fixed tests _ all pass

Author: petermr

docs/scielo/test_article_page.py

@@ -68,10 +68,11 @@ def test_article_page():
             json.dump(metadata, f, indent=2)
         print(f"Saved metadata to: {output_dir / 'test_article_metadata.json'}")
 
-        return metadata, download_links
+        assert metadata is not None, "Metadata should be extracted"
+        assert isinstance(download_links, list), "Download links should be a list"
+        assert response.status_code == 200, f"Expected status 200, got {response.status_code}"
     else:
-        print(f"Failed to access article page: {response.status_code}")
-        return None, []
+        assert False, f"Failed to access article page: {response.status_code}"
 
 
 def extract_article_metadata(soup, url):

docs/scielo/test_scielo_basic.py

@@ -48,59 +48,46 @@ def test_scielo_basic():
             logger.warning("❌ No articles found")
 
     except Exception as e:
-        logger.error(f"❌ Test 1 failed: {e}")
-        return False
+        assert False, f"Test 1 failed: {e}"
 
     # Test 2: Main scielo method
     logger.info("Test 2: Main scielo method with CSV output")
-    try:
-        results = scielo.scielo(
-            query="climate change", cutoff_size=2, makecsv=True, makehtml=True
-        )
-        logger.info(
-            f"✅ Main method completed. Found {results['total_results']} articles"
-        )
-        logger.info(f"✅ Generated CSV and HTML outputs")
-
-    except Exception as e:
-        logger.error(f"❌ Test 2 failed: {e}")
-        return False
+    results = scielo.scielo(
+        query="climate change", cutoff_size=2, makecsv=True, makehtml=True
+    )
+    assert isinstance(results, dict), "Results should be a dictionary"
+    assert "total_results" in results, "Results should contain total_results"
+    logger.info(
+        f"✅ Main method completed. Found {results['total_results']} articles"
+    )
+    logger.info(f"✅ Generated CSV and HTML outputs")
 
     # Test 3: Noexecute method
     logger.info("Test 3: Noexecute method")
-    try:
-        query_namespace = {"query": "climate change", "limit": 2}
-        scielo.noexecute(query_namespace)
-        logger.info("✅ Noexecute method completed")
-
-    except Exception as e:
-        logger.error(f"❌ Test 3 failed: {e}")
-        return False
+    query_namespace = {"query": "climate change", "limit": 2}
+    assert hasattr(scielo, "noexecute"), "SciELO should have noexecute method"
+    scielo.noexecute(query_namespace)
+    logger.info("✅ Noexecute method completed")
 
     # Test 4: Article download
     logger.info("Test 4: Article download")
-    try:
-        if articles:
-            # Download first article
-            first_article_url = articles[0].get("url")
-            if first_article_url:
-                output_dir = "temp/scielo_test_downloads"
-                success = scielo.download_article(first_article_url, output_dir)
-                if success:
-                    logger.info(f"✅ Article downloaded to {output_dir}")
-                else:
-                    logger.warning("⚠️ Article download failed")
+    if articles:
+        # Download first article
+        first_article_url = articles[0].get("url")
+        if first_article_url:
+            output_dir = "temp/scielo_test_downloads"
+            assert hasattr(scielo, "download_article"), "SciELO should have download_article method"
+            success = scielo.download_article(first_article_url, output_dir)
+            if success:
+                logger.info(f"✅ Article downloaded to {output_dir}")
             else:
-                logger.warning("⚠️ No article URL available for download test")
+                logger.warning("⚠️ Article download failed")
         else:
-            logger.warning("⚠️ No articles available for download test")
-
-    except Exception as e:
-        logger.error(f"❌ Test 4 failed: {e}")
-        return False
+            logger.warning("⚠️ No article URL available for download test")
+    else:
+        logger.warning("⚠️ No articles available for download test")
 
     logger.info("=== All Basic Tests Completed ===")
-    return True
 
 
 def test_scielo_metadata_extraction():
@@ -127,15 +114,14 @@ def test_scielo_metadata_extraction():
             logger.info(f"  DOI: {metadata.get('doi', 'No DOI')}")
             logger.info(f"  PDF URLs: {len(metadata.get('pdf_urls', []))}")
             logger.info(f"  Collection: {metadata.get('collection', 'Unknown')}")
-
-            return True
+            
+            assert metadata is not None, "Metadata should be extracted"
+            assert isinstance(metadata, dict), "Metadata should be a dictionary"
         else:
-            logger.error("❌ Failed to get article page")
-            return False
+            assert False, "Failed to get article page"
 
     except Exception as e:
-        logger.error(f"❌ Metadata extraction test failed: {e}")
-        return False
+        assert False, f"Metadata extraction test failed: {e}"
 
 
 def main():

docs/test-repos-config-guide.md

@@ -0,0 +1,157 @@
+# Repository Test Skipping Configuration Guide
+
+## Overview
+
+Repository-specific tests can be skipped using a configuration file (`tests/test_repos_config.ini`). This allows you to control which repository tests run without modifying code or command-line arguments.
+
+## Configuration File
+
+**Location**: `tests/test_repos_config.ini`
+
+**Format**:
+```ini
+[test_repositories]
+# Set to 'true' or '1' to skip tests for that repository
+# Set to 'false' or '0' to run tests for that repository
+
+skip_redalyc = true
+skip_scielo = true
+skip_biorxiv = true
+```
+
+## Priority Order
+
+Settings are applied in this order (later settings override earlier ones):
+
+1. **Config file** (`test_repos_config.ini`) - Default/base settings
+2. **Pytest markers** (`-m "not redalyc"`) - Command-line filtering
+
+## Usage Examples
+
+### Using Config File Only
+
+Edit `tests/test_repos_config.ini`:
+```ini
+[test_repositories]
+skip_redalyc = true
+skip_scielo = true
+skip_biorxiv = false  # Run BioRxiv tests
+```
+
+Then run:
+```bash
+pytest  # Automatically skips Redalyc and SciELO, runs BioRxiv
+```
+
+### Override with Pytest Markers
+
+```bash
+# Config file settings + marker filtering
+pytest -m "not redalyc"  # Skips Redalyc (even if config says run)
+```
+
+## Common Scenarios
+
+### Scenario 1: Skip All Repository Tests (Default)
+
+```ini
+[test_repositories]
+skip_redalyc = true
+skip_scielo = true
+skip_biorxiv = true
+```
+
+```bash
+pytest  # Only runs core tests
+```
+
+### Scenario 2: Run Only One Repository
+
+```ini
+[test_repositories]
+skip_redalyc = true
+skip_scielo = true
+skip_biorxiv = false  # Only run BioRxiv tests
+```
+
+```bash
+pytest  # Runs BioRxiv tests only
+```
+
+### Scenario 3: Run Specific Repository Tests
+
+Use pytest markers to run only specific repository tests:
+
+```bash
+# Run only Redalyc tests (ignores config file)
+pytest -m redalyc
+
+# Run only SciELO tests
+pytest -m scielo
+
+# Run all repository tests
+pytest -m "redalyc or scielo or biorxiv"
+```
+
+## Editing the Config File
+
+The config file uses standard INI format:
+
+```ini
+[test_repositories]
+# Boolean values: true, false, 1, 0, yes, no
+skip_redalyc = true
+skip_scielo = false
+skip_biorxiv = 1  # Also accepts 1/0
+```
+
+**Valid values for `true`**: `true`, `1`, `yes`  
+**Valid values for `false`**: `false`, `0`, `no`
+
+## Default Configuration
+
+By default, all repository tests are **skipped**:
+- `skip_redalyc = true`
+- `skip_scielo = true`
+- `skip_biorxiv = true`
+
+This ensures fast test runs without external dependencies.
+
+## Enabling Repository Tests
+
+To enable repository tests, edit `tests/test_repos_config.ini`:
+
+```ini
+[test_repositories]
+skip_redalyc = false  # Enable Redalyc tests
+skip_scielo = false   # Enable SciELO tests
+skip_biorxiv = false  # Enable BioRxiv tests
+```
+
+Or use pytest markers to override config file settings:
+```bash
+# Run Redalyc tests even if config says skip
+pytest -m redalyc
+
+# Run all repository tests
+pytest -m "redalyc or scielo or biorxiv"
+```
+
+## Verification
+
+Check which tests will be skipped:
+```bash
+# Show what will be skipped
+pytest --collect-only | grep -i "skip"
+
+# Test with config
+pytest --collect-only -q | head -20
+```
+
+## File Location
+
+The config file is located at:
+- **Path**: `tests/test_repos_config.ini`
+- **Relative to project root**: `tests/test_repos_config.ini`
+
+If the file doesn't exist, defaults are used (all repositories enabled for testing).