Fix: Expending articles research inside DOM - Only the last few hours

go.mod

@@ -10,19 +10,19 @@ require (
 	github.com/antchfx/htmlquery v1.2.3 // indirect
 	github.com/antchfx/xmlquery v1.2.4 // indirect
 	github.com/antchfx/xpath v1.1.8 // indirect
-	github.com/bwmarrin/discordgo v0.27.1 // indirect
+	github.com/bwmarrin/discordgo v0.28.1 // indirect
 	github.com/gobwas/glob v0.2.3 // indirect
 	github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e // indirect
 	github.com/golang/protobuf v1.4.2 // indirect
-	github.com/gorilla/websocket v1.4.2 // indirect
+	github.com/gorilla/websocket v1.5.3 // indirect
 	github.com/kennygrant/sanitize v1.2.4 // indirect
 	github.com/robfig/cron/v3 v3.0.1 // indirect
 	github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca // indirect
 	github.com/temoto/robotstxt v1.1.1 // indirect
-	golang.org/x/crypto v0.0.0-20210421170649-83a5a9bb288b // indirect
-	golang.org/x/net v0.0.0-20210226172049-e18ecbb05110 // indirect
-	golang.org/x/sys v0.0.0-20201119102817-f84b799fce68 // indirect
-	golang.org/x/text v0.3.3 // indirect
+	golang.org/x/crypto v0.24.0 // indirect
+	golang.org/x/net v0.21.0 // indirect
+	golang.org/x/sys v0.21.0 // indirect
+	golang.org/x/text v0.16.0 // indirect
 	google.golang.org/appengine v1.6.6 // indirect
 	google.golang.org/protobuf v1.24.0 // indirect
 )

go.sum

@@ -14,6 +14,8 @@ github.com/antchfx/xpath v1.1.8 h1:PcL6bIX42Px5usSx6xRYw/wjB3wYGkj0MJ9MBzEKVgk=
 github.com/antchfx/xpath v1.1.8/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
 github.com/bwmarrin/discordgo v0.27.1 h1:ib9AIc/dom1E/fSIulrBwnez0CToJE113ZGt4HoliGY=
 github.com/bwmarrin/discordgo v0.27.1/go.mod h1:NJZpH+1AfhIcyQsPeuBKsUtYrRnjkyu0kIVMCHkZtRY=
+github.com/bwmarrin/discordgo v0.28.1 h1:gXsuo2GBO7NbR6uqmrrBDplPUx2T3nzu775q/Rd1aG4=
+github.com/bwmarrin/discordgo v0.28.1/go.mod h1:NJZpH+1AfhIcyQsPeuBKsUtYrRnjkyu0kIVMCHkZtRY=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
 github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -47,6 +49,8 @@ github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMyw
 github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/gorilla/websocket v1.4.2 h1:+/TMaTYc4QFitKJxsQ7Yye35DkWvkdLcvGKqM+x0Ufc=
 github.com/gorilla/websocket v1.4.2/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
+github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg=
+github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
 github.com/jawher/mow.cli v1.1.0/go.mod h1:aNaQlc7ozF3vw6IJ2dHjp2ZFiA4ozMIYY6PyuRJwlUg=
 github.com/kennygrant/sanitize v1.2.4 h1:gN25/otpP5vAsO2djbMhF/LQX6R7+O1TB4yv8NzpJ3o=
 github.com/kennygrant/sanitize v1.2.4/go.mod h1:LGsjYYtgxbetdg5owWB2mpgUL6e2nfw2eObZ0u0qvak=
@@ -65,6 +69,8 @@ golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACk
 golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20210421170649-83a5a9bb288b h1:7mWr3k41Qtv8XlltBkDkl8LoP3mpSgBW8BUoxtEdbXg=
 golang.org/x/crypto v0.0.0-20210421170649-83a5a9bb288b/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
+golang.org/x/crypto v0.24.0 h1:mnl8DM0o513X8fdIkmyFE/5hTYxbwYOjDS/+rK6qpRI=
+golang.org/x/crypto v0.24.0/go.mod h1:Z1PMYSOR5nyMcyAVAIQSKCDwalqy85Aqn1x3Ws4L5DM=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
 golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
@@ -81,6 +87,8 @@ golang.org/x/net v0.0.0-20200421231249-e086a090c8fd/go.mod h1:qpuaurCH72eLCgpAm/
 golang.org/x/net v0.0.0-20200602114024-627f9648deb9/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110 h1:qWPm9rbaAMKs8Bq/9LRpbMqxWRVUAQwMI9fVrssnTfw=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
+golang.org/x/net v0.21.0 h1:AQyQV4dYCvJ7vGmJyKki9+PBdyvhkSd8EIx/qb0AYv4=
+golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -91,11 +99,15 @@ golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68 h1:nxC68pudNYkKU6jWhgrqdreuFiOQWj1Fs7T3VrH4Pjw=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws=
+golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3 h1:cokOdA+Jmi5PJGXLlLllQSgYigAEfHXJAERHVMaCc2k=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
+golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=

main.go

@@ -3,6 +3,7 @@ package main
 import (
 	"fmt"
 	"log"
+	"regexp"
 	"strings"
 
 	"github.com/bwmarrin/discordgo"
@@ -94,14 +95,22 @@ func searchArticle(channelID string) string {
 	c := colly.NewCollector()
 	var hrefSlice []string
 
-	/* Try to get the first span that contains "hours" keyword, and then get the link above
-	 */
+	re := regexp.MustCompile(`\d+\s*h(?:ours?)?\s*ago`)
+
 	c.OnHTML("span", func(e *colly.HTMLElement) {
-		if strings.Contains(e.Text, "hours") || strings.Contains(e.Text, "Just now") {
+		if re.MatchString(e.Text) {
+
+			// Search <a> elements inside parent
 			a := e.DOM.ParentsUntil("body").Filter("a").First()
+
+			// If no <a> parent is found, then search inside next ones
+			if a.Length() == 0 {
+				a = e.DOM.ParentsUntil("body").Find("a").First()
+			}
+
 			if href_, exists := a.Attr("href"); exists {
 				long_href := e.Request.AbsoluteURL(href_)
-				href = strings.Split(long_href, "?source")[0]
+				href := strings.Split(long_href, "?source")[0]
 				hrefSlice = append(hrefSlice, href)
 			}
 		}

setup-data.json

@@ -1 +1 @@
-{"mode":"channel_mode","userID":"177839639648796673","selectedChannelID":"1169659227653017611","mediumCategory":"Programming","hourToSend":"4am","previousArticle":"https://medium.com/@erlandmuchasaj/php-design-patterns-23adbac88c6e"}
+{"mode":"channel_mode","userID":"177839639648796673","selectedChannelID":"1251221248139329647","mediumCategory":"Programming","hourToSend":"8am","previousArticle":"https://medium.com/@subroto.2003/a-guide-to-flutter-internals-ce8d64d01c50"}