summaryrefslogtreecommitdiff
path: root/modules
diff options
context:
space:
mode:
authorPhilipp Tanlak <philipp.tanlak@gmail.com>2025-01-10 13:09:50 +0100
committerGitHub <noreply@github.com>2025-01-10 13:09:50 +0100
commit40e02d5d28e59dbeb6134afdce12536c602e6aa5 (patch)
tree24c84c4084cf72e552804397eecc9f5bb3c2d4be /modules
parentbf99c233a18c3165e0d4d251b41224e5bc6eb93d (diff)
Implement manual following (#82)
Diffstat (limited to 'modules')
-rw-r--r--modules/followlinks/followlinks.go16
-rw-r--r--modules/followlinks/followlinks_test.go40
2 files changed, 49 insertions, 7 deletions
diff --git a/modules/followlinks/followlinks.go b/modules/followlinks/followlinks.go
index c1448be..3ce2797 100644
--- a/modules/followlinks/followlinks.go
+++ b/modules/followlinks/followlinks.go
@@ -18,7 +18,7 @@ func init() {
}
type Module struct {
- Follow []string `json:"follow"`
+ Follow *[]string `json:"follow"`
}
func (Module) ModuleInfo() flyscrape.ModuleInfo {
@@ -29,18 +29,26 @@ func (Module) ModuleInfo() flyscrape.ModuleInfo {
}
func (m *Module) Provision(ctx flyscrape.Context) {
- if len(m.Follow) == 0 {
- m.Follow = []string{"a[href]"}
+ if m.Follow == nil {
+ m.Follow = &[]string{"a[href]"}
}
}
func (m *Module) ReceiveResponse(resp *flyscrape.Response) {
+ if m.Follow == nil {
+ return
+ }
+
for _, link := range m.parseLinks(string(resp.Body), resp.Request.URL) {
resp.Visit(link)
}
}
func (m *Module) parseLinks(html string, origin string) []string {
+ if m.Follow == nil {
+ return nil
+ }
+
var links []string
doc, err := goquery.NewDocumentFromReader(strings.NewReader(html))
if err != nil {
@@ -54,7 +62,7 @@ func (m *Module) parseLinks(html string, origin string) []string {
uniqueLinks := make(map[string]bool)
- for _, selector := range m.Follow {
+ for _, selector := range *m.Follow {
attr := parseSelectorAttr(selector)
doc.Find(selector).Each(func(i int, s *goquery.Selection) {
link, _ := s.Attr(attr)
diff --git a/modules/followlinks/followlinks_test.go b/modules/followlinks/followlinks_test.go
index af186f9..b09b0cd 100644
--- a/modules/followlinks/followlinks_test.go
+++ b/modules/followlinks/followlinks_test.go
@@ -57,7 +57,7 @@ func TestFollowSelector(t *testing.T) {
mods := []flyscrape.Module{
&starturl.Module{URL: "http://www.example.com/foo/bar"},
&followlinks.Module{
- Follow: []string{".next a[href]"},
+ Follow: &[]string{".next a[href]"},
},
hook.Module{
AdaptTransportFn: func(rt http.RoundTripper) http.RoundTripper {
@@ -92,7 +92,7 @@ func TestFollowDataAttr(t *testing.T) {
mods := []flyscrape.Module{
&starturl.Module{URL: "http://www.example.com/foo/bar"},
&followlinks.Module{
- Follow: []string{"[data-url]"},
+ Follow: &[]string{"[data-url]"},
},
hook.Module{
AdaptTransportFn: func(rt http.RoundTripper) http.RoundTripper {
@@ -125,7 +125,7 @@ func TestFollowMultiple(t *testing.T) {
mods := []flyscrape.Module{
&starturl.Module{URL: "http://www.example.com/foo/bar"},
&followlinks.Module{
- Follow: []string{"a.prev", "a.next"},
+ Follow: &[]string{"a.prev", "a.next"},
},
hook.Module{
AdaptTransportFn: func(rt http.RoundTripper) http.RoundTripper {
@@ -151,3 +151,37 @@ func TestFollowMultiple(t *testing.T) {
require.Contains(t, urls, "http://www.example.com/foo/a")
require.Contains(t, urls, "http://www.example.com/foo/b")
}
+
+func TestFollowNoFollow(t *testing.T) {
+ var urls []string
+ var mu sync.Mutex
+
+ mods := []flyscrape.Module{
+ &starturl.Module{URL: "http://www.example.com/foo/bar"},
+ &followlinks.Module{
+ Follow: &[]string{},
+ },
+ hook.Module{
+ AdaptTransportFn: func(rt http.RoundTripper) http.RoundTripper {
+ return flyscrape.MockTransport(200, `
+ <a href="/baz">Baz</a>
+ <a href="baz">Baz</a>
+ <div class="next">
+ <a href="http://www.google.com">Google</a>
+ </div>`)
+ },
+ ReceiveResponseFn: func(r *flyscrape.Response) {
+ mu.Lock()
+ urls = append(urls, r.Request.URL)
+ mu.Unlock()
+ },
+ },
+ }
+
+ scraper := flyscrape.NewScraper()
+ scraper.Modules = mods
+ scraper.Run()
+
+ require.Len(t, urls, 1)
+ require.Contains(t, urls, "http://www.example.com/foo/bar")
+}