Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix data URLs with spaces #349

Merged
merged 7 commits into from
Nov 25, 2023
Merged

Fix data URLs with spaces #349

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
8e90394
Remove whitespace from URLs
raviqqe Nov 25, 2023
3b9bbb1
Fix
raviqqe Nov 25, 2023
521ae6a
Fix
raviqqe Nov 25, 2023
1c74d88
Fix
raviqqe Nov 25, 2023
15fe6c9
Fix
raviqqe Nov 25, 2023
3820491
Fix
raviqqe Nov 25, 2023
b40f6ae
Fix
raviqqe Nov 25, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 21 additions & 4 deletions link_finder.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ import (
"net/url"
"regexp"
"strings"
"unicode"

"github.com/yhat/scrape"
"golang.org/x/net/html"
Expand All @@ -22,7 +23,7 @@ var atomToAttributes = map[atom.Atom][]string{
atom.Meta: {"content"},
}

var imageDescriptorPattern = regexp.MustCompile(" [^ ]*$")
var imageDescriptorPattern = regexp.MustCompile(`(\S)\s+\S+\s*$`)

type linkFinder struct {
linkFilterer linkFilterer
Expand All @@ -43,7 +44,7 @@ func (f linkFinder) Find(n *html.Node, base *url.URL) map[string]error {
ss := f.parseLinks(n, a)

for _, s := range ss {
s := strings.TrimSpace(s)
s := f.trimUrl(s)

if s == "" {
continue
Expand All @@ -67,14 +68,14 @@ func (f linkFinder) Find(n *html.Node, base *url.URL) map[string]error {
return ls
}

func (linkFinder) parseLinks(n *html.Node, a string) []string {
func (f linkFinder) parseLinks(n *html.Node, a string) []string {
s := scrape.Attr(n, a)
ss := []string{}

switch a {
case "srcset":
for _, s := range strings.Split(s, ",") {
ss = append(ss, imageDescriptorPattern.ReplaceAllString(strings.TrimSpace(s), ""))
ss = append(ss, f.trimUrl(imageDescriptorPattern.ReplaceAllString(s, "$1")))
}
case "content":
switch scrape.Attr(n, "property") {
Expand All @@ -87,3 +88,19 @@ func (linkFinder) parseLinks(n *html.Node, a string) []string {

return ss
}

func (linkFinder) trimUrl(s string) string {
s = strings.TrimSpace(s)

if !strings.HasPrefix(s, "data:") {
return s
}

return strings.Map(func(r rune) rune {
if unicode.IsSpace(r) {
return -1
}

return r
}, s)
}
14 changes: 14 additions & 0 deletions link_finder_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -189,6 +189,20 @@ func TestLinkFinderFindMetaTags(t *testing.T) {
assert.Nil(t, err)
}

func TestLinkFinderFindDataSchemeLinkWithSpaces(t *testing.T) {
b, err := url.Parse("http://foo.com")
assert.Nil(t, err)

n, err := html.Parse(strings.NewReader(
htmlWithBody(`<a href="data:text/plain, Hello,%20world! " />`)),
)
assert.Nil(t, err)

ls := newTestLinkFinder().Find(n, b)

assert.Len(t, ls, 0)
}

func TestLinkFinderIgnoreMetaTags(t *testing.T) {
b, err := url.Parse("http://foo.com")
assert.Nil(t, err)
Expand Down
Loading