feat: add endpoint to generate RSS feed

go.mod

@@ -1,3 +1,10 @@
 module github.com/Kichiyaki/lubimyczytacrss
 
 go 1.18
+
+require github.com/PuerkitoBio/goquery v1.8.0
+
+require (
+	github.com/andybalholm/cascadia v1.3.1 // indirect
+	golang.org/x/net v0.0.0-20210916014120-12bc252f5db8 // indirect
+)

go.sum

@@ -0,0 +1,11 @@
+github.com/PuerkitoBio/goquery v1.8.0 h1:PJTF7AmFCFKk1N6V6jmKfrNH9tV5pNE6lZMkG0gta/U=
+github.com/PuerkitoBio/goquery v1.8.0/go.mod h1:ypIiRMtY7COPGk+I/YbZLbxsxn9g5ejnI2HSMtkjZvI=
+github.com/andybalholm/cascadia v1.3.1 h1:nhxRkql1kdYCc8Snf7D5/D3spOX+dBgjA6u8x004T2c=
+github.com/andybalholm/cascadia v1.3.1/go.mod h1:R4bJ1UQfqADjvDa4P6HZHLh/3OxWWEqc0Sk8XGwHqvA=
+golang.org/x/net v0.0.0-20210916014120-12bc252f5db8 h1:/6y1LfuqNuQdHAm0jjtPtgRcxIxjVZgm5OTu8/QhZvk=
+golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+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/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=

main.go

@@ -2,17 +2,28 @@ package main
 
 import (
 	"context"
+	"encoding/xml"
+	"fmt"
+	"github.com/PuerkitoBio/goquery"
+	"io"
 	"log"
 	"net/http"
+	"net/url"
 	"os"
 	"os/signal"
+	"strings"
 	"time"
 )
 
+const (
+	lubimyCzytacDomain = "lubimyczytac.pl"
+	defaultTimeout     = 5 * time.Second
+)
+
 func main() {
 	httpSrv := &http.Server{
 		Addr:              ":9234",
-		Handler:           nil,
+		Handler:           newHandler(),
 		ReadTimeout:       2 * time.Second,
 		ReadHeaderTimeout: 2 * time.Second,
 		WriteTimeout:      2 * time.Second,
@@ -38,3 +49,107 @@ func main() {
 		log.Fatalln("httpSrv.Shutdown:", err)
 	}
 }
+
+type rssMain struct {
+	XMLName xml.Name   `xml:"rss"`
+	Version string     `xml:"version,attr"`
+	Channel rssChannel `xml:"channel"`
+}
+
+type rssChannel struct {
+	XMLName     xml.Name  `xml:"channel"`
+	Link        string    `xml:"link"`
+	Description string    `xml:"description"`
+	Language    string    `xml:"language"`
+	Items       []rssItem `xml:"items"`
+}
+
+type rssItem struct {
+	XMLName     xml.Name `xml:"item"`
+	Title       string   `xml:"title"`
+	Link        string   `xml:"link"`
+	GUID        string   `xml:"guid"`
+	Description string   `xml:"description"`
+}
+
+func newHandler() http.Handler {
+	client := &http.Client{
+		Timeout: defaultTimeout,
+	}
+	return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != http.MethodGet {
+			w.WriteHeader(http.StatusMethodNotAllowed)
+			return
+		}
+
+		req, err := http.NewRequestWithContext(r.Context(), http.MethodGet, r.URL.Path[1:], nil)
+		if err != nil || req.URL.Host != lubimyCzytacDomain {
+			w.WriteHeader(http.StatusBadRequest)
+			return
+		}
+
+		resp, err := client.Do(req)
+		if err != nil {
+			w.WriteHeader(http.StatusInternalServerError)
+			return
+		}
+		defer func() {
+			_ = resp.Body.Close()
+		}()
+
+		p, err := newAuthorPageParser(resp.Body)
+		if err != nil {
+			_, _ = io.Copy(io.Discard, resp.Body)
+			w.WriteHeader(http.StatusBadRequest)
+			return
+		}
+
+		w.Header().Set("Content-Type", "text/xml; charset=utf-8")
+		w.WriteHeader(http.StatusOK)
+		if err := xml.NewEncoder(w).Encode(rssMain{
+			Version: "2.0",
+			Channel: rssChannel{
+				Link:  req.URL.String(),
+				Items: p.items(req.URL),
+			},
+		}); err != nil {
+			w.WriteHeader(http.StatusInternalServerError)
+			return
+		}
+	})
+}
+
+type authorPageParser struct {
+	doc *goquery.Document
+}
+
+func newAuthorPageParser(r io.Reader) (authorPageParser, error) {
+	doc, err := goquery.NewDocumentFromReader(r)
+	if err != nil {
+		return authorPageParser{}, fmt.Errorf("goquery.NewDocumentFromReader: %w", err)
+	}
+	return authorPageParser{
+		doc: doc,
+	}, nil
+}
+
+func (p authorPageParser) items(baseURL *url.URL) []rssItem {
+	booksSel := p.doc.Find("#authorBooks .authorAllBooks__single")
+	items := make([]rssItem, booksSel.Length())
+	booksSel.Each(func(i int, selection *goquery.Selection) {
+		link := url.URL{
+			Scheme: baseURL.Scheme,
+			Host:   baseURL.Host,
+			Path:   selection.Find(".authorAllBooks__singleTextTitle").AttrOr("href", ""),
+		}
+		linkStr := link.String()
+		title := strings.TrimSpace(selection.Find(".authorAllBooks__singleTextTitle").Text())
+		items[i] = rssItem{
+			Title:       title,
+			Link:        linkStr,
+			GUID:        linkStr,
+			Description: "",
+		}
+	})
+	return items
+}