miniflux/ui/entry_scraper.go

52 lines
1.2 KiB
Go
Raw Normal View History

// 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.
2018-08-25 06:51:50 +02:00
package ui // import "miniflux.app/ui"
import (
"errors"
"net/http"
2018-08-25 06:51:50 +02:00
"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
}
2018-09-03 23:26:40 +02:00
builder := c.store.NewEntryQueryBuilder(request.UserID(r))
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})
}