Fix torrent URL extraction

almalinux/main.go

@@ -4,8 +4,8 @@ import (
 	"fmt"
 	"log"
 
-	"tildegit.org/hyperreal/go-torrent-helper/common"
 	"github.com/hekmon/transmissionrpc"
+	"tildegit.org/hyperreal/go-torrent-helper/common"
 )
 
 type AlmaLinux struct {

command/main.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"os"
 
+	"github.com/hekmon/transmissionrpc"
 	"tildegit.org/hyperreal/go-torrent-helper/almalinux"
 	"tildegit.org/hyperreal/go-torrent-helper/debian"
 	"tildegit.org/hyperreal/go-torrent-helper/fedora"
@@ -13,7 +14,6 @@ import (
 	"tildegit.org/hyperreal/go-torrent-helper/parrot"
 	"tildegit.org/hyperreal/go-torrent-helper/qubes"
 	"tildegit.org/hyperreal/go-torrent-helper/rocky"
-	"github.com/hekmon/transmissionrpc"
 )
 
 type Distro interface {

common/main.go

@@ -2,7 +2,7 @@ package common
 
 import (
 	"fmt"
-	"io/ioutil"
+	"io"
 	"log"
 	"net/http"
 	"strings"
@@ -10,7 +10,7 @@ import (
 	"github.com/hekmon/transmissionrpc"
 )
 
-func GetResponse(url string) ([]byte, error) {
+func GetResponse(url string) (io.ReadCloser, error) {
 	req, _ := http.NewRequest("GET", url, nil)
 	req.Header.Add("User-Agent", "go-torrent-helper")
 
@@ -33,13 +33,8 @@ func GetResponse(url string) ([]byte, error) {
 		return nil, fmt.Errorf("Error: %d %s\n", resp.StatusCode, resp.Status)
 	}
 
-	// Return response as bytes
+	// Return response body
-	dataInBytes, err := ioutil.ReadAll(resp.Body)
+	return resp.Body, nil
-	if err != nil {
-		return nil, fmt.Errorf("Error reading response: %s\n", err)
-	}
-
-	return dataInBytes, nil
 }
 
 func values[M ~map[K]V, K comparable, V any](m M) []V {

debian/main.go

@@ -4,8 +4,8 @@ import (
 	"fmt"
 	"log"
 
-	"tildegit.org/hyperreal/go-torrent-helper/common"
 	"github.com/hekmon/transmissionrpc"
+	"tildegit.org/hyperreal/go-torrent-helper/common"
 )
 
 type Debian struct {

fedora/main.go

@@ -2,12 +2,13 @@ package fedora
 
 import (
 	"fmt"
+	"io/ioutil"
 	"log"
 	"regexp"
 	"strings"
 
-	"tildegit.org/hyperreal/go-torrent-helper/common"
 	"github.com/hekmon/transmissionrpc"
+	"tildegit.org/hyperreal/go-torrent-helper/common"
 )
 
 type Fedora struct {
@@ -20,11 +21,16 @@ func (f Fedora) AddNewTorrents(transmissionbt *transmissionrpc.Client) error {
 	// Send HTTP GET request and receive response
 	f.URL = "https://torrent.fedoraproject.org/"
 	torrentSubstr := fmt.Sprintf("%s.torrent", f.Relver)
-	dataInBytes, err := common.GetResponse(f.URL)
+	respBody, err := common.GetResponse(f.URL)
 	if err != nil {
 		return err
 	}
 
+	dataInBytes, err := ioutil.ReadAll(respBody)
+	if err != nil {
+		return fmt.Errorf("Error reading response body: %s\n", err)
+	}
+
 	bodyText := string(dataInBytes)
 
 	// Extract torrent URLs from web page contents

go.mod

@@ -5,6 +5,9 @@ go 1.20
 require github.com/hekmon/transmissionrpc v1.1.0
 
 require (
+	github.com/PuerkitoBio/goquery v1.8.1 // indirect
+	github.com/andybalholm/cascadia v1.3.1 // indirect
 	github.com/hashicorp/go-cleanhttp v0.5.1 // indirect
 	github.com/hekmon/cunits/v2 v2.0.2 // indirect
+	golang.org/x/net v0.7.0 // indirect
 )

go.sum

@@ -1,6 +1,41 @@
+github.com/PuerkitoBio/goquery v1.8.1 h1:uQxhNlArOIdbrH1tr0UXwdVFgDcZDrZVdcpygAcwmWM=
+github.com/PuerkitoBio/goquery v1.8.1/go.mod h1:Q8ICL1kNUJ2sXGoAhPGUdYDJvgQgHzJsnnd3H7Ho5jQ=
+github.com/andybalholm/cascadia v1.3.1 h1:nhxRkql1kdYCc8Snf7D5/D3spOX+dBgjA6u8x004T2c=
+github.com/andybalholm/cascadia v1.3.1/go.mod h1:R4bJ1UQfqADjvDa4P6HZHLh/3OxWWEqc0Sk8XGwHqvA=
 github.com/hashicorp/go-cleanhttp v0.5.1 h1:dH3aiDG9Jvb5r5+bYHsikaOUIpcM0xvgMXVoDkXMzJM=
 github.com/hashicorp/go-cleanhttp v0.5.1/go.mod h1:JpRdi6/HCYpAwUzNwuwqhbovhLtngrth3wmdIIUrZ80=
 github.com/hekmon/cunits/v2 v2.0.2 h1:qnZMfVxBiTgtAXVSMLKxzV1nihS6KzdjDHgh+nS4RgI=
 github.com/hekmon/cunits/v2 v2.0.2/go.mod h1:9r1TycXYXaTmEWlAIfFV8JT+Xo59U96yUJAYHxzii2M=
 github.com/hekmon/transmissionrpc v1.1.0 h1:58xY27x2JYxaMlIj7ycKnxqgCm3IjvTxfB7cHPLxOfs=
 github.com/hekmon/transmissionrpc v1.1.0/go.mod h1:qkwhsyD/MQSlWvOE1AC92xajwEveAuGsOvTuOBZEuHc=
+github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
+golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
+golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/net v0.7.0 h1:rJrUqqhjsgNp7KqAIc25s9pZnjU7TUcSY7HcVZjdn1g=
+golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
+golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
+golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

nixos/main.go

@@ -2,10 +2,12 @@ package nixos
 
 import (
 	"encoding/json"
+	"fmt"
+	"io/ioutil"
 	"log"
 
-	"tildegit.org/hyperreal/go-torrent-helper/common"
 	"github.com/hekmon/transmissionrpc"
+	"tildegit.org/hyperreal/go-torrent-helper/common"
 )
 
 type Nixos struct {
@@ -17,11 +19,16 @@ type Nixos struct {
 func (n Nixos) AddNewTorrents(transmissionbt *transmissionrpc.Client) error {
 	// Send GET request and receive HTTP response
 	n.URL = "https://api.github.com/repos/AnimMouse/NixOS-ISO-Torrents/releases/latest"
-	dataInBytes, err := common.GetResponse(n.URL)
+	respBody, err := common.GetResponse(n.URL)
 	if err != nil {
 		return err
 	}
 
+	dataInBytes, err := ioutil.ReadAll(respBody)
+	if err != nil {
+		return fmt.Errorf("Error reading response body: %s\n", err)
+	}
+
 	result := make(map[string]interface{})
 	if err := json.Unmarshal(dataInBytes, &result); err != nil {
 		return err

parrot/main.go

@@ -3,9 +3,9 @@ package parrot
 import (
 	"fmt"
 	"log"
-	"regexp"
 	"strings"
 
+	"github.com/PuerkitoBio/goquery"
 	"github.com/hekmon/transmissionrpc"
 	"tildegit.org/hyperreal/go-torrent-helper/common"
 )
@@ -17,24 +17,25 @@ type Parrot struct {
 }
 
 func (p Parrot) AddNewTorrents(transmissionbt *transmissionrpc.Client) error {
-	// Set torrentURLs for Parrot Security
 	p.URL = fmt.Sprintf("https://deb.parrot.sh/parrot/iso/%s/", p.Relver)
-	dataInBytes, err := common.GetResponse(p.URL)
+	respBody, err := common.GetResponse(p.URL)
 	if err != nil {
 		return err
 	}
 
-	bodyText := string(dataInBytes)
+	// Get a goquery doc from response body
+	doc, err := goquery.NewDocumentFromReader(respBody)
+	if err != nil {
+		return err
+	}
 
 	// Extract torrent URLs from web page contents
 	var torrentURLs []string
-	re := regexp.MustCompile(`(http|ftp|https):\/\/([\w_-]+(?:(?:\.[\w_-]+)+))([\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-])`)
+	doc.Find("a").Each(func(i int, s *goquery.Selection) {
-	match := re.FindAllString(bodyText, 1000)
+		if strings.Contains(s.Text(), "torrent") {
-	for _, v := range match {
+			torrentURLs = append(torrentURLs, fmt.Sprintf("%s/%s", p.URL, s.Text()))
-		if strings.Contains(v, ".torrent") {
-			torrentURLs = append(torrentURLs, v)
-		}
 		}
+	})
 
 	// Add torrents to Transmission instance
 	for _, torrentURL := range torrentURLs {

qubes/main.go

@@ -1,10 +1,11 @@
 package qubes
 
 import (
+	"fmt"
 	"log"
-	"regexp"
 	"strings"
 
+	"github.com/PuerkitoBio/goquery"
 	"github.com/hekmon/transmissionrpc"
 	"tildegit.org/hyperreal/go-torrent-helper/common"
 )
@@ -17,23 +18,25 @@ type Qubes struct {
 
 func (q Qubes) AddNewTorrents(transmissionbt *transmissionrpc.Client) error {
 	// Set torrentURLs for Qubes OS
-	q.URL = "https://mirrors.edge.kernel.org/qubes/iso/Qubes/iso/"
+	q.URL = "https://mirrors.edge.kernel.org/qubes/iso/"
-	dataInBytes, err := common.GetResponse(q.URL)
+	respBody, err := common.GetResponse(q.URL)
 	if err != nil {
 		return err
 	}
 
-	bodyText := string(dataInBytes)
+	// Get a goquery doc from response body
+	doc, err := goquery.NewDocumentFromReader(respBody)
+	if err != nil {
+		return err
+	}
 
 	// Extract torrent URLs from web page contents
 	var torrentURLs []string
-	re := regexp.MustCompile(`(http|ftp|https):\/\/([\w_-]+(?:(?:\.[\w_-]+)+))([\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-])`)
+	doc.Find("a").Each(func(i int, s *goquery.Selection) {
-	match := re.FindAllString(bodyText, 1000)
+		if strings.Contains(s.Text(), q.Relver) && strings.Contains(s.Text(), "torrent") {
-	for _, v := range match {
+			torrentURLs = append(torrentURLs, fmt.Sprintf("%s/%s", q.URL, s.Text()))
-		if strings.Contains(v, ".torrent") && strings.Contains(v, q.Relver) {
-			torrentURLs = append(torrentURLs, v)
-		}
 		}
+	})
 
 	// Add torrents to Transmission instance
 	for _, torrentURL := range torrentURLs {

rocky/main.go

@@ -3,9 +3,9 @@ package rocky
 import (
 	"fmt"
 	"log"
-	"regexp"
 	"strings"
 
+	"github.com/PuerkitoBio/goquery"
 	"github.com/hekmon/transmissionrpc"
 	"tildegit.org/hyperreal/go-torrent-helper/common"
 )
@@ -21,23 +21,26 @@ func (r Rocky) AddNewTorrents(transmissionbt *transmissionrpc.Client) error {
 	archs := []string{"aarch64", "ppc64le", "s390x", "x86_64"}
 	var torrentURLs []string
 
+	// Iterate over architectures and extract torrent URLs for each
 	for _, arch := range archs {
 		r.URL = fmt.Sprintf("https://download.rockylinux.org/pub/rocky/%s/isos/%s/", r.Relver, arch)
-		dataInBytes, err := common.GetResponse(r.URL)
+		respBody, err := common.GetResponse(r.URL)
 		if err != nil {
 			return err
 		}
 
-		bodyText := string(dataInBytes)
+		// Get a goquery doc from response body
+		doc, err := goquery.NewDocumentFromReader(respBody)
+		if err != nil {
+			return err
+		}
 
 		// Extract torrent URLs from web page contents
-		re := regexp.MustCompile(`(http|ftp|https):\/\/([\w_-]+(?:(?:\.[\w_-]+)+))([\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-])`)
+		doc.Find("a").Each(func(i int, s *goquery.Selection) {
-		match := re.FindAllString(bodyText, 1000)
+			if strings.Contains(s.Text(), "torrent") {
-		for _, v := range match {
+				torrentURLs = append(torrentURLs, fmt.Sprintf("%s/%s", r.URL, s.Text()))
-			if strings.Contains(v, ".torrent") {
-				torrentURLs = append(torrentURLs, v)
-			}
 			}
+		})
 	}
 
 	// Add torrents to Transmission instance