commit 9fe9efbd1831aa8ca3459d849580a96dca728772 Author: christian Date: Sat Jun 8 16:11:40 2024 +0200 initial commit diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..dd569eb --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +/thehub_cache +/jobs.json \ No newline at end of file diff --git a/go.mod b/go.mod new file mode 100644 index 0000000..5f50063 --- /dev/null +++ b/go.mod @@ -0,0 +1,22 @@ +module go-scraper + +go 1.22.3 + +require ( + github.com/PuerkitoBio/goquery v1.9.2 // indirect + github.com/andybalholm/cascadia v1.3.2 // indirect + github.com/antchfx/htmlquery v1.3.1 // indirect + github.com/antchfx/xmlquery v1.4.0 // indirect + github.com/antchfx/xpath v1.3.0 // indirect + github.com/gobwas/glob v0.2.3 // indirect + github.com/gocolly/colly v1.2.0 // indirect + github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect + github.com/golang/protobuf v1.5.2 // indirect + github.com/kennygrant/sanitize v1.2.4 // indirect + github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d // indirect + github.com/temoto/robotstxt v1.1.2 // indirect + golang.org/x/net v0.26.0 // indirect + golang.org/x/text v0.16.0 // indirect + google.golang.org/appengine v1.6.8 // indirect + google.golang.org/protobuf v1.26.0 // indirect +) diff --git a/go.sum b/go.sum new file mode 100644 index 0000000..cf66d2f --- /dev/null +++ b/go.sum @@ -0,0 +1,76 @@ +github.com/PuerkitoBio/goquery v1.9.2 h1:4/wZksC3KgkQw7SQgkKotmKljk0M6V8TUvA8Wb4yPeE= +github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk= +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/antchfx/htmlquery v1.3.1 h1:wm0LxjLMsZhRHfQKKZscDf2COyH4vDYA3wyH+qZ+Ylc= +github.com/antchfx/htmlquery v1.3.1/go.mod h1:PTj+f1V2zksPlwNt7uVvZPsxpKNa7mlVliCRxLX6Nx8= +github.com/antchfx/xmlquery v1.4.0 h1:xg2HkfcRK2TeTbdb0m1jxCYnvsPaGY/oeZWTGqX/0hA= +github.com/antchfx/xmlquery v1.4.0/go.mod h1:Ax2aeaeDjfIw3CwXKDQ0GkwZ6QlxoChlIBP+mGnDFjI= +github.com/antchfx/xpath v1.3.0 h1:nTMlzGAK3IJ0bPpME2urTuFL76o4A96iYvoKFHRXJgc= +github.com/antchfx/xpath v1.3.0/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs= +github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y= +github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8= +github.com/gocolly/colly v1.2.0 h1:qRz9YAn8FIH0qzgNUw+HT9UN7wm1oF9OBAilwEWpyrI= +github.com/gocolly/colly v1.2.0/go.mod h1:Hof5T3ZswNVsOHYmba1u03W65HDWgpV5HifSuueE0EA= +github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE= +github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc= +github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk= +github.com/golang/protobuf v1.5.2 h1:ROPKBNFfQgOUMifHyP+KYbvpjbdoFNs+aK7DXlji0Tw= +github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY= +github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/kennygrant/sanitize v1.2.4 h1:gN25/otpP5vAsO2djbMhF/LQX6R7+O1TB4yv8NzpJ3o= +github.com/kennygrant/sanitize v1.2.4/go.mod h1:LGsjYYtgxbetdg5owWB2mpgUL6e2nfw2eObZ0u0qvak= +github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d h1:hrujxIzL1woJ7AwssoOcM/tq5JjjG2yYOc8odClEiXA= +github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d/go.mod h1:uugorj2VCxiV1x+LzaIdVa9b4S4qGAcH6cbhh4qVxOU= +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/temoto/robotstxt v1.1.2 h1:W2pOjSJ6SWvldyEuiFXNxz3xZ8aiWX5LbfDiOFd7Fxg= +github.com/temoto/robotstxt v1.1.2/go.mod h1:+1AmkuG3IYkh1kv0d2qEB9Le88ehNO0zwOr3ujewlOo= +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 v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs= +golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns= +golang.org/x/net v0.26.0 h1:soB7SVo0PWrY4vPW/+ay0jKDNScG2X9wFeYlXIvJsOQ= +golang.org/x/net v0.26.0/go.mod h1:5YKkiSynbBIh3p6iOc/vibscux0x38BZDkn8sCUPxHE= +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 v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ= +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/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= +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= +golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +google.golang.org/appengine v1.6.8 h1:IhEN5q69dyKagZPYMSdIjS2HqprW324FRQZJcGqPAsM= +google.golang.org/appengine v1.6.8/go.mod h1:1jJ3jBArFh5pcgW8gCtRJnepW8FzD1V44FJffLiz/Ds= +google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw= +google.golang.org/protobuf v1.26.0 h1:bxAC2xTBsZGibn2RTntX0oH50xLsqy1OxA9tTL3p/lk= +google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc= diff --git a/readme.md b/readme.md new file mode 100644 index 0000000..b1810ac --- /dev/null +++ b/readme.md @@ -0,0 +1,13 @@ +# The Hub Scraper + +This is a simple scraper that extracts job details from the [The Hub](https://thehub.io) website. + +## Usage + +To run the scraper, simply execute the following command: + +```bash +go run scraper.go +``` + +The scraper will create a `jobs.json` file in the current directory, which contains a list of job details in JSON format. diff --git a/scraper.go b/scraper.go new file mode 100644 index 0000000..00a6023 --- /dev/null +++ b/scraper.go @@ -0,0 +1,130 @@ +package main + +import ( + "encoding/json" + "fmt" + "log" + "os" + "strings" + + "github.com/gocolly/colly" +) + +type job struct { + Title string `json:"title"` + Logo string `json:"logo"` + Company string `json:"company"` + Location string `json:"location"` + Type string `json:"type"` + Description string `json:"description"` + Link string `json:"link"` + Skills skills `json:"skills"` +} + +type skills struct { + React bool `json:"react"` + Python bool `json:"python"` + Golang bool `json:"golang"` + Svelte bool `json:"svelte"` + Nextjs bool `json:"nextjs"` + Typescript bool `json:"typescript"` +} + +func skillChecker(description string) skills { + return skills{ + React: strings.Contains(description, "React"), + Python: strings.Contains(description, "Python"), + Golang: strings.Contains(description, "Go"), + Svelte: strings.Contains(description, "Svelte"), + Nextjs: strings.Contains(description, "Next.js"), + Typescript: strings.Contains(description, "TypeScript"), + } +} + +// Slice to store job details +var jobs []job + +func main() { + + fName := "jobs.json" + file, err := os.Create(fName) + if err != nil { + log.Fatalf("Cannot create file %q: %s", fName, err) + } + defer file.Close() + baseUrl := "https://thehub.io" + searchString := "https://thehub.io/jobs?roles=frontenddeveloper&roles=fullstackdeveloper&roles=backenddeveloper&roles=devops&paid=true&countryCode=DK&sorting=newJobs" + // Instantiate default collector + c := colly.NewCollector( + // visit only the hub + colly.AllowedDomains("www.thehub.io", "thehub.io"), + + // Cache responses to prevent multiple requests + colly.CacheDir("./thehub_cache"), + ) + + // Slice of excluded words in the job titles + excluded := []string{"senior", "lead"} + // Instantiate a new collector to visit the job details page + detailsCollector := c.Clone() + // On every
element with class "card__content attribute call callback + c.OnHTML("div[class=card__content]", func(e *colly.HTMLElement) { + // Get the title and ensure it doesn't contain any excluded words + title := e.ChildText("span.card-job-find-list__position") + for _, excludedWord := range excluded { + if strings.Contains(strings.ToLower(title), excludedWord) { + return + } + } + link := e.ChildAttr("a", "href") + fullLink := baseUrl + link + + detailsCollector.Visit(fullLink) + }) + + detailsCollector.OnRequest(func(r *colly.Request) { + fmt.Println("Visiting", r.URL.String()) + }) + + detailsCollector.OnHTML("div.view-job-details", func(e *colly.HTMLElement) { + // Get logo and trim the url + + logo := e.ChildAttr("div.media-item__image", "style") + cutLeft := "background-image:url(" + cutRight := ");" + trimmedLogo := strings.Trim(logo, cutLeft+cutRight) + + // Get company name + jobDetails := job{ + Title: e.ChildText("h2[class=view-job-details__title]"), + Logo: trimmedLogo, + Company: e.ChildText(".bullet-inline-list > a:first-child"), + Location: e.ChildText(".bullet-inline-list > a:nth-child(2)"), + Type: e.ChildText(".bullet-inline-list > a:nth-child(3)"), + Description: e.ChildText("content.text-block__content > span"), + Link: e.Request.URL.String(), + Skills: skillChecker(e.ChildText("content.text-block__content > span")), + } + jobs = append(jobs, jobDetails) + }) + // Handle pagination + c.OnHTML("a.page-link", func(e *colly.HTMLElement) { + nextPage := e.Attr("href") + if nextPage != "" { + fullNextPage := baseUrl + nextPage + fmt.Println("Visiting next page:", fullNextPage) + e.Request.Visit(fullNextPage) + } + }) + + c.Visit(searchString) + + // Encode jobs slice to JSON + encoder := json.NewEncoder(file) + encoder.SetIndent("", " ") // Pretty-print with indentation + if err := encoder.Encode(jobs); err != nil { + log.Fatalf("Cannot write to file %q: %s", fName, err) + } + + fmt.Println("Job details successfully written to", fName) +}