aboutsummaryrefslogtreecommitdiffhomepage
path: root/ui/entry_scraper.go
blob: 52e084679077e8458937755a145a82ab6d8de3e8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
// Copyright 2018 Frédéric Guillot. All rights reserved.
// Use of this source code is governed by the Apache 2.0
// license that can be found in the LICENSE file.

package ui  // import "miniflux.app/ui"

import (
	"errors"
	"net/http"

	"miniflux.app/http/context"
	"miniflux.app/http/request"
	"miniflux.app/http/response/json"
	"miniflux.app/model"
	"miniflux.app/reader/sanitizer"
	"miniflux.app/reader/scraper"
)

// FetchContent downloads the original HTML page and returns relevant contents.
func (c *Controller) FetchContent(w http.ResponseWriter, r *http.Request) {
	entryID, err := request.IntParam(r, "entryID")
	if err != nil {
		json.BadRequest(w, err)
		return
	}

	ctx := context.New(r)
	builder := c.store.NewEntryQueryBuilder(ctx.UserID())
	builder.WithEntryID(entryID)
	builder.WithoutStatus(model.EntryStatusRemoved)

	entry, err := builder.GetEntry()
	if err != nil {
		json.ServerError(w, err)
		return
	}

	if entry == nil {
		json.NotFound(w, errors.New("Entry not found"))
		return
	}

	content, err := scraper.Fetch(entry.URL, entry.Feed.ScraperRules)
	if err != nil {
		json.ServerError(w, err)
		return
	}

	entry.Content = sanitizer.Sanitize(entry.URL, content)
	c.store.UpdateEntryContent(entry)

	json.OK(w, r, map[string]string{"content": entry.Content})
}