commit a3f9289777dd949a233e0bb78c8309653a3121f9 Author: moxitech Date: Fri Sep 27 02:11:48 2024 +0700 create worker universal parser & http getter diff --git a/.env b/.env new file mode 100644 index 0000000..e69de29 diff --git a/TODO.md b/TODO.md new file mode 100644 index 0000000..05b52fc --- /dev/null +++ b/TODO.md @@ -0,0 +1,11 @@ +#### Парсим: + + +| Имя | Статус | +|---|---| +| Телеграмм | N | +| VK | N | +| Gismeteo | N | +| Центробанк | N | +| СШИ | N | + diff --git a/docker-compose.yaml b/docker-compose.yaml new file mode 100644 index 0000000..e69de29 diff --git a/server/api/cmd/main.go b/server/api/cmd/main.go new file mode 100644 index 0000000..50fffb3 --- /dev/null +++ b/server/api/cmd/main.go @@ -0,0 +1,20 @@ +package main + +import ( + "fmt" + "log" + "moxitech/mechboard/api/internal/http" + "moxitech/mechboard/api/internal/parser" +) + +func main() { + res, err := http.Get("https://www.selenium.dev/") + if err != nil { + log.Fatalf("ERROR GET DATA FROM LINK : %v", err) + } + result, err := parser.ParseHtml(res, "div.col-lg-4:nth-child(2) > div:nth-child(1) > div:nth-child(1)", "h4") + if err != nil { + log.Fatalf("ERROR GET DATA FROM LINK : %v", err) + } + fmt.Printf("%v\n", result) +} diff --git a/server/api/go.mod b/server/api/go.mod new file mode 100644 index 0000000..23fb57d --- /dev/null +++ b/server/api/go.mod @@ -0,0 +1,10 @@ +module moxitech/mechboard/api + +go 1.22.7 + +require github.com/PuerkitoBio/goquery v1.9.3 + +require ( + github.com/andybalholm/cascadia v1.3.2 // indirect + golang.org/x/net v0.29.0 // indirect +) diff --git a/server/api/go.sum b/server/api/go.sum new file mode 100644 index 0000000..4fff810 --- /dev/null +++ b/server/api/go.sum @@ -0,0 +1,40 @@ +github.com/PuerkitoBio/goquery v1.9.3 h1:mpJr/ikUA9/GNJB/DBZcGeFDXUtosHRyRrwh7KGdTG0= +github.com/PuerkitoBio/goquery v1.9.3/go.mod h1:1ndLHPdTz+DyQPICCWYlYQMPl0oXZj0G6D4LCYA6u4U= +github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss= +github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU= +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/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= +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 v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c= +golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs= +golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns= +golang.org/x/net v0.29.0 h1:5ORfpBpCs4HzDYoodCDBbwHzdR5UrLBZ3sOnUJmFoHo= +golang.org/x/net v0.29.0/go.mod h1:gLkgy8jTGERgjzMic6DS9+SP0ajcu6Xu3Orq/SpETg0= +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/sync v0.1.0/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 v0.0.0-20210615035016-665e8c7367d1/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/sys v0.7.0/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/term v0.7.0/go.mod h1:P32HKFT3hSsZrRxla30E9HqToFYAQPCMs/zFMBUFqPY= +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 v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= +golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8= +golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8= +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/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= +golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= diff --git a/server/api/internal/http/http.go b/server/api/internal/http/http.go new file mode 100644 index 0000000..b64eab6 --- /dev/null +++ b/server/api/internal/http/http.go @@ -0,0 +1,22 @@ +package http + +import ( + "io" + "log" + "net/http" +) + +func Get(url string) (io.Reader, error) { + client := &http.Client{} + req, err := http.NewRequest("GET", url, nil) + if err != nil { + log.Printf("[GET] err! :: %v", err) + return nil, err + } + res, err := client.Do(req) + if err != nil { + log.Printf("[GET] err! :: %v", err) + return nil, err + } + return res.Body, nil +} diff --git a/server/api/internal/parser/html.go b/server/api/internal/parser/html.go new file mode 100644 index 0000000..8636ee7 --- /dev/null +++ b/server/api/internal/parser/html.go @@ -0,0 +1,30 @@ +package parser + +import ( + "io" + + "github.com/PuerkitoBio/goquery" +) + +// ParseHtml parse html from reader +// @reader - reader instance +// @findRule - find rule (css-selector, z-index, etc...) +// @tag - html tag, which text has needed from @reader +func ParseHtml(reader io.Reader, findRule string, tag string) ([]string, error) { + // Load the HTML document + var result []string + doc, err := goquery.NewDocumentFromReader(reader) + if err != nil { + return nil, err + } + + // Find the review items + doc.Find(findRule).Each(func(i int, s *goquery.Selection) { + // For each item found, get the text + text := s.Find(tag).Text() + // fmt.Printf("Найден: %d: %s\n", i+1, text) + result = append(result, text) + }) + return result, err + +}