feat: add reusable CSV/XLS export utility and filtered download routes to journal page classes

core/home/models.py

@@ -18,6 +18,11 @@
 from wagtailcaptcha.models import WagtailCaptchaEmailForm
 
 from collection.models import Collection
+from core.home.utils.export_journals import (
+    generate_csv_response,
+    generate_xls_response,
+    get_scielo_journals_data,
+)
 from core.home.utils.get_social_networks import get_social_networks
 from journal.choices import STUDY_AREA
 from journal.models import OwnerHistory, SciELOJournal
@@ -79,6 +84,18 @@ def _default_context(context):
     context["page_about"] = get_page_about()
 
 
+class JournalDownloadMixin:
+    @re_path(r"^download-csv/$", name="download_csv")
+    def download_csv(self, request):
+        journals_data = get_scielo_journals_data()
+        return generate_csv_response(journals_data)
+
+    @re_path(r"^download-xls/$", name="download_xls")
+    def download_xls(self, request):
+        journals_data = get_scielo_journals_data()
+        return generate_xls_response(journals_data)
+
+
 def get_page_about():
     try:
         locale = _get_current_locale()
@@ -221,7 +238,7 @@ def get_context(self, request, *args, **kwargs):
         return context
 
 
-class ListPageJournal(Page):
+class ListPageJournal(JournalDownloadMixin, RoutablePageMixin, Page):
     def get_context(self, request, *args, **kwargs):
         context = super().get_context(request, *args, **kwargs)
         search_term = request.GET.get("search_term", "")
@@ -237,7 +254,7 @@ def get_context(self, request, *args, **kwargs):
         return context
 
 
-class ListPageJournalByPublisher(Page):
+class ListPageJournalByPublisher(JournalDownloadMixin, RoutablePageMixin, Page):
     def get_context(self, request, *args, **kwargs):
         context = super().get_context(request, *args, **kwargs)
         search_term = request.GET.get("search_term", "")
@@ -283,7 +300,7 @@ def get_context(self, request, *args, **kwargs):
         return context
 
 
-class ListPageJournalByCategory(RoutablePageMixin, Page):
+class ListPageJournalByCategory(JournalDownloadMixin, RoutablePageMixin, Page):
     def get_context(self, request, *args, **kwargs):
         context = super().get_context(request, *args, **kwargs)
 

core/home/tests.py

@@ -6,7 +6,11 @@
 from core.users.models import User
 from journal.models import Journal, SciELOJournal
 
-from core.home.views import _get_scielo_journals_data
+from core.home.utils.export_journals import (
+    generate_csv_response,
+    generate_xls_response,
+    get_scielo_journals_data,
+)
 
 
 class TestGetScieloJournalsData(TestCase):
@@ -30,15 +34,15 @@ def setUp(self):
 
     def test_scielo_url_does_not_have_double_http_prefix(self):
         """URL must not contain 'http://http://' when domain already has http://"""
-        data = _get_scielo_journals_data()
+        data = get_scielo_journals_data()
         self.assertTrue(len(data) > 0)
         for item in data:
             self.assertNotIn("http://http://", item["scielo_url"])
             self.assertNotIn("http://https://", item["scielo_url"])
 
     def test_scielo_url_is_well_formed(self):
         """URL must be a valid scielo.php URL with the correct domain"""
-        data = _get_scielo_journals_data()
+        data = get_scielo_journals_data()
         self.assertEqual(len(data), 1)
         expected_url = (
             "http://www.scielo.org.pe/scielo.php?script=sci_serial"
@@ -50,15 +54,58 @@ def test_scielo_url_strips_trailing_slash_from_domain(self):
         """Trailing slash in domain must not produce double slash in URL"""
         self.collection.domain = "http://www.scielo.org.pe/"
         self.collection.save()
-        data = _get_scielo_journals_data()
+        data = get_scielo_journals_data()
         self.assertEqual(len(data), 1)
         self.assertNotIn("//scielo.php", data[0]["scielo_url"])
 
     def test_scielo_url_with_https_domain(self):
         """URL must be correct when domain uses https://"""
         self.collection.domain = "https://www.scielo.br"
         self.collection.save()
-        data = _get_scielo_journals_data()
+        data = get_scielo_journals_data()
         self.assertEqual(len(data), 1)
         self.assertTrue(data[0]["scielo_url"].startswith("https://www.scielo.br/"))
         self.assertNotIn("https://https://", data[0]["scielo_url"])
+
+
+class TestGenerateCsvResponse(TestCase):
+    def test_csv_response_content_type(self):
+        response = generate_csv_response([])
+        self.assertEqual(response["Content-Type"], "text/csv")
+
+    def test_csv_response_has_attachment_header(self):
+        response = generate_csv_response([])
+        self.assertIn("attachment", response["Content-Disposition"])
+        self.assertIn(".csv", response["Content-Disposition"])
+
+    def test_csv_response_contains_headers(self):
+        response = generate_csv_response([])
+        content = response.content.decode("utf-8")
+        self.assertIn("journals", content)
+        self.assertIn("scielo_url", content)
+        self.assertIn("publisher", content)
+
+    def test_csv_response_contains_data(self):
+        data = [
+            {
+                "title": "Test Journal",
+                "scielo_url": "http://example.com/journal",
+                "owner": "Test Publisher",
+            }
+        ]
+        response = generate_csv_response(data)
+        content = response.content.decode("utf-8")
+        self.assertIn("Test Journal", content)
+        self.assertIn("http://example.com/journal", content)
+        self.assertIn("Test Publisher", content)
+
+
+class TestGenerateXlsResponse(TestCase):
+    def test_xls_response_content_type(self):
+        response = generate_xls_response([])
+        self.assertEqual(response["Content-Type"], "application/vnd.ms-excel")
+
+    def test_xls_response_has_attachment_header(self):
+        response = generate_xls_response([])
+        self.assertIn("attachment", response["Content-Disposition"])
+        self.assertIn(".xls", response["Content-Disposition"])

core/home/utils/export_journals.py

@@ -0,0 +1,87 @@
+import csv
+import logging
+
+import xlwt
+from django.http import HttpResponse
+from django.utils import timezone
+
+from journal.models import SciELOJournal
+
+logger = logging.getLogger(__name__)
+
+HEADERS = ["journals", "scielo_url", "publisher"]
+
+
+def get_scielo_journals_data():
+    try:
+        scielo_journals = SciELOJournal.objects.values(
+            "journal__title",
+            "collection__domain",
+            "journal__owner_history__institution__institution__institution_identification__name",
+            "issn_scielo",
+        )
+
+        formatted_data = []
+        for journal in scielo_journals:
+            title = journal.get("journal__title", "")
+            issn_scielo = journal.get("issn_scielo", "")
+            domain = journal.get("collection__domain", "")
+            owner = journal.get(
+                "journal__owner_history__institution__institution__institution_identification__name",
+                "",
+            )
+            scielo_url = (
+                f"{domain.rstrip('/')}/scielo.php?script=sci_serial&pid={issn_scielo}&lng=en"
+            )
+            formatted_data.append(
+                {
+                    "title": title,
+                    "scielo_url": scielo_url,
+                    "owner": owner,
+                }
+            )
+        return formatted_data
+    except Exception as e:
+        logger.error(f"Error fetching scielo journals data: {e}")
+        return []
+
+
+def generate_csv_response(journals_data):
+    date = timezone.now().strftime("%Y-%m-%d")
+    filename = f"journals_{date}.csv"
+    response = HttpResponse(content_type="text/csv")
+    response["Content-Disposition"] = f'attachment; filename="{filename}"'
+    try:
+        writer = csv.writer(response)
+        writer.writerow(HEADERS)
+        for journal in journals_data:
+            writer.writerow(
+                [journal.get("title"), journal.get("scielo_url"), journal.get("owner")]
+            )
+        logger.info(f"Generated CSV file with: {len(journals_data)} journals")
+    except Exception as e:
+        logger.error(f"Error generating CSV file: {e}")
+        response = HttpResponse("Error generating CSV file", status=500)
+    return response
+
+
+def generate_xls_response(journals_data):
+    date = timezone.now().strftime("%Y-%m-%d")
+    filename = f"journals_{date}.xls"
+    response = HttpResponse(content_type="application/vnd.ms-excel")
+    response["Content-Disposition"] = f'attachment; filename="{filename}"'
+    try:
+        wb = xlwt.Workbook(encoding="utf-8")
+        ws = wb.add_sheet("journals")
+        for col, header in enumerate(HEADERS):
+            ws.write(0, col, header)
+        for row, journal in enumerate(journals_data, start=1):
+            ws.write(row, 0, journal.get("title"))
+            ws.write(row, 1, journal.get("scielo_url"))
+            ws.write(row, 2, journal.get("owner"))
+        wb.save(response)
+        logger.info(f"Generated XLS file with: {len(journals_data)} journals")
+    except Exception as e:
+        logger.error(f"Error generating XLS file: {e}")
+        response = HttpResponse("Error generating XLS file", status=500)
+    return response

core/home/views.py

@@ -1,14 +1,15 @@
-import csv
 import logging
 
 import feedparser
-import xlwt
 from django.http import HttpResponse, JsonResponse
-from django.utils import timezone
 from django.utils.translation import get_language
 from django.views.decorators.http import require_GET
 
-from journal.models import SciELOJournal
+from core.home.utils.export_journals import (
+    generate_csv_response,
+    generate_xls_response,
+    get_scielo_journals_data,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -56,84 +57,11 @@ def youtube_feed_json(request):
     return JsonResponse({"posts": posts})
 
 
-def _get_scielo_journals_data():
-    try:
-        scielo_journals = SciELOJournal.objects.values(
-            "journal__title",
-            "collection__domain",
-            "journal__owner_history__institution__institution__institution_identification__name",
-            "issn_scielo",
-        )
-
-        formatted_data = []
-        for journal in scielo_journals:
-            title = journal.get("journal__title", "")
-            issn_scielo = journal.get("issn_scielo", "")
-            domain = journal.get("collection__domain", "")
-            owner = journal.get(
-                "journal__owner_history__institution__institution__institution_identification__name",
-                "",
-            )
-            scielo_url = (
-                f"{domain.rstrip('/')}/scielo.php?script=sci_serial&pid={issn_scielo}&lng=en"
-            )
-            formatted_data.append(
-                {
-                    "title": title,
-                    "scielo_url": scielo_url,
-                    "owner": owner,
-                }
-            )
-        return formatted_data
-    except Exception as e:
-        logger.error(f"Error fetching scielo journals data: {e}")
-        return []
-
-
 def download_xls_journals_page_scielo_org(request):
-    date = timezone.now().strftime("%Y-%m-%d")
-    filename = f"journals_{date}.xls"
-
-    response = HttpResponse(content_type="application/vnd.ms-excel")
-    response["Content-Disposition"] = f'attachment; filename="{filename}"'
-    try:
-        wb = xlwt.Workbook(encoding="utf-8")
-        ws = wb.add_sheet("journals")
-        headers = ["journals", "scielo_url", "publisher"]
-
-        for col, header in enumerate(headers):
-            ws.write(0, col, header)
-
-        journals_data = _get_scielo_journals_data()
-        for row, journal in enumerate(journals_data, start=1):
-            ws.write(row, 0, journal.get("title"))
-            ws.write(row, 1, journal.get("scielo_url"))
-            ws.write(row, 2, journal.get("owner"))
-        wb.save(response)
-        logger.info(f"Generated XLS file with: {len(journals_data)} journals")
-    except Exception as e:
-        logger.error(f"Error generating XLS file: {e}")
-        response = HttpResponse("Error generating file", status=500)
-    return response
+    journals_data = get_scielo_journals_data()
+    return generate_xls_response(journals_data)
 
 
 def download_csv_journals_page_scielo_org(request):
-    date = timezone.now().strftime("%Y-%m-%d")
-    filename = f"journals_{date}.csv"
-    response = HttpResponse(content_type="text/csv")
-    response["Content-Disposition"] = f'attachment; filename="{filename}"'
-    try:
-        writer = csv.writer(response)
-        headers = ["journals", "scielo_url", "publisher"]
-        writer.writerow(headers)
-        journals_data = _get_scielo_journals_data()
-        for journal in journals_data:
-            writer.writerow(
-                [journal.get("title"), journal.get("scielo_url"), journal.get("owner")]
-            )
-        logger.info(f"Generated CSV file with: {len(journals_data)} journals")
-    except Exception as e:
-        logger.error(f"Error generating CSV file: {e}")
-        response = HttpResponse("Error generating file", status=500)
-
-    return response
+    journals_data = get_scielo_journals_data()
+    return generate_csv_response(journals_data)

core/templates/home/include/download_button_csv_xls.html

@@ -1,13 +1,14 @@
+{% load wagtailroutable_tags %}
 <th class="text-nowrap w-auto" scope="col">
         <button id="btnGroupDropDownload" type="submit" class="btn btn-sm btn-secondary scielo__btn-with-icon--only dropdown-toggle mb-0 float-end d-print-none" data-bs-toggle="dropdown" aria-expanded="false">
             <span class="material-icons-outlined">download</span>
         </button>
         <ul class="dropdown-menu dropdown-menu-end" aria-labelledby="btnGroupDropDownload" >
             <li>
-                <a class="dropdown-item" href="{% url 'download_xls_journals_page_scielo_org' %}">XLS</a>
+                <a class="dropdown-item" href="{% routablepageurl page 'download_xls' %}">XLS</a>
             </li>
             <li>
-                <a class="dropdown-item" href="{% url 'download_csv_journals_page_scielo_org' %}">CSV</a>
+                <a class="dropdown-item" href="{% routablepageurl page 'download_csv' %}">CSV</a>
             </li>
         </ul>
 </th>