From 07d85c0bfc82b5df7366d3810c95aa8b959837a4 Mon Sep 17 00:00:00 2001
From: nytpu <alex@nytpu.com>
Date: Tue, 16 Mar 2021 22:43:18 -0600
Subject: implement New* routines for fetching and creating new feeds/pages.

Also includes routines for fetching gemini, http, and gopher resources.

TODO: add Update* routines to update existing feeds/pages.
---
 fetch/http.go | 99 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 99 insertions(+)
 create mode 100644 fetch/http.go

(limited to 'fetch/http.go')

diff --git a/fetch/http.go b/fetch/http.go
new file mode 100644
index 0000000..fb373e6
--- /dev/null
+++ b/fetch/http.go
@@ -0,0 +1,99 @@
+// 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) {
+	resp, err := fetchHTTP(remoteURL)
+	if err != nil {
+		return nil, err
+	}
+	defer resp.Body.Close()
+
+	reader := io.LimitReader(resp.Body, 1073741824) // 1 GiB
+
+	var page core.Page
+	page.Title = title
+	page.Link = remoteURL
+	page.Updated = time.Now()
+
+	h := sha256.New()
+	if _, err := io.Copy(h, reader); err != nil {
+		return nil, err
+	}
+	page.Hash = fmt.Sprintf("%x", h.Sum(nil))
+
+	return &page, nil
+}
-- 
cgit v1.2.3