Update app.py

app.py

@@ -2,7 +2,7 @@ import streamlit as st
 import requests
 import xml.etree.ElementTree as ET
 import pandas as pd
-from googletrans import Translator
+from googletrans import Translator, LANGUAGES
 
 # 语言翻译字典
 translations = {
@@ -19,7 +19,10 @@ translations = {
         "col_title": "Title",
         "col_abstract": "Abstract",
         "col_authors": "Authors",
-        "col_link": "Link"
+        "col_link": "Link",
+        "spinner_searching": "Searching PubMed and fetching articles...",
+        "spinner_translating": "Translating results to Chinese...",
+        "translation_warning": "Could not translate an entry. Displaying original text."
     },
     "zh": {
         "title": "PubMed 文献检索",
@@ -34,13 +37,17 @@ translations = {
         "col_title": "文献标题",
         "col_abstract": "文献摘要",
         "col_authors": "文献作者",
-        "col_link": "文献链接"
+        "col_link": "文献链接",
+        "spinner_searching": "正在检索 PubMed 并获取文献...",
+        "spinner_translating": "正在将结果翻译成中文...",
+        "translation_warning": "部分条目翻译失败，将显示原文。"
     }
 }
 
 def get_translation(lang, key):
     return translations[lang][key]
 
+@st.cache_data(ttl=3600)  # 缓存1小时，避免重复请求
 def search_pubmed(query, retmax=200):
     """
     使用PubMed API进行检索
@@ -48,28 +55,31 @@ def search_pubmed(query, retmax=200):
     base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
     search_url = f"{base_url}esearch.fcgi?db=pubmed&term={query}&retmax={retmax}"
     try:
-        search_response = requests.get(search_url)
+        search_response = requests.get(search_url, timeout=15)
         search_response.raise_for_status()
         search_root = ET.fromstring(search_response.content)
         id_list = [id_elem.text for id_elem in search_root.findall(".//Id")]
         return id_list
     except requests.exceptions.RequestException as e:
-        st.error(f"Error during eSearch: {e}")
+        st.error(f"Error during PubMed ID search: {e}")
         return []
 
-def fetch_articles(id_list):
+@st.cache_data(ttl=3600) # 缓存1小时
+def fetch_articles(_id_list): # _id_list to indicate it's cached based on this value
     """
     根据ID列表获取文献详情
     """
+    if not _id_list:
+        return None
     base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
-    ids = ",".join(id_list)
+    ids = ",".join(_id_list)
     fetch_url = f"{base_url}efetch.fcgi?db=pubmed&id={ids}&rettype=xml"
     try:
-        fetch_response = requests.get(fetch_url)
+        fetch_response = requests.get(fetch_url, timeout=30)
         fetch_response.raise_for_status()
         return fetch_response.content
     except requests.exceptions.RequestException as e:
-        st.error(f"Error during eFetch: {e}")
+        st.error(f"Error during fetching article details: {e}")
         return None
 
 def parse_articles(xml_data):
@@ -81,14 +91,14 @@ def parse_articles(xml_data):
         root = ET.fromstring(xml_data)
         for article in root.findall(".//PubmedArticle"):
             title_elem = article.find(".//ArticleTitle")
-            title = title_elem.text if title_elem is not None else "No Title"
+            title = "".join(title_elem.itertext()) if title_elem is not None else "No Title"
 
-            abstract_elem = article.find(".//AbstractText")
-            abstract = abstract_elem.text if abstract_elem is not None else "No Abstract"
+            abstract_elem = article.find(".//Abstract/AbstractText")
+            abstract = "".join(abstract_elem.itertext()) if abstract_elem is not None else "No Abstract"
 
             author_list = article.findall(".//Author")
             authors = ", ".join([
-                f"{author.find('LastName').text if author.find('LastName') is not None else ''} {author.find('ForeName').text if author.find('ForeName') is not None else ''}".strip()
+                f"{author.find('LastName').text if author.find('LastName') is not None else ''} {author.find('Initials').text if author.find('Initials') is not None else ''}".strip()
                 for author in author_list
             ]) if author_list else "No Authors"
 
@@ -105,11 +115,11 @@ def parse_articles(xml_data):
     return articles
 
 def main():
-    st.set_page_config(layout="wide")
+    st.set_page_config(layout="wide", page_title="PubMed Search Tool")
 
     # 语言选择
     lang = st.sidebar.radio(
-        "Language / 语言",
+        get_translation("en", "language_label") + " / " + get_translation("zh", "language_label"),
         ("en", "zh"),
         format_func=lambda x: "English" if x == "en" else "中文"
     )
@@ -117,48 +127,58 @@ def main():
     st.title(get_translation(lang, "title"))
 
     # 搜索框
-    search_query = st.text_input(get_translation(lang, "search_placeholder"))
+    search_query = st.text_input("", placeholder=get_translation(lang, "search_placeholder"))
 
     if st.button(get_translation(lang, "search_button")):
         if search_query:
-            with st.spinner('Searching...'):
+            with st.spinner(get_translation(lang, "spinner_searching")):
                 id_list = search_pubmed(search_query)
                 if id_list:
-                    xml_data = fetch_articles(id_list)
+                    xml_data = fetch_articles(tuple(id_list)) # Use tuple for caching
                     if xml_data:
                         articles = parse_articles(xml_data)
-                        if articles:
-                            st.subheader(get_translation(lang, "results_title"))
-
-                            # 翻译标题和摘要
-                            if lang == 'zh':
-                                translator = Translator()
-                                for article in articles:
-                                    try:
-                                        article['Title'] = translator.translate(article['Title'], dest='zh-cn').text
-                                        article['Abstract'] = translator.translate(article['Abstract'], dest='zh-cn').text
-                                    except Exception as e:
-                                        st.warning(f"翻译时出错: {e}")
-
-
-                            df = pd.DataFrame(articles)
-                            df.index = range(1, len(df) + 1)
-                            df.rename(columns={
-                                "Title": get_translation(lang, "col_title"),
-                                "Abstract": get_translation(lang, "col_abstract"),
-                                "Authors": get_translation(lang, "col_authors"),
-                                "Link": get_translation(lang, "col_link")
-                            }, inplace=True)
-                            df.index.name = get_translation(lang, "col_index")
-
-                            st.dataframe(df)
-                        else:
-                            st.warning(get_translation(lang, "no_results"))
                     else:
-                        st.error(get_translation(lang, "error_message"))
+                        articles = []
                 else:
-                    st.warning(get_translation(lang, "no_results"))
+                    articles = []
+
+            if articles:
+                st.subheader(get_translation(lang, "results_title"))
+                df = pd.DataFrame(articles)
+
+                # 如果是中文，则进行翻译
+                if lang == 'zh':
+                    with st.spinner(get_translation(lang, "spinner_translating")):
+                        translator = Translator()
+                        # 创建一个新的DataFrame来存储翻译结果
+                        df_translated = df.copy()
+                        for index, row in df.iterrows():
+                            try:
+                                # 翻译标题
+                                if row['Title'] != "No Title":
+                                    df_translated.at[index, 'Title'] = translator.translate(row['Title'], dest='zh-cn').text
+                                # 翻译摘要
+                                if row['Abstract'] != "No Abstract":
+                                    df_translated.at[index, 'Abstract'] = translator.translate(row['Abstract'], dest='zh-cn').text
+                            except Exception:
+                                st.warning(get_translation(lang, "translation_warning"), icon="⚠️")
+                                # 如果翻译失败，保留原文
+                                continue
+                        df = df_translated
+
+
+                df.index = range(1, len(df) + 1)
+                df.rename(columns={
+                    "Title": get_translation(lang, "col_title"),
+                    "Abstract": get_translation(lang, "col_abstract"),
+                    "Authors": get_translation(lang, "col_authors"),
+                    "Link": get_translation(lang, "col_link")
+                }, inplace=True)
+                df.index.name = get_translation(lang, "col_index")
+
+                st.dataframe(df)
+            else:
+                st.warning(get_translation(lang, "no_results"))
 
 if __name__ == "__main__":
-    main()
-
+    main()