commit a0fb036da5505cbcd2e4f20677ac9a099ccee404 Author: PhatPhuckDave Date: Tue Nov 5 22:42:46 2024 +0100 Initial commit diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..0c6bcc4 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +main.log +test.html diff --git a/go.mod b/go.mod new file mode 100644 index 0000000..55601eb --- /dev/null +++ b/go.mod @@ -0,0 +1,13 @@ +module wowdocscraper + +go 1.23.2 + +require ( + github.com/PuerkitoBio/goquery v1.10.0 + golang.org/x/time v0.7.0 +) + +require ( + github.com/andybalholm/cascadia v1.3.2 // indirect + golang.org/x/net v0.29.0 // indirect +) diff --git a/go.sum b/go.sum new file mode 100644 index 0000000..278cc0d --- /dev/null +++ b/go.sum @@ -0,0 +1,42 @@ +github.com/PuerkitoBio/goquery v1.10.0 h1:6fiXdLuUvYs2OJSvNRqlNPoBm6YABE226xrbavY5Wv4= +github.com/PuerkitoBio/goquery v1.10.0/go.mod h1:TjZZl68Q3eGHNBA8CWaxAN7rOU1EbDz3CWuolcO5Yu4= +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/time v0.7.0 h1:ntUhktv3OPE6TgYxXWv9vKvUSJyIFJlyohwbkEwPrKQ= +golang.org/x/time v0.7.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM= +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/html-getter.go b/html-getter.go new file mode 100644 index 0000000..28a2e36 --- /dev/null +++ b/html-getter.go @@ -0,0 +1,30 @@ +package main + +import ( + "fmt" + "io" + "net/http" + + "golang.org/x/time/rate" +) + +var LIMITER = rate.NewLimiter(rate.Limit(1), 2) + +func FetchFull(url string) (string, error) { + res, err := http.Get(url) + if err != nil { + return "", fmt.Errorf("Error fetching %s: %v", url, err) + } + defer res.Body.Close() + + if res.StatusCode != http.StatusOK { + return "", fmt.Errorf("Error fetching %s, returned code %d: %v", url, res.StatusCode, err) + } + + body, err := io.ReadAll(res.Body) + if err != nil { + return "", fmt.Errorf("Error reading body of %s: %v", url, err) + } + + return string(body), nil +} diff --git a/html-parser.go b/html-parser.go new file mode 100644 index 0000000..f653bcf --- /dev/null +++ b/html-parser.go @@ -0,0 +1,49 @@ +package main + +import ( + "fmt" + "strings" + + "github.com/PuerkitoBio/goquery" +) + +func ParseHTML(html string) ([]string, error) { + res := []string{} + doc, err := goquery.NewDocumentFromReader(strings.NewReader(html)) + if err != nil { + return res, fmt.Errorf("failed parsing html: %v", err) + } + + doc.Find("tr > td > a").Each(func(i int, s *goquery.Selection) { + href, exists := s.Attr("href") + if !exists { + Warning.Printf("href not found for element %v", s) + return + } + res = append(res, href) + }) + return res, nil +} + +//doc, err := goquery.NewDocumentFromReader(strings.NewReader(*task.Html)) +//if err != nil { +// Error.Printf("failed to parse html: %v", err) +// return +//} + +//doc.Find("img").Each(func(i int, s *goquery.Selection) { +// parent := s.Parent() +// if parent.Is("a") { +// href, _ := parent.Attr("href") +// href, ok := fixLink(href) +// if ok { +// hw.output <- &ImageDownloadTask{Url: &href, Topic: task.Topic} +// } +// } else { +// src, _ := s.Attr("src") +// src, ok := fixLink(src) +// if ok { +// hw.output <- &ImageDownloadTask{Url: &src, Topic: task.Topic} +// } +// } +//}) diff --git a/main.go b/main.go new file mode 100644 index 0000000..8a23b43 --- /dev/null +++ b/main.go @@ -0,0 +1,51 @@ +package main + +import ( + _ "embed" + "fmt" + "io" + "log" + "os" +) + +var url = `https://wowprogramming.com/docs/api.html` + +var Error *log.Logger +var Warning *log.Logger + +func init() { + log.SetFlags(log.Lmicroseconds | log.Lshortfile) + logFile, err := os.Create("main.log") + if err != nil { + log.Printf("Error creating log file: %v", err) + os.Exit(1) + } + logger := io.MultiWriter(os.Stdout, logFile) + log.SetOutput(logger) + + Error = log.New(io.MultiWriter(logFile, os.Stderr, os.Stdout), + fmt.Sprintf("%sERROR:%s ", "\033[0;101m", "\033[0m"), + log.Lmicroseconds|log.Lshortfile) + Warning = log.New(io.MultiWriter(logFile, os.Stdout), + fmt.Sprintf("%sWarning:%s ", "\033[0;93m", "\033[0m"), + log.Lmicroseconds|log.Lshortfile) +} + +//go:embed test.html +var html string + +func main() { + //res, err := FetchFull(url) + //if err != nil { + // Error.Printf("Error fetching %s: %v", url, err) + // return + //} + + //os.WriteFile("test.html", []byte(res), 0644) + foo, err := ParseHTML(html) + if err != nil { + Error.Printf("Error parsing HTML: %v", err) + return + } + log.Printf("%#v", foo) +}