From d56fd17239cca425a72c4882fb0db01c23fd1eff Mon Sep 17 00:00:00 2001 From: Ivan Pavlovich <ivan.pavlovic@hes-so.ch> Date: Wed, 12 Mar 2025 18:34:13 +0100 Subject: [PATCH] Modification of article store script --- .gitignore | 1 + dataSources/PubMed/data/save_3_years.json | 1 - dataSources/PubMed/pubmedApi.py | 14 ++++++++++---- 3 files changed, 11 insertions(+), 5 deletions(-) delete mode 100644 dataSources/PubMed/data/save_3_years.json diff --git a/.gitignore b/.gitignore index f13d16f8b..575b7a337 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,3 @@ dataSources/PubMed/tmp/* +dataSources/PubMed/data/* .venv \ No newline at end of file diff --git a/dataSources/PubMed/data/save_3_years.json b/dataSources/PubMed/data/save_3_years.json deleted file mode 100644 index 0637a088a..000000000 --- a/dataSources/PubMed/data/save_3_years.json +++ /dev/null @@ -1 +0,0 @@ -[] \ No newline at end of file diff --git a/dataSources/PubMed/pubmedApi.py b/dataSources/PubMed/pubmedApi.py index 8523c34c8..df29e7449 100644 --- a/dataSources/PubMed/pubmedApi.py +++ b/dataSources/PubMed/pubmedApi.py @@ -85,16 +85,20 @@ def getPubmedData(term, date_min, date_max, nb_items = -1, debug = False, store for part in entrie["MedlineCitation"]["Article"]["Journal"]["Title"]: if "#text" in part: data["Title"] += part["#text"] - else: - data["Title"] = entrie["MedlineCitation"]["Article"]["Journal"]["Title"] + elif isinstance(entrie["MedlineCitation"]["Article"]["Journal"]["Title"], object): + data["Title"] = entrie["MedlineCitation"]["Article"]["Journal"]["Title"]["#text"] + else: + data["Title"] = entrie["MedlineCitation"]["Article"]["Journal"]["Title"] data["ArticleTitle"] = "" if isinstance(entrie["MedlineCitation"]["Article"]["ArticleTitle"], list): for part in entrie["MedlineCitation"]["Article"]["ArticleTitle"]: if "#text" in part: data["ArticleTitle"] += part["#text"] - else: - data["ArticleTitle"] = entrie["MedlineCitation"]["Article"]["ArticleTitle"] + elif isinstance(entrie["MedlineCitation"]["Article"]["ArticleTitle"], object): + data["ArticleTitle"] = entrie["MedlineCitation"]["Article"]["ArticleTitle"]["#text"] + else: + data["ArticleTitle"] = entrie["MedlineCitation"]["Article"]["ArticleTitle"] data["Abstract"] = "" if "Abstract" in entrie["MedlineCitation"]["Article"] : @@ -102,6 +106,8 @@ def getPubmedData(term, date_min, date_max, nb_items = -1, debug = False, store for part in entrie["MedlineCitation"]["Article"]["Abstract"]["AbstractText"]: if "#text" in part: data["Abstract"] += part["#text"] + elif isinstance(entrie["MedlineCitation"]["Article"]["Abstract"]["AbstractText"], object): + data["Abstract"] = entrie["MedlineCitation"]["Article"]["Abstract"]["AbstractText"]["#text"] else: data["Abstract"] = entrie["MedlineCitation"]["Article"]["Abstract"]["AbstractText"] -- GitLab