// Copyright (C) 2019 Evgeny Kuznetsov (evgeny@kuznetsov.md) // // This program is free software: you can redistribute it and/or modify // it under the terms of the GNU General Public License as published by // the Free Software Foundation, either version 3 of the License, or // (at your option) any later version. // // This program is distributed in the hope that it will be useful, // but WITHOUT ANY WARRANTY; without even the implied warranty of // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the // GNU General Public License for more details. // // You should have received a copy of the GNU General Public License // along tihe this program. If not, see . package main import ( "flag" "github.com/gorilla/feeds" "io/ioutil" "log" "net/http" "regexp" "strconv" "time" ) type subst struct { from string to string } var ( substitutes = []subst{ {from: `"`, to: `"`}, {from: `–`, to: `–`}, } programNameRe = regexp.MustCompile(`

(.+?)?

`) programAboutRe = regexp.MustCompile(`(?s)
(.+?)?
`) programImageRe = regexp.MustCompile(`(?s)
(.+?)?`) episodeRe = regexp.MustCompile(`(?s)
(.+?)?
`) episodeAudioRe = regexp.MustCompile(`data\-id="(.+?)?">`) episodeDateRe = regexp.MustCompile(`brand\-time brand\-menu\-link">(.+?)?\.(.+?)?\.(.+?)? в (.+?)?:(.+?)?`) episodeDescRe = regexp.MustCompile(`

(.+?)?

`) episodeTitleRe = regexp.MustCompile(`title brand\-menu\-link">(.+?)?`) episodeUrlRe = regexp.MustCompile(``) feed.Description = string(re.ReplaceAll(programAbout, []byte(``))) badFeed := false for _, episode := range episodes { if len(episodeUrlRe.FindAllSubmatch(episode, -1)) > 1 { badFeed = true break } episodeUrl := "http://www.radiorus.ru/brand/" + string(episodeUrlRe.FindSubmatch(episode)[1]) episodeTitle := string(episodeTitleRe.FindSubmatch(episode)[1]) episodeAudioUrl := "https://audio.vgtrk.com/download?id=" + string(episodeAudioRe.FindSubmatch(episode)[1]) dateBytes := episodeDateRe.FindSubmatch(episode) var date [5]int for i, b := range dateBytes[1:] { date[i], err = strconv.Atoi(string(b)) if err != nil { log.Fatal(err) } } moscow := time.FixedZone("Moscow Time", int((3 * time.Hour).Seconds())) episodeDate := time.Date(date[2], time.Month(date[1]), date[0], date[3], date[4], 0, 0, moscow) episodePage := getPage(episodeUrl) episodeDesc := string(episodeDescRe.FindSubmatch(episodePage)[1]) feed.Add(&feeds.Item{ Id: episodeUrl, Link: &feeds.Link{Href: episodeUrl}, Title: episodeTitle, Enclosure: &feeds.Enclosure{ Url: episodeAudioUrl, Length: "1024", Type: "audio/mpeg", }, Created: episodeDate, Description: episodeDesc, }) } if badFeed { log.Println("Page looks strange. Episode in progress? Will wait for 15 minutes and try again...") time.Sleep(15 * 60 * time.Second) continue } rss, err := feed.ToRss() if err != nil { log.Fatal(err) } outputFile := outputPath + "radiorus-" + programNumber + ".rss" output := []byte(rss) if err := ioutil.WriteFile(outputFile, output, 0644); err != nil { log.Fatal(err) } break } } func getPage(pageUrl string) []byte { res, err := http.Get(pageUrl) if err != nil { log.Fatal(err) } defer res.Body.Close() page, err := ioutil.ReadAll(res.Body) if err != nil { log.Fatal(err) } for _, sub := range substitutes { re := regexp.MustCompile(sub.from) page = re.ReplaceAll(page, []byte(sub.to)) } return page }