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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
|
// Copyright 2017 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 scraper
import (
"errors"
"io"
"log"
"strings"
"github.com/PuerkitoBio/goquery"
"github.com/miniflux/miniflux/http"
"github.com/miniflux/miniflux/reader/readability"
"github.com/miniflux/miniflux/url"
)
// Fetch download a web page a returns relevant contents.
func Fetch(websiteURL, rules string) (string, error) {
client := http.NewClient(websiteURL)
response, err := client.Get()
if err != nil {
return "", err
}
if response.HasServerFailure() {
return "", errors.New("unable to download web page")
}
page, err := response.NormalizeBodyEncoding()
if err != nil {
return "", err
}
if rules == "" {
rules = getPredefinedScraperRules(websiteURL)
}
var content string
if rules != "" {
log.Printf(`[Scraper] Using rules "%s" for "%s"`, rules, websiteURL)
content, err = scrapContent(page, rules)
} else {
log.Printf(`[Scraper] Using readability for "%s"`, websiteURL)
content, err = readability.ExtractContent(page)
}
if err != nil {
return "", err
}
return content, nil
}
func scrapContent(page io.Reader, rules string) (string, error) {
document, err := goquery.NewDocumentFromReader(page)
if err != nil {
return "", err
}
contents := ""
document.Find(rules).Each(func(i int, s *goquery.Selection) {
var content string
// For some inline elements, we get the parent.
if s.Is("img") {
content, _ = s.Parent().Html()
} else {
content, _ = s.Html()
}
contents += content
})
return contents, nil
}
func getPredefinedScraperRules(websiteURL string) string {
urlDomain := url.Domain(websiteURL)
for domain, rules := range predefinedRules {
if strings.Contains(urlDomain, domain) {
return rules
}
}
return ""
}
|
