Thanks to visit codestin.com
Credit goes to github.com

Skip to content

moving filterings to one function (checkFilters) and use it in case of redirect too #638

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

Merged
WGH- merged 2 commits into from
Feb 1, 2022
Merged

moving filterings to one function (checkFilters) and use it in case of redirect too #638

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
436664e
move filterings to one function (checkFilters) and use it in case of …
joelazar Aug 10, 2021
c5df65c
preserve error message at filtered redirect attempt
joelazar Jan 30, 2022
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
36 changes: 21 additions & 15 deletions colly.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -713,18 +713,8 @@ func (c *Collector) requestCheck(u string, parsedURL *url.URL, method string, re
if c.MaxDepth > 0 && c.MaxDepth < depth {
return ErrMaxDepth
}
if len(c.DisallowedURLFilters) > 0 {
if isMatchingFilter(c.DisallowedURLFilters, []byte(u)) {
return ErrForbiddenURL
}
}
if len(c.URLFilters) > 0 {
if !isMatchingFilter(c.URLFilters, []byte(u)) {
return ErrNoURLFiltersMatch
}
}
if !c.isDomainAllowed(parsedURL.Hostname()) {
return ErrForbiddenDomain
if err := c.checkFilters(u, parsedURL.Hostname()); err != nil {
return err
}
if method != "HEAD" && !c.IgnoreRobotsTxt {
if err := c.checkRobots(parsedURL); err != nil {
Expand Down Expand Up @@ -757,6 +747,23 @@ func (c *Collector) requestCheck(u string, parsedURL *url.URL, method string, re
return nil
}

func (c *Collector) checkFilters(URL, domain string) error {
if len(c.DisallowedURLFilters) > 0 {
if isMatchingFilter(c.DisallowedURLFilters, []byte(URL)) {
return ErrForbiddenURL
}
}
if len(c.URLFilters) > 0 {
if !isMatchingFilter(c.URLFilters, []byte(URL)) {
return ErrNoURLFiltersMatch
}
}
if !c.isDomainAllowed(domain) {
return ErrForbiddenDomain
}
return nil
}

func (c *Collector) isDomainAllowed(domain string) bool {
for _, d2 := range c.DisallowedDomains {
if d2 == domain {
Expand Down Expand Up @@ -1285,10 +1292,9 @@ func (c *Collector) Clone() *Collector {

func (c *Collector) checkRedirectFunc() func(req *http.Request, via []*http.Request) error {
return func(req *http.Request, via []*http.Request) error {
if !c.isDomainAllowed(req.URL.Hostname()) {
return fmt.Errorf("Not following redirect to %s because its not in AllowedDomains", req.URL.Host)
if err := c.checkFilters(req.URL.String(), req.URL.Hostname()); err != nil {
return fmt.Errorf("Not following redirect to %q: %w", req.URL, err)
}

if c.redirectHandler != nil {
return c.redirectHandler(req, via)
}
Expand Down
18 changes: 18 additions & 0 deletions colly_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ import (
"bufio"
"bytes"
"context"
"errors"
"fmt"
"net/http"
"net/http/httptest"
Expand Down Expand Up @@ -804,6 +805,23 @@ func TestRedirect(t *testing.T) {
c.Visit(ts.URL + "/redirect")
}

func TestRedirectWithDisallowedURLs(t *testing.T) {
ts := newTestServer()
defer ts.Close()

c := NewCollector()
c.DisallowedURLFilters = []*regexp.Regexp{regexp.MustCompile(ts.URL + "/redirected/test")}
c.OnHTML("a[href]", func(e *HTMLElement) {
u := e.Request.AbsoluteURL(e.Attr("href"))
err := c.Visit(u)
if !errors.Is(err, ErrForbiddenURL) {
t.Error("URL should have been forbidden: " + u)
}
})

c.Visit(ts.URL + "/redirect")
}

func TestBaseTag(t *testing.T) {
ts := newTestServer()
defer ts.Close()
Expand Down