added scraper for it-jobbank
This commit is contained in:
parent
979ed97738
commit
32f83e358b
4
.gitignore
vendored
4
.gitignore
vendored
@ -1,2 +1,4 @@
|
||||
/thehub_cache
|
||||
/jobs.json
|
||||
/thehub.json
|
||||
/itjobbank_cache
|
||||
/it-jobbank.json
|
||||
178
main.go
178
main.go
@ -12,15 +12,16 @@ import (
|
||||
)
|
||||
|
||||
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"`
|
||||
FirstSeen time.Time `json:"firstSeen"`
|
||||
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"`
|
||||
FirstSeen time.Time `json:"firstSeen"`
|
||||
Source string `json:"source"`
|
||||
}
|
||||
|
||||
type skills struct {
|
||||
@ -33,6 +34,9 @@ type skills struct {
|
||||
Tailwind bool `json:"tailwind"`
|
||||
}
|
||||
|
||||
// Utility functions
|
||||
|
||||
// Checks if a string contains any of the given keywords
|
||||
func skillChecker(description string) skills {
|
||||
return skills{
|
||||
React: strings.Contains(description, "React"),
|
||||
@ -44,7 +48,9 @@ func skillChecker(description string) skills {
|
||||
Tailwind: strings.Contains(description, "Tailwind"),
|
||||
}
|
||||
}
|
||||
func jobsToJson(file *os.File) {
|
||||
|
||||
// Converts job struct to json
|
||||
func jobsToJson(file *os.File, jobs []job, fName string) {
|
||||
// Encode jobs slice to JSON
|
||||
encoder := json.NewEncoder(file)
|
||||
encoder.SetIndent("", " ") // Pretty-print with indentation
|
||||
@ -55,24 +61,47 @@ func jobsToJson(file *os.File) {
|
||||
fmt.Println("Job details successfully written to", fName)
|
||||
}
|
||||
|
||||
func checkIfPaid(description string) {
|
||||
for _, keyword := range unpaidKeywords {
|
||||
if strings.Contains(strings.ToLower(description), keyword) {
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func checkIfStudent(description string) string {
|
||||
for _, keyword := range studentKeywords {
|
||||
if strings.Contains(strings.ToLower(description), keyword) {
|
||||
return "student"
|
||||
}
|
||||
}
|
||||
return "full time"
|
||||
}
|
||||
|
||||
// Slice to store job details
|
||||
var (
|
||||
jobs []job
|
||||
jobCount int
|
||||
maxJobs int = 30
|
||||
fName string = "jobs.json"
|
||||
excluded = []string{"senior", "lead", "founder", "cto", "vp of"}
|
||||
excluded = []string{"senior", "lead", "founder", "cto", "vp of", "erfaren", "arkitekt", "architect", "manager", "ulønnet", "unpaid", "praktik"}
|
||||
unpaidKeywords = []string{"unpaid", "praktik", "ulønnet"}
|
||||
studentKeywords = []string{"studerende", "studenter", "student", "medhjælper"}
|
||||
)
|
||||
|
||||
func scrapeHub() {
|
||||
// declare and initialize variables
|
||||
var (
|
||||
jobs []job
|
||||
jobCount int
|
||||
fName = "thehub.json"
|
||||
maxJobs = 30
|
||||
baseUrl = "https://thehub.io"
|
||||
searchString = "https://thehub.io/jobs?roles=frontenddeveloper&roles=fullstackdeveloper&roles=backenddeveloper&roles=devops&paid=true&countryCode=DK&sorting=newJobs"
|
||||
file, err = os.Create(fName)
|
||||
)
|
||||
|
||||
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
|
||||
@ -86,7 +115,9 @@ func scrapeHub() {
|
||||
detailsCollector := c.Clone()
|
||||
// On every <div> element with class "card__content attribute call callback
|
||||
c.OnHTML("div[class=card__content]", func(e *colly.HTMLElement) {
|
||||
//ensure only scrape the amount of jobs specified
|
||||
if jobCount >= maxJobs {
|
||||
return
|
||||
}
|
||||
|
||||
// Get the title and ensure it doesn't contain any excluded words
|
||||
title := e.ChildText("span.card-job-find-list__position")
|
||||
@ -114,14 +145,14 @@ func scrapeHub() {
|
||||
cutRight := ");"
|
||||
trimmedLogo := strings.Trim(logo, cutLeft+cutRight)
|
||||
|
||||
// Get job description
|
||||
// Get the HTML of the description
|
||||
// Get the HTML of the description and check to see if it's paid
|
||||
descriptionHTML, err := e.DOM.Find("content.text-block__content > span").Html()
|
||||
if err != nil {
|
||||
log.Printf("Error getting HTML of description: %s", err)
|
||||
return
|
||||
}
|
||||
// Get company name
|
||||
|
||||
// fill in the job struct
|
||||
jobDetails := job{
|
||||
Title: e.ChildText("h2[class=view-job-details__title]"),
|
||||
Logo: trimmedLogo,
|
||||
@ -132,13 +163,14 @@ func scrapeHub() {
|
||||
Link: e.Request.URL.String(),
|
||||
Skills: skillChecker(e.ChildText("content.text-block__content > span")),
|
||||
FirstSeen: time.Now(),
|
||||
Source: baseUrl,
|
||||
}
|
||||
jobs = append(jobs, jobDetails)
|
||||
jobCount++
|
||||
fmt.Println("Scraped job", jobCount)
|
||||
if jobCount == maxJobs {
|
||||
jobsToJson(file)
|
||||
os.Exit(0)
|
||||
if jobCount >= maxJobs {
|
||||
jobsToJson(file, jobs, fName)
|
||||
return
|
||||
}
|
||||
})
|
||||
// Handle pagination
|
||||
@ -146,7 +178,6 @@ func scrapeHub() {
|
||||
nextPage := e.Attr("href")
|
||||
if nextPage != "" {
|
||||
fullNextPage := baseUrl + nextPage
|
||||
fmt.Println("Visiting next page:", fullNextPage)
|
||||
e.Request.Visit(fullNextPage)
|
||||
}
|
||||
})
|
||||
@ -155,8 +186,103 @@ func scrapeHub() {
|
||||
|
||||
}
|
||||
|
||||
func scrapeItJobBank() {
|
||||
// declare and initialize variables
|
||||
var (
|
||||
jobs []job
|
||||
jobCount int
|
||||
fName = "it-jobbank.json"
|
||||
maxJobs = 30
|
||||
baseUrl = "https://www.it-jobbank.dk"
|
||||
searchString = "https://www.it-jobbank.dk/jobsoegning"
|
||||
file, err = os.Create(fName)
|
||||
)
|
||||
if err != nil {
|
||||
log.Fatalf("Cannot create file %q: %s", fName, err)
|
||||
}
|
||||
defer file.Close()
|
||||
|
||||
// Instantiate default collector
|
||||
c := colly.NewCollector(
|
||||
// visit only the hub
|
||||
colly.AllowedDomains("www.it-jobbank.dk", "it-jobbank.dk"),
|
||||
|
||||
// Cache responses to prevent multiple requests
|
||||
colly.CacheDir("./itjobbank_cache"),
|
||||
)
|
||||
|
||||
// Instantiate a new collector to visit the job details page
|
||||
detailsCollector := c.Clone()
|
||||
// On every <div> element with class "card__content attribute call callback
|
||||
c.OnHTML("div[class=result]", func(e *colly.HTMLElement) {
|
||||
if jobCount >= maxJobs {
|
||||
return
|
||||
}
|
||||
// Get the title and ensure it doesn't contain any excluded words
|
||||
title := e.ChildText("h3.job-title > a")
|
||||
for _, excludedWord := range excluded {
|
||||
if strings.Contains(strings.ToLower(title), excludedWord) {
|
||||
return
|
||||
}
|
||||
}
|
||||
fullLink := e.ChildAttr("h3.job-title > a", "href")
|
||||
|
||||
detailsCollector.Visit(fullLink)
|
||||
})
|
||||
|
||||
detailsCollector.OnRequest(func(r *colly.Request) {
|
||||
fmt.Println("Visiting", r.URL.String())
|
||||
})
|
||||
|
||||
detailsCollector.OnHTML("section > div", func(e *colly.HTMLElement) {
|
||||
// get the description as html
|
||||
descriptionHTML, err := e.DOM.Find("div[id=job_ad]").Html()
|
||||
if err != nil {
|
||||
log.Printf("Error getting HTML of description: %s", err)
|
||||
return
|
||||
}
|
||||
// Check if the job is paid
|
||||
checkIfPaid(descriptionHTML)
|
||||
// fill in the job struct
|
||||
title := e.ChildText("h1.title")
|
||||
if title == "" {
|
||||
title = e.ChildText("h1[id=jobtitle]")
|
||||
}
|
||||
jobDetails := job{
|
||||
Title: title,
|
||||
Logo: baseUrl + e.ChildAttr("div.companmony-logo > img", "src"),
|
||||
Company: e.ChildText("p.published"),
|
||||
Location: e.ChildText("div.job-location > p.caption"),
|
||||
Type: checkIfStudent(descriptionHTML),
|
||||
Description: descriptionHTML,
|
||||
Link: e.Request.URL.String(),
|
||||
Skills: skillChecker(descriptionHTML),
|
||||
FirstSeen: time.Now(),
|
||||
Source: baseUrl,
|
||||
}
|
||||
jobs = append(jobs, jobDetails)
|
||||
jobCount++
|
||||
fmt.Println("Scraped job", jobCount)
|
||||
if jobCount >= maxJobs {
|
||||
jobsToJson(file, jobs, fName)
|
||||
return
|
||||
}
|
||||
})
|
||||
// Handle pagination
|
||||
c.OnHTML("a.page-link", func(e *colly.HTMLElement) {
|
||||
if jobCount >= maxJobs {
|
||||
return
|
||||
}
|
||||
nextPage := e.Attr("href")
|
||||
if nextPage != "" {
|
||||
e.Request.Visit(nextPage)
|
||||
}
|
||||
})
|
||||
|
||||
c.Visit(searchString)
|
||||
}
|
||||
|
||||
func main() {
|
||||
scrapeHub()
|
||||
scrapeItJobBank()
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user