From 08df9258a532b653c243e077e82491dbe62ad854 Mon Sep 17 00:00:00 2001
From: Philipp Tanlak <philipp.tanlak@gmail.com>
Date: Sat, 23 Sep 2023 17:41:57 +0200
Subject: refactor scraper into modules

---
 modules/domainfilter/domainfilter.go      | 62 +++++++++++++++++++++
 modules/domainfilter/domainfilter_test.go | 92 +++++++++++++++++++++++++++++++
 2 files changed, 154 insertions(+)
 create mode 100644 modules/domainfilter/domainfilter.go
 create mode 100644 modules/domainfilter/domainfilter_test.go

(limited to 'modules/domainfilter')

diff --git a/modules/domainfilter/domainfilter.go b/modules/domainfilter/domainfilter.go
new file mode 100644
index 0000000..b892882
--- /dev/null
+++ b/modules/domainfilter/domainfilter.go
@@ -0,0 +1,62 @@
+// This Source Code Form is subject to the terms of the Mozilla Public
+// License, v. 2.0. If a copy of the MPL was not distributed with this
+// file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+package domainfilter
+
+import (
+	"github.com/nlnwa/whatwg-url/url"
+	"github.com/philippta/flyscrape"
+)
+
+func init() {
+	flyscrape.RegisterModule(new(Module))
+}
+
+type Module struct {
+	URL            string   `json:"url"`
+	AllowedDomains []string `json:"allowedDomains"`
+	BlockedDomains []string `json:"blockedDomains"`
+}
+
+func (m *Module) ID() string {
+	return "domainfilter"
+}
+
+func (m *Module) OnLoad(v flyscrape.Visitor) {
+	if u, err := url.Parse(m.URL); err == nil {
+		m.AllowedDomains = append(m.AllowedDomains, u.Host())
+	}
+}
+
+func (m *Module) CanRequest(rawurl string, depth int) bool {
+	u, err := url.Parse(rawurl)
+	if err != nil {
+		return false
+	}
+
+	host := u.Host()
+	ok := false
+
+	for _, domain := range m.AllowedDomains {
+		if domain == "*" || host == domain {
+			ok = true
+			break
+		}
+	}
+
+	for _, domain := range m.BlockedDomains {
+		if host == domain {
+			ok = false
+			break
+		}
+	}
+
+	return ok
+}
+
+var (
+	_ flyscrape.Module     = (*Module)(nil)
+	_ flyscrape.CanRequest = (*Module)(nil)
+	_ flyscrape.OnLoad     = (*Module)(nil)
+)
diff --git a/modules/domainfilter/domainfilter_test.go b/modules/domainfilter/domainfilter_test.go
new file mode 100644
index 0000000..97bdc9c
--- /dev/null
+++ b/modules/domainfilter/domainfilter_test.go
@@ -0,0 +1,92 @@
+// This Source Code Form is subject to the terms of the Mozilla Public
+// License, v. 2.0. If a copy of the MPL was not distributed with this
+// file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+package domainfilter_test
+
+import (
+	"testing"
+
+	"github.com/philippta/flyscrape"
+	"github.com/philippta/flyscrape/modules/domainfilter"
+	"github.com/philippta/flyscrape/modules/followlinks"
+	"github.com/philippta/flyscrape/modules/starturl"
+	"github.com/stretchr/testify/require"
+)
+
+func TestDomainfilterAllowed(t *testing.T) {
+	scraper := flyscrape.NewScraper()
+	scraper.LoadModule(&starturl.Module{URL: "http://www.example.com"})
+	scraper.LoadModule(&followlinks.Module{})
+	scraper.LoadModule(&domainfilter.Module{
+		URL:            "http://www.example.com",
+		AllowedDomains: []string{"www.google.com"},
+	})
+
+	scraper.SetTransport(flyscrape.MockTransport(200, `
+        <a href="http://www.google.com">Google</a>
+        <a href="http://www.duckduckgo.com">DuckDuckGo</a>`))
+
+	var urls []string
+	scraper.OnRequest(func(req *flyscrape.Request) {
+		urls = append(urls, req.URL)
+	})
+
+	scraper.Run()
+
+	require.Len(t, urls, 2)
+	require.Contains(t, urls, "http://www.example.com")
+	require.Contains(t, urls, "http://www.google.com/")
+}
+
+func TestDomainfilterAllowedAll(t *testing.T) {
+	scraper := flyscrape.NewScraper()
+	scraper.LoadModule(&starturl.Module{URL: "http://www.example.com"})
+	scraper.LoadModule(&followlinks.Module{})
+	scraper.LoadModule(&domainfilter.Module{
+		URL:            "http://www.example.com",
+		AllowedDomains: []string{"*"},
+	})
+
+	scraper.SetTransport(flyscrape.MockTransport(200, `
+        <a href="http://www.google.com">Google</a>
+        <a href="http://www.duckduckgo.com">DuckDuckGo</a>`))
+
+	var urls []string
+	scraper.OnRequest(func(req *flyscrape.Request) {
+		urls = append(urls, req.URL)
+	})
+
+	scraper.Run()
+
+	require.Len(t, urls, 3)
+	require.Contains(t, urls, "http://www.example.com")
+	require.Contains(t, urls, "http://www.duckduckgo.com/")
+	require.Contains(t, urls, "http://www.google.com/")
+}
+
+func TestDomainfilterBlocked(t *testing.T) {
+	scraper := flyscrape.NewScraper()
+	scraper.LoadModule(&starturl.Module{URL: "http://www.example.com"})
+	scraper.LoadModule(&followlinks.Module{})
+	scraper.LoadModule(&domainfilter.Module{
+		URL:            "http://www.example.com",
+		AllowedDomains: []string{"*"},
+		BlockedDomains: []string{"www.google.com"},
+	})
+
+	scraper.SetTransport(flyscrape.MockTransport(200, `
+        <a href="http://www.google.com">Google</a>
+        <a href="http://www.duckduckgo.com">DuckDuckGo</a>`))
+
+	var urls []string
+	scraper.OnRequest(func(req *flyscrape.Request) {
+		urls = append(urls, req.URL)
+	})
+
+	scraper.Run()
+
+	require.Len(t, urls, 2)
+	require.Contains(t, urls, "http://www.example.com")
+	require.Contains(t, urls, "http://www.duckduckgo.com/")
+}
-- 
cgit v1.2.3