From 40e02d5d28e59dbeb6134afdce12536c602e6aa5 Mon Sep 17 00:00:00 2001 From: Philipp Tanlak Date: Fri, 10 Jan 2025 13:09:50 +0100 Subject: Implement manual following (#82) --- modules/followlinks/followlinks.go | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'modules/followlinks/followlinks.go') 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) -- cgit v1.2.3