package extractor import ( "context" "fmt" "strings" "testing" ) func TestReadability_ValidHTML(t *testing.T) { html := ` Test Article

Test Article

This is a test article with enough content to be parsed by readability. It needs to have a reasonable amount of text so the algorithm considers it a valid article. Let us add several sentences to make sure this works correctly. The readability library requires a minimum amount of content to successfully extract an article from a page.

Here is another paragraph to add more content. We want to make sure that the content is substantial enough for the readability algorithm to consider this a valid article and extract the text properly.

` doc := mockDocument{ url: "https://example.com/article", content: html, } article, err := Readability(context.Background(), doc) if err != nil { t.Fatalf("Readability() error = %v", err) } if article.Title != "Test Article" { t.Errorf("Title = %q, want %q", article.Title, "Test Article") } if article.TextContent == "" { t.Error("TextContent should not be empty") } } func TestReadability_EmptyContent(t *testing.T) { doc := mockDocument{ url: "https://example.com/empty", content: "", } article, err := Readability(context.Background(), doc) if err != nil { t.Fatalf("Readability() unexpected error = %v", err) } // Empty content should produce an empty article. if article.Title != "" && article.TextContent != "" { t.Error("expected empty article from empty content") } } func TestReadability_InvalidURL(t *testing.T) { doc := mockDocument{ url: "://invalid", content: "

text

", } _, err := Readability(context.Background(), doc) if err == nil { t.Error("Readability() expected error for invalid URL, got nil") } } func TestReadabilityWithOptions_RemoveSelectors(t *testing.T) { html := ` Main Article

Main Article

This is the main article content that we want to extract properly. It contains several sentences about the main topic of interest. The readability algorithm should pick this up as the primary content of the page without any interference from other elements.

Here is a second paragraph with more relevant content about the main topic. This paragraph adds depth and detail to the article.

Unrelated Article

This is content from an unrelated article loaded via infinite scroll. It should not appear in the extracted content because we will remove it using the RemoveSelectors option before readability extraction.

` doc := mockDocument{ url: "https://example.com/article", content: html, } article, err := ReadabilityWithOptions(context.Background(), doc, ReadabilityOptions{ RemoveSelectors: []string{".infinite-scroll", ".sidebar"}, }) if err != nil { t.Fatalf("ReadabilityWithOptions() error = %v", err) } if article.TextContent == "" { t.Fatal("TextContent should not be empty") } if strings.Contains(article.TextContent, "Unrelated Article") { t.Error("TextContent should not contain content from removed .infinite-scroll element") } if strings.Contains(article.TextContent, "Sidebar content") { t.Error("TextContent should not contain content from removed .sidebar element") } if !strings.Contains(article.TextContent, "main article content") { t.Error("TextContent should still contain the main article content") } } func TestReadabilityWithOptions_NoSelectors(t *testing.T) { html := ` Test Article

Test Article

This is a test article with enough content to be parsed by readability. It needs to have a reasonable amount of text so the algorithm considers it a valid article. Let us add several sentences to make sure this works correctly. The readability library requires a minimum amount of content to successfully extract an article from a page.

Here is another paragraph to add more content. We want to make sure that the content is substantial enough for the readability algorithm to consider this a valid article and extract the text properly.

` doc := mockDocument{ url: "https://example.com/article", content: html, } // With empty options, should behave identically to Readability(). article, err := ReadabilityWithOptions(context.Background(), doc, ReadabilityOptions{}) if err != nil { t.Fatalf("ReadabilityWithOptions() error = %v", err) } if article.Title != "Test Article" { t.Errorf("Title = %q, want %q", article.Title, "Test Article") } if article.TextContent == "" { t.Error("TextContent should not be empty") } } func TestRemoveSelectors(t *testing.T) { html := `
Keep this
Remove this
` result, err := removeSelectors(html, []string{".remove"}) if err != nil { t.Fatalf("removeSelectors() error = %v", err) } if strings.Contains(result, "Remove this") { t.Error("result should not contain removed element content") } if !strings.Contains(result, "Keep this") { t.Error("result should still contain kept element content") } } func TestRemoveSelectors_MultipleSelectors(t *testing.T) { html := `
A
B
C
` result, err := removeSelectors(html, []string{".a", ".c"}) if err != nil { t.Fatalf("removeSelectors() error = %v", err) } if strings.Contains(result, ">A<") { t.Error("result should not contain element .a") } if strings.Contains(result, ">C<") { t.Error("result should not contain element .c") } if !strings.Contains(result, ">B<") { t.Error("result should still contain element .b") } } // mockPageEvalDocument is a mock Document that supports PageEvaluate. // The evaluateFn callback simulates JavaScript evaluation by allowing // tests to mutate the document's content field. type mockPageEvalDocument struct { mockDocument evaluateFn func(expression string) (interface{}, error) } func (m *mockPageEvalDocument) PageEvaluate(expression string) (interface{}, error) { if m.evaluateFn != nil { return m.evaluateFn(expression) } return nil, nil } func TestReadabilityWithOptions_RemoveHidden(t *testing.T) { htmlBefore := ` Article With Hidden Honeypot

Real Article

This is the real article content that should be extracted. It contains several sentences about a real topic. The readability algorithm should pick this up as the primary content of the page.

Here is another paragraph with more real content to make the article substantial enough for readability extraction to work properly.

` // After JS evaluation removes display:none elements, the content // should no longer contain the honeypot div. htmlAfter := ` Article With Hidden Honeypot

Real Article

This is the real article content that should be extracted. It contains several sentences about a real topic. The readability algorithm should pick this up as the primary content of the page.

Here is another paragraph with more real content to make the article substantial enough for readability extraction to work properly.

` doc := &mockPageEvalDocument{ mockDocument: mockDocument{ url: "https://example.com/article", content: htmlBefore, }, } doc.evaluateFn = func(expression string) (interface{}, error) { // Simulate the JS removing hidden elements by swapping content. doc.content = htmlAfter return nil, nil } article, err := ReadabilityWithOptions(context.Background(), doc, ReadabilityOptions{ RemoveHidden: true, }) if err != nil { t.Fatalf("ReadabilityWithOptions() error = %v", err) } if strings.Contains(article.TextContent, "step-by-step") { t.Error("TextContent should not contain hidden honeypot content") } if !strings.Contains(article.TextContent, "real article content") { t.Error("TextContent should still contain the real article content") } } func TestReadabilityWithOptions_RemoveHidden_EvaluateError(t *testing.T) { doc := &mockPageEvalDocument{ mockDocument: mockDocument{ url: "https://example.com/article", content: "

text

", }, evaluateFn: func(expression string) (interface{}, error) { return nil, fmt.Errorf("JS evaluation failed") }, } _, err := ReadabilityWithOptions(context.Background(), doc, ReadabilityOptions{ RemoveHidden: true, }) if err == nil { t.Fatal("expected error when PageEvaluate fails, got nil") } if !strings.Contains(err.Error(), "failed to remove hidden elements") { t.Errorf("error = %q, want it to contain %q", err.Error(), "failed to remove hidden elements") } } func TestReadabilityWithOptions_RemoveHidden_UnsupportedDocument(t *testing.T) { // A plain mockDocument does not implement pageEvaluator. doc := mockDocument{ url: "https://example.com/article", content: "

text

", } _, err := ReadabilityWithOptions(context.Background(), doc, ReadabilityOptions{ RemoveHidden: true, }) if err == nil { t.Fatal("expected error when Document does not support PageEvaluate, got nil") } if !strings.Contains(err.Error(), "RemoveHidden requires") { t.Errorf("error = %q, want it to contain %q", err.Error(), "RemoveHidden requires") } }