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
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
|
// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
package scraper // import "miniflux.app/v2/internal/reader/scraper"
import (
"fmt"
"io"
"log/slog"
"strings"
"miniflux.app/v2/internal/config"
"miniflux.app/v2/internal/reader/encoding"
"miniflux.app/v2/internal/reader/fetcher"
"miniflux.app/v2/internal/reader/readability"
"miniflux.app/v2/internal/urllib"
"github.com/PuerkitoBio/goquery"
)
func ScrapeWebsite(requestBuilder *fetcher.RequestBuilder, websiteURL, rules string) (string, error) {
responseHandler := fetcher.NewResponseHandler(requestBuilder.ExecuteRequest(websiteURL))
defer responseHandler.Close()
if localizedError := responseHandler.LocalizedError(); localizedError != nil {
slog.Warn("Unable to scrape website", slog.String("website_url", websiteURL), slog.Any("error", localizedError.Error()))
return "", localizedError.Error()
}
if !isAllowedContentType(responseHandler.ContentType()) {
return "", fmt.Errorf("scraper: this resource is not a HTML document (%s)", responseHandler.ContentType())
}
// The entry URL could redirect somewhere else.
sameSite := urllib.Domain(websiteURL) == urllib.Domain(responseHandler.EffectiveURL())
websiteURL = responseHandler.EffectiveURL()
if rules == "" {
rules = getPredefinedScraperRules(websiteURL)
}
var content string
var err error
htmlDocumentReader, err := encoding.CharsetReaderFromContentType(
responseHandler.ContentType(),
responseHandler.Body(config.Opts.HTTPClientMaxBodySize()),
)
if err != nil {
return "", fmt.Errorf("scraper: unable to read HTML document: %v", err)
}
if sameSite && rules != "" {
slog.Debug("Extracting content with custom rules",
"url", websiteURL,
"rules", rules,
)
content, err = findContentUsingCustomRules(htmlDocumentReader, rules)
} else {
slog.Debug("Extracting content with readability",
"url", websiteURL,
)
content, err = readability.ExtractContent(htmlDocumentReader)
}
if err != nil {
return "", err
}
return content, nil
}
func findContentUsingCustomRules(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
content, _ = goquery.OuterHtml(s)
contents += content
})
return contents, nil
}
func getPredefinedScraperRules(websiteURL string) string {
urlDomain := urllib.Domain(websiteURL)
for domain, rules := range predefinedRules {
if strings.Contains(urlDomain, domain) {
return rules
}
}
return ""
}
func isAllowedContentType(contentType string) bool {
contentType = strings.ToLower(contentType)
return strings.HasPrefix(contentType, "text/html") ||
strings.HasPrefix(contentType, "application/xhtml+xml")
}
|
