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

Copy the headers from the last request on redirect #24

Merged
merged 4 commits into from
Oct 13, 2017
Merged

Copy the headers from the last request on redirect #24

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
2ed9c50
Copy the headers from the last request on redirect
gummiboll Oct 12, 2017
4cefa8a
Don't follow redirect if domain is not in AllowedDomains
gummiboll Oct 13, 2017
bcf9e50
Removes the Authorization header if it exists and host has changed af…
gummiboll Oct 13, 2017
928ff10
Removes accidental newline
gummiboll Oct 13, 2017
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
27 changes: 27 additions & 0 deletions colly.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ package colly
import (
"bytes"
"errors"
"fmt"
"io"
"io/ioutil"
"net/http"
Expand Down Expand Up @@ -130,6 +131,7 @@ func (c *Collector) Init() {
c.MaxBodySize = 10 * 1024 * 1024
c.backend = &httpBackend{}
c.backend.Init()
c.backend.Client.CheckRedirect = c.checkRedirectFunc()
c.wg = &sync.WaitGroup{}
c.lock = &sync.Mutex{}
}
Expand Down Expand Up @@ -356,6 +358,31 @@ func (c *Collector) Cookies(URL string) []*http.Cookie {
return c.backend.Client.Jar.Cookies(u)
}

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.Host) {
return fmt.Errorf("Not following redirect to %s because its not in AllowedDomains", req.URL.Host)
}

// Honor golangs default of maximum of 10 redirects
if len(via) >= 10 {
return http.ErrUseLastResponse
}

lastRequest := via[len(via)-1]

// Copy the headers from last request
req.Header = lastRequest.Header

// If domain has changed, remove the Authorization-header if it exists
if req.URL.Host != lastRequest.URL.Host {
req.Header.Del("Authorization")
}

return nil
}
}

// Attr returns the selected attribute of a HTMLElement or empty string
// if no attribute found
func (h *HTMLElement) Attr(k string) string {
Expand Down