoS ONE"
 
 
 def test_parse_pubmed_paragraph():