aboutsummaryrefslogtreecommitdiffstats
path: root/crawler/crawler.go
blob: a29f81414708818baf0dd050a6dfd11d6731d3b6 (plain) (blame)
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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
package crawler

import (
	"adammathes.com/neko/models/feed"
	"adammathes.com/neko/models/item"
	"adammathes.com/neko/vlog"
	"github.com/mmcdole/gofeed"
	"io/ioutil"
	"log"
	"net/http"
	"time"
)

func Crawl() {

	ch := make(chan string)

	feeds, err := feed.All()
	if err != nil {
		log.Fatal(err)
	}
	for _, f := range feeds {
		vlog.Printf("crawling %s\n", f.Url)
		go CrawlFeed(f, ch)
	}

	for i := 0; i < len(feeds); i++ {
		vlog.Println(<-ch)
	}
}

/*
Simple HTTP Get fnx with custom user agent header
*/
func GetFeedContent(feedURL string) string {

	c := &http.Client{
		// give up after 5 seconds
		Timeout: 5 * time.Second,
	}

	request, err := http.NewRequest("GET", feedURL, nil)
	if err != nil {
		log.Fatalln(err)
	}

	userAgent := "neko RSS Crawler +https://github.com/adammathes/neko"
	request.Header.Set("User-Agent", userAgent)
	resp, err := c.Do(request)

	if err != nil {
		return ""
	}

	if resp != nil {
		defer func() {
			ce := resp.Body.Close()
			if ce != nil {
				err = ce
			}
		}()
	}

	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
		return ""
	}

	bodyBytes, err := ioutil.ReadAll(resp.Body)
	if err != nil {
		return ""
	}
	return string(bodyBytes)
}

/*
 TODO: sanitize input on crawl
*/
func CrawlFeed(f *feed.Feed, ch chan<- string) {
	c := &http.Client{
		// give up after 5 seconds
		Timeout: 5 * time.Second,
	}

	fp := gofeed.NewParser()
	fp.Client = c

	content := GetFeedContent(f.Url)
	feed, err := fp.ParseString(content)
	if err != nil {
		vlog.Println(err)
		ch <- "failed to fetch and parse for " + f.Url + "\n"
		return
	}

	f.Title = feed.Title
	f.WebUrl = feed.Link
	f.Update()

	for _, i := range feed.Items {
		vlog.Printf("storing item: %s", i.Link)
		var item item.Item
		item.Title = i.Title
		item.Url = i.Link

		item.Description = i.Description
		if len(i.Content) > len(item.Description) {
			item.Description = i.Content
		}

		// a lot of RSS2.0 generated by wordpress and others
		// uses <content:encoded>
		e, ok := i.Extensions["content"]["encoded"]
		var encoded = ""
		if ok {
			encoded = e[0].Value
		}
		if len(encoded) > len(item.Description) {
			item.Description = encoded
		}

		if i.PublishedParsed != nil {
			item.PublishDate = i.PublishedParsed.Format("2006-01-02 15:04:05")
		} else {
			item.PublishDate = time.Now().Format("2006-01-02 15:04:05")
		}

		item.FeedId = f.Id
		err := item.Create()
		if err != nil {
			vlog.Println(err)
		}
		// else {
		//	item.GetFullContent()
		//}
	}
	ch <- "successfully crawled " + f.Url + "\n"
}