Find feed url from webpage

This commit is contained in:
Marcus Noble 2021-03-17 08:02:14 +00:00
parent 47c72d0029
commit 42014bdaa1
5 changed files with 63 additions and 8 deletions

1
go.mod
View File

@ -3,6 +3,7 @@ module github.com/averagemarcus/gopherss
go 1.15
require (
github.com/PuerkitoBio/goquery v1.5.1
github.com/dustin/go-humanize v1.0.0
github.com/gofiber/fiber/v2 v2.0.6
github.com/gofiber/template v1.6.3

9
go.sum
View File

@ -140,6 +140,7 @@ github.com/google/uuid v1.0.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+
github.com/googleapis/gax-go/v2 v2.0.4/go.mod h1:0Wqv26UfaUD9n4G6kQubkQ+KchISgw+vpHVxEJEs9eg=
github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=
github.com/gookit/color v1.2.4/go.mod h1:AhIE+pS6D4Ql0SQWbBeXPHw7gY0/sjHoA4s/n1KB7xg=
github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1 h1:EGx4pi6eqNxGaHF6qqu48+N2wcFQ5qg5FXgOdqsJ5d8=
github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
github.com/gorilla/websocket v1.4.0/go.mod h1:E7qHFY5m1UJ88s3WnNqhKjPHQ0heANvMoAMk2YaljkQ=
github.com/gorilla/websocket v1.4.2/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
@ -185,6 +186,7 @@ github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCV
github.com/json-iterator/go v1.1.10 h1:Kz6Cvnvv2wGdaG/V8yMvfkmNiXq9Ya2KUv4rouJJr68=
github.com/json-iterator/go v1.1.10/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
github.com/jstemmer/go-junit-report v0.0.0-20190106144839-af01ea7f8024/go.mod h1:6v2b51hI/fHJwM22ozAgKL4VKDeJcHhJFhtBdhmNjmU=
github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
github.com/kisielk/errcheck v1.1.0/go.mod h1:EZBBE59ingxPouuu3KfxchcWSUPOHkagtvWXihfKN4Q=
@ -201,6 +203,7 @@ github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORN
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/kyoh86/exportloopref v0.1.4/go.mod h1:h1rDl2Kdj97+Kwh4gdz3ujE7XHmH51Q0lUiZ1z4NLj8=
github.com/lib/pq v1.0.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
@ -252,6 +255,7 @@ github.com/mozilla/tls-observatory v0.0.0-20200317151703-4fa42e1c2dee/go.mod h1:
github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
github.com/nakabonne/nestif v0.3.0/go.mod h1:dI314BppzXjJ4HsCnbo7XzrJHPszZsjnk5wEBSYHI2c=
github.com/nbutton23/zxcvbn-go v0.0.0-20180912185939-ae427f1e4c1d/go.mod h1:o96djdrsSGy3AWPyBgZMAGfxZNfgntdJG+11KU4QvbU=
github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e h1:fD57ERR4JtEqsWbfPhv4DMiApHyliiK5xCTNVSPiaAs=
github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
github.com/nishanths/exhaustive v0.0.0-20200525081945-8e46705b6132/go.mod h1:wBEpHwM2OdmeNpdCvRPUlkEbBuaFmcK4Wv8Q7FuGW3c=
github.com/oklog/ulid v1.3.1/go.mod h1:CirwcVhetQ6Lv90oh/F+FBtV6XMibvdAFo93nm5qn4U=
@ -298,7 +302,9 @@ github.com/shurcooL/go-goon v0.0.0-20170922171312-37c2f522c041/go.mod h1:N5mDOms
github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
github.com/sirupsen/logrus v1.6.0/go.mod h1:7uNnSEd1DgxDLC74fIahvMZmmYsHGZGEOFrfsX/uA88=
github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d h1:zE9ykElWQ6/NYmHa3jpm/yHnI4xSofP+UP6SpjHcSeM=
github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d/go.mod h1:OnSkiWE9lh6wB0YB77sQom3nweQdgAjqCqsofrRNTgc=
github.com/smartystreets/goconvey v1.6.4 h1:fv0U8FUIMPNf1L9lnHLvLhgicrIVChEkdzIKYqbNC9s=
github.com/smartystreets/goconvey v1.6.4/go.mod h1:syvi0/a8iFYH4r/RixwvyeAJjdLS9QV7WQ/tjFTllLA=
github.com/soheilhy/cmux v0.1.4/go.mod h1:IM3LyeVVIOuxMH7sFAkER9+bJ4dT7Ms6E4xg4kGIyLM=
github.com/sonatard/noctx v0.0.1/go.mod h1:9D2D/EoULe8Yy2joDHJj7bv3sZoq9AaSb8B4lqBjiZI=
@ -327,6 +333,7 @@ github.com/stretchr/testify v1.3.0 h1:TivCn/peBQ7UY8ooIcPgZFpTNSz0Q2U6UrFlUfqbe0
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
github.com/stretchr/testify v1.6.1 h1:hDPOHmpOpP40lSULcqw7IrRb/u7w6RpDC9399XyoNd0=
github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/subosito/gotenv v1.2.0 h1:Slr1R9HxAlEKefgq5jn9U+DnETlIUa6HfgEzj0g5d7s=
github.com/subosito/gotenv v1.2.0/go.mod h1:N0PQaV/YGNqwC0u51sEeR/aUtSLEXKX9iv69rRypqCw=
@ -522,6 +529,7 @@ gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127 h1:qIbj1fsPNlZgppZ+VLlY7N33
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20200902074654-038fdea0a05b h1:QRR6H1YWRnHb4Y/HeNFCTJLFVxaq6wH4YuVdsUOr75U=
gopkg.in/check.v1 v1.0.0-20200902074654-038fdea0a05b/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
gopkg.in/fsnotify.v1 v1.4.7/go.mod h1:Tz8NjZHkW78fSQdbUxIjBTcgA1z1m8ZHf0WmKUhAMys=
@ -537,6 +545,7 @@ gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.3.0 h1:clyUAQHOM3G0M3f5vQj7LuJrETvjVot3Z5el9nffUtU=
gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gorm.io/driver/sqlite v1.1.3 h1:BYfdVuZB5He/u9dt4qDpZqiqDJ6KhPqs5QUqsr/Eeuc=
gorm.io/driver/sqlite v1.1.3/go.mod h1:AKDgRWk8lcSQSw+9kxCJnX/yySj8G3rdwYlU57cB45c=

View File

@ -3,9 +3,12 @@ package feeds
import (
"encoding/base64"
"fmt"
"net/http"
"net/url"
"strings"
"time"
"github.com/PuerkitoBio/goquery"
"github.com/mmcdole/gofeed"
"github.com/spf13/viper"
)
@ -31,12 +34,17 @@ func Refresh() error {
}
}
func RefreshFeed(url string) Feed {
fmt.Printf("Refreshing %s\n", url)
func RefreshFeed(feedUrl string) Feed {
fmt.Printf("Refreshing %s\n", feedUrl)
var feed Feed
f, err := fp.ParseURL(url)
if err != nil {
fmt.Printf("Failed to refresh %s\n", url)
f, err := fp.ParseURL(feedUrl)
if err != nil && err == gofeed.ErrFeedTypeNotDetected {
foundFeed := loadFeedFromWebpage(feedUrl)
if foundFeed != nil {
feed = *foundFeed
}
} else if err != nil {
fmt.Printf("Failed to refresh %s\n%v\n", feedUrl, err)
} else {
imageURL := ""
if f.Image != nil {
@ -44,11 +52,11 @@ func RefreshFeed(url string) Feed {
}
feed = Feed{
ID: strings.ReplaceAll(base64.StdEncoding.EncodeToString([]byte(url)), "/", ""),
ID: strings.ReplaceAll(base64.StdEncoding.EncodeToString([]byte(feedUrl)), "/", ""),
Title: f.Title,
Description: f.Description,
HomepageURL: f.Link,
FeedURL: url,
FeedURL: feedUrl,
ImageURL: imageURL,
LastUpdated: f.UpdatedParsed,
Items: []Item{},
@ -84,3 +92,35 @@ func RefreshFeed(url string) Feed {
return feed
}
func loadFeedFromWebpage(webpageUrl string) *Feed {
res, err := http.Get(webpageUrl)
if err != nil {
fmt.Println(err)
return nil
}
defer res.Body.Close()
if res.StatusCode != 200 {
fmt.Printf("status code error: %d %s", res.StatusCode, res.Status)
return nil
}
doc, err := goquery.NewDocumentFromReader(res.Body)
if err != nil {
fmt.Println(err)
return nil
}
feedUrl, ok := doc.Find(`[rel="alternate"][type="application/rss+xml"]`).First().Attr("href")
if ok {
if !strings.HasPrefix(feedUrl, "http") {
parsedUrl, _ := url.Parse(webpageUrl)
feedUrl = fmt.Sprintf("%s://%s%s", parsedUrl.Scheme, parsedUrl.Host, feedUrl)
}
feed := RefreshFeed(feedUrl)
return &feed
}
return nil
}

View File

@ -90,7 +90,6 @@
<fieldset class="form-group">
<label for="url">URL:</label>
<input id="url" type="text" placeholder="" class="form-control" v-model="newSiteURL">
<div class="help-block">Enter the direct URL to the feed</div>
</fieldset>
<div class="form-actions">
<button type="button" class="btn btn-primary btn-block" v-on:click="addSite(newSiteURL)" :disabled="isBusy">Add</button>
@ -306,10 +305,12 @@
})
.then(() => {
this.setBusy(false);
this.newSiteURL = '';
})
.catch(err => {
console.error(err);
this.setBusy(false);
this.newSiteURL = '';
});
this.showAddModal = false;
},

View File

@ -185,3 +185,7 @@ button:not(:disabled):hover svg path {
.dark .item-content .card-content a {
color: #ccc;
}
.card-header {
padding: 5px !important;
}