Modified els parser to use 'author' abstract as default (#124)

* Modified els parser to use 'author' abstract as default * replacing elsevier test case with OA record * redacted source content --------- Co-authored-by: Mugdha Polimera <[email protected]> Co-authored-by: Mugdha Polimera <[email protected]>
adsabs · Aug 21, 2024 · 5f376ac · 5f376ac
1 parent 4874484
commit 5f376ac
Show file tree

Hide file tree

Showing 4 changed files with 1,233 additions and 11 deletions.
diff --git a/adsingestp/parsers/elsevier.py b/adsingestp/parsers/elsevier.py
@@ -183,23 +183,19 @@ def _parse_title_abstract(self):
             for abs in abs_all:
                 if abs.get("class", None) == "author":
                     abs_text_all = abs.find_all("ce:simple-para")
+                    break
                 elif abs.find("ce:section-title"):
                     if abs.find("ce:section-title").get_text().lower() == "abstract":
                         abs_text_all = abs.find_all("ce:simple-para")
+                        break
                     elif abs.find("ce:section-title").get_text().lower() == "highlights":
                         abs_text_all = abs.find_all("p")
 
-                abstract = ""
-                for abs_text in abs_text_all:
-                    abstract = (
-                        abstract
-                        + " "
-                        + self._detag(abs_text, self.HTML_TAGSET["abstract"]).strip()
-                    )
-
-                if abstract:
-                    self.base_metadata["abstract"] = abstract
-                    break
+            abstract = ""
+            for abs_text in abs_text_all:
+                abstract = (
+                    abstract + " " + self._detag(abs_text, self.HTML_TAGSET["abstract"]).strip()
+                )
 
             if abstract:
                 self.base_metadata["abstract"] = self._clean_output(abstract)