diff options
author | Alexander Neonxp Kiryukhin <i@neonxp.ru> | 2024-12-15 17:37:47 +0300 |
---|---|---|
committer | Alexander Neonxp Kiryukhin <i@neonxp.ru> | 2024-12-15 17:37:47 +0300 |
commit | 70565ecac31f7bb5c1d6c559ed18ff9f9c56ac46 (patch) | |
tree | 2a45103ab148653d72fd6c33cd39201984509442 | |
parent | 533c0aeaeb5c674304624ec1024ca0e962a8f3f2 (diff) |
Изображение в фиде
-rw-r--r-- | Dockerfile | 8 | ||||
-rw-r--r-- | app/app.go | 72 | ||||
-rw-r--r-- | app/config.go | 4 | ||||
-rw-r--r-- | go.mod | 12 | ||||
-rw-r--r-- | go.sum | 20 | ||||
-rw-r--r-- | main.go | 2 | ||||
-rw-r--r-- | store/seq.txt | 1 | ||||
-rw-r--r-- | templates/telegram.gotmpl | 4 |
8 files changed, 78 insertions, 45 deletions
@@ -1,6 +1,6 @@ # syntax=docker/dockerfile:1 -FROM golang:1.22.4-alpine +FROM golang:1.23.4-alpine WORKDIR /app @@ -9,12 +9,12 @@ RUN go mod download COPY . . -RUN CGO_ENABLED=0 GOOS=linux go build -o /rss2world +RUN CGO_ENABLED=0 GOOS=linux go build -o /posse -ENV RSS_URL="https://neonxp.ru/feed.atom" +ENV RSS_URL="https://neonxp.ru/feed/" ENV CHECK_INTERVAL="5m" ENV SEQ_FILE="/store/seq.txt" ENV TELEGRAM_TOKEN="279146841:AAE9Yd2W........_gAhbO3usM" ENV TELEGRAM_GROUPS="-1001003209449" -CMD ["/rss2world"]
\ No newline at end of file +CMD ["/posse"]
\ No newline at end of file @@ -5,14 +5,15 @@ import ( "context" "log/slog" "os" - "regexp" "strings" "text/template" "time" + "git.neonxp.ru/posse/templates" + tgbotapi "github.com/go-telegram-bot-api/telegram-bot-api/v5" + "github.com/microcosm-cc/bluemonday" "github.com/mmcdole/gofeed" - "gitrepo.ru/neonxp/rss2world/templates" ) type App struct { @@ -41,6 +42,9 @@ func New(cfg *Config) (*App, error) { func (a *App) Run(ctx context.Context) error { ticker := time.NewTicker(a.config.RSS.CheckInterval) + if err := a.iteration(); err != nil { + slog.ErrorContext(ctx, "failed iteration", slog.Any("error", err)) + } for { select { case <-ctx.Done(): @@ -82,16 +86,49 @@ func (a *App) iteration() error { func (a *App) processItem(item *gofeed.Item) error { buf := bytes.NewBufferString("") - item.Content = trimHtml(item.Description) + + p := bluemonday.Policy{} + p.AllowStandardURLs() + p.AllowElements("b", "i", "code", "u", "strike", "pre", "br", "a") + p.AllowNoAttrs().Globally() + p.AllowAttrs("href").OnElements("a") + s := strings.ReplaceAll(item.Description, "<del>", "<strike>") + s = strings.ReplaceAll(s, "</del>", "</strike>") + s = strings.ReplaceAll(s, "<h1", "<b") + s = strings.ReplaceAll(s, "</h1>", "</b>") + s = strings.ReplaceAll(s, "<h2", "<b") + s = strings.ReplaceAll(s, "</h2>", "</b>") + s = strings.ReplaceAll(s, "<br />", "\n") + s = strings.ReplaceAll(s, "<p>", "") + s = strings.ReplaceAll(s, "</p>", "") + item.Content = p.Sanitize(s) + if err := a.templates.ExecuteTemplate(buf, "telegram", item); err != nil { return err } - str := buf.String() + str := "" + str2 := buf.String() + for str != str2 { + str = str2 + str2 = strings.ReplaceAll(str, "\n\n", "\n") + str2 = strings.ReplaceAll(str2, " ", " ") + str2 = strings.Trim(str2, " \t\n") + } for _, group := range a.config.Telegram.TargetGroups { - msg := tgbotapi.NewMessage(group, str) - msg.ParseMode = tgbotapi.ModeHTML - if _, err := a.telegram.Send(msg); err != nil { - return err + switch { + case item.Image != nil: + msg := tgbotapi.NewPhoto(group, tgbotapi.FileURL(item.Image.URL)) + msg.ParseMode = tgbotapi.ModeHTML + msg.Caption = str + if _, err := a.telegram.Send(msg); err != nil { + return err + } + default: + msg := tgbotapi.NewMessage(group, str) + msg.ParseMode = tgbotapi.ModeHTML + if _, err := a.telegram.Send(msg); err != nil { + return err + } } } @@ -127,22 +164,3 @@ func (a *App) findNewItems(from string) ([]*gofeed.Item, error) { return out, nil } - -func trimHtml(src string) string { - // Convert all HTML tags to lowercase - re, _ := regexp.Compile("\\<[\\S\\s]+?\\>") - src = re.ReplaceAllStringFunc(src, strings.ToLower) - // Remove STYLE - re, _ = regexp.Compile("\\<style[\\S\\s]+?\\</style\\>") - src = re.ReplaceAllString(src, "") - // Remove SCRIPT - re, _ = regexp.Compile("\\<script[\\S\\s]+?\\</script\\>") - src = re.ReplaceAllString(src, "") - // Remove all HTML code in angle brackets and replace them with newline characters - re, _ = regexp.Compile("\\<[\\S\\s]+?\\>") - src = re.ReplaceAllString(src, "\n") - // Remove consecutive newlines - re, _ = regexp.Compile("\\s{2,}") - src = re.ReplaceAllString(src, "\n") - return strings.TrimSpace(src) -} diff --git a/app/config.go b/app/config.go index 66531aa..093400f 100644 --- a/app/config.go +++ b/app/config.go @@ -1,8 +1,8 @@ package app import ( - "gitrepo.ru/neonxp/rss2world/internal/rss" - "gitrepo.ru/neonxp/rss2world/internal/telegram" + "git.neonxp.ru/posse/internal/rss" + "git.neonxp.ru/posse/internal/telegram" "github.com/caarlos0/env/v11" ) @@ -1,4 +1,4 @@ -module gitrepo.ru/neonxp/rss2world +module git.neonxp.ru/posse go 1.22.4 @@ -8,13 +8,19 @@ require ( ) require ( + github.com/aymerick/douceur v0.2.0 // indirect + github.com/gorilla/css v1.0.1 // indirect +) + +require ( github.com/PuerkitoBio/goquery v1.8.0 // indirect github.com/andybalholm/cascadia v1.3.1 // indirect github.com/go-telegram-bot-api/telegram-bot-api/v5 v5.5.1 github.com/json-iterator/go v1.1.12 // indirect + github.com/microcosm-cc/bluemonday v1.0.27 github.com/mmcdole/goxpp v1.1.1-0.20240225020742-a0c311522b23 // indirect github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect github.com/modern-go/reflect2 v1.0.2 // indirect - golang.org/x/net v0.4.0 // indirect - golang.org/x/text v0.5.0 // indirect + golang.org/x/net v0.26.0 // indirect + golang.org/x/text v0.16.0 // indirect ) @@ -2,15 +2,22 @@ github.com/PuerkitoBio/goquery v1.8.0 h1:PJTF7AmFCFKk1N6V6jmKfrNH9tV5pNE6lZMkG0g 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= +github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk= +github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4= github.com/caarlos0/env/v11 v11.1.0 h1:a5qZqieE9ZfzdvbbdhTalRrHT5vu/4V1/ad1Ka6frhI= github.com/caarlos0/env/v11 v11.1.0/go.mod h1:LwgkYk1kDvfGpHthrWWLof3Ny7PezzFwS4QrsJdHTMo= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/go-telegram-bot-api/telegram-bot-api/v5 v5.5.1 h1:wG8n/XJQ07TmjbITcGiUaOtXxdrINDz1b0J1w0SzqDc= github.com/go-telegram-bot-api/telegram-bot-api/v5 v5.5.1/go.mod h1:A2S0CWkNylc2phvKXWBBdD3K0iGnDBGbzRpISP2zBl8= github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg= +github.com/gorilla/css v1.0.1 h1:ntNaBIghp6JmvWnxbZKANoLyuXTPZ4cAMlo6RyhlbO8= +github.com/gorilla/css v1.0.1/go.mod h1:BvnYkspnSzMmwRK+b8/xgNPLiIuNZr6vbZBTPQ2A3b0= github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM= github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo= +github.com/microcosm-cc/bluemonday v1.0.27 h1:MpEUotklkwCSLeH+Qdx1VJgNqLlpY2KXwXFM08ygZfk= +github.com/microcosm-cc/bluemonday v1.0.27/go.mod h1:jFi9vgW+H7c3V0lb6nR74Ib/DIB5OBs92Dimizgw2cA= github.com/mmcdole/gofeed v1.3.0 h1:5yn+HeqlcvjMeAI4gu6T+crm7d0anY85+M+v6fIFNG4= github.com/mmcdole/gofeed v1.3.0/go.mod h1:9TGv2LcJhdXePDzxiuMnukhV2/zb6VtnZt1mS+SjkLE= github.com/mmcdole/goxpp v1.1.1-0.20240225020742-a0c311522b23 h1:Zr92CAlFhy2gL+V1F+EyIuzbQNbSgP4xhTODZtrXUtk= @@ -20,16 +27,21 @@ github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M= github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk= +github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= +github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk= +github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4= golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y= -golang.org/x/net v0.4.0 h1:Q5QPcMlvfxFTAPV0+07Xz/MpK9NTXu2VDUuy0FeMfaU= -golang.org/x/net v0.4.0/go.mod h1:MBQ8lrhLObU/6UmLb4fmbmk5OcyYmqtbGd/9yIeKjEE= +golang.org/x/net v0.26.0 h1:soB7SVo0PWrY4vPW/+ay0jKDNScG2X9wFeYlXIvJsOQ= +golang.org/x/net v0.26.0/go.mod h1:5YKkiSynbBIh3p6iOc/vibscux0x38BZDkn8sCUPxHE= 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/text v0.5.0 h1:OLmvp0KP+FVG99Ct/qFiL/Fhk4zp4QQnZ7b2U+5piUM= -golang.org/x/text v0.5.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8= +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= +gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= +gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= @@ -5,7 +5,7 @@ import ( "os" "os/signal" - "gitrepo.ru/neonxp/rss2world/app" + "git.neonxp.ru/posse/app" ) func main() { diff --git a/store/seq.txt b/store/seq.txt deleted file mode 100644 index aeb20ea..0000000 --- a/store/seq.txt +++ /dev/null @@ -1 +0,0 @@ -https://neonxp.ru/posts/2024/06/02/%D0%BA%D0%BD%D0%B8%D0%B6%D0%BD%D1%8B%D0%B5_%D1%80%D0%B5%D0%BA%D0%BE%D0%BC%D0%B5%D0%BD%D0%B4%D0%B0%D1%86%D0%B8%D0%B8_1/
\ No newline at end of file diff --git a/templates/telegram.gotmpl b/templates/telegram.gotmpl index d217731..775322c 100644 --- a/templates/telegram.gotmpl +++ b/templates/telegram.gotmpl @@ -3,7 +3,5 @@ {{.Content}} -<a href="{{.Link}}">Запись полностью и комментарии</a> - -Отправлено через <a href="https://git.neonxp.ru/neonxp/rss2world">rss2world</a> +<a href="{{.Link}}">Перейти к оригиналу</a> {{end}}
\ No newline at end of file |