Files
comitium/fetch/http.go
T
2021-03-17 09:02:02 -06:00

111 lines
2.6 KiB
Go

// Copyright (C) 2021 nytpu
// SPDX-License-Identifier: AGPL-3.0-or-later
// For more license details, see LICENSE or <https://www.gnu.org/licenses/agpl-3.0.html>.
// This file incorporates code from Drew DeVault's gemreader:
// https://git.sr.ht/~sircmpwn/gemreader/tree/master/item/feeds/fetch.go
// Original source is Copyright 2021 Drew DeVault and is licensed under the
// terms of the GNU Affero General Public License Version 3.0.
// https://www.gnu.org/licenses/agpl-3.0-standalone.html
package fetch
import (
"context"
"crypto/sha256"
"fmt"
"io"
"net/http"
"net/url"
"time"
"github.com/mmcdole/gofeed"
"golang.nytpu.com/comitium/core"
)
// fetchHTTP will make a request for an http resource
func fetchHTTP(remoteURL *url.URL) (*http.Response, error) {
client := &http.Client{
Timeout: 10 * time.Second,
}
req, err := http.NewRequestWithContext(context.Background(), "GET", remoteURL.String(), nil)
req.Header.Add("User-Agent", "comitium (https://git.nytpu.com/comitium/)")
if err != nil {
return nil, err
}
resp, err := client.Do(req)
if err != nil {
return nil, err
}
if resp.StatusCode != 200 {
resp.Body.Close()
return nil, fmt.Errorf("Unexpected HTTP response %s", resp.Status)
}
return resp, nil
}
// newHTTPFeed will fetch and create a new core.Feed given an http url
func newHTTPFeed(remoteURL *url.URL, title string) (*core.Feed, error) {
resp, err := fetchHTTP(remoteURL)
if err != nil {
return nil, err
}
defer resp.Body.Close()
if resp.Header.Get("Content-Type") == "text/html" {
// TODO
return nil, fmt.Errorf("Extracting feed from HTML pages is unimplemented")
}
reader := io.LimitReader(resp.Body, 1073741824) // 1 GiB
data, err := io.ReadAll(reader)
if err != nil {
return nil, err
}
gofeed, err := gofeed.NewParser().Parse(reader)
if err != nil {
return nil, err
}
feed, err := core.GofeedConvert(gofeed, title)
return feed, err
}
// newHTTPPage will create a new core.Page given an http url
func newHTTPPage(remoteURL *url.URL, title string) (*core.Page, error) {
var page core.Page
page.Title = title
page.Link = remoteURL
err := updateHTTPPage(&page)
if err != nil {
return nil, err
}
return &page, nil
}
// updateHTTPPage will check an existing core.Page for changes
func updateHTTPPage(p *core.Page) error {
resp, err := fetchHTTP(p.Link)
if err != nil {
return err
}
defer resp.Body.Close()
reader := io.LimitReader(resp.Body, 1073741824) // 1 GiB
h := sha256.New()
if _, err := io.Copy(h, reader); err != nil {
return err
}
newHash := fmt.Sprintf("%x", h.Sum(nil))
if newHash != p.Hash {
p.Hash = newHash
p.Updated = time.Now()
}
return nil
}