package pages import ( "codeberg.org/gothub/gothub/utils" "context" "github.com/carlmjohnson/requests" "github.com/gocolly/colly" "github.com/gofiber/fiber/v2" "github.com/gomarkdown/markdown" "log" "net/http" "os" ) type Repo struct { Fullname string Description string Parent string Stars string Forks string Watchers string Language []string License string DefaultBranch string Readme string } type RepoFiles struct { Name string Path string Type string Fullname string DefaultBranch string } func HandleRepo(c *fiber.Ctx) error { var repoArray []Repo var repoFilesArray []RepoFiles resp, statusErr := http.Get("https://github.com/" + c.Params("user") + "/" + c.Params("repo")) if statusErr != nil { log.Println(statusErr) } if resp.StatusCode == 404 { // I need a better way to do this return c.Status(404).Render("error", fiber.Map{ "title": "Error", "error": "Repository " + c.Params("user") + "/" + c.Params("repo") + " not found", }) } // Scraping Scrape := Repo{} UserAgent, ok := os.LookupEnv("GOTHUB_USER_AGENT") if !ok { UserAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36" } sc := colly.NewCollector(colly.AllowedDomains("github.com"), colly.UserAgent(UserAgent)) sc.OnHTML("div.Layout-sidebar", func(e *colly.HTMLElement) { Scrape.Fullname = c.Params("user") + "/" + c.Params("repo") Scrape.Description = e.ChildText("p.f4") Scrape.Stars = e.ChildText("a[href*='/" + c.Params("user") + "/" + c.Params("repo") + "/stargazers' i] strong") Scrape.Watchers = e.ChildText("a[href*='/" + c.Params("user") + "/" + c.Params("repo") + "/watchers' i] strong") Scrape.Forks = e.ChildText("a[href*='/" + c.Params("user") + "/" + c.Params("repo") + "/network/members' i] strong") Scrape.License = e.ChildText("a[data-analytics-event*='{\"category\":\"Repository Overview\",\"action\":\"click\",\"label\":\"location:sidebar;file:license\"}']") }) sc.OnHTML("div#readme", func(e *colly.HTMLElement) { Scrape.Readme = e.ChildText("a[href*='#readme']") }) sc.OnHTML("div.BorderGrid-cell ul.list-style-none", func(e *colly.HTMLElement) { e.ForEach("li.d-inline .d-inline-flex", func(i int, el *colly.HTMLElement) { Scrape.Language = append(Scrape.Language, el.ChildText("span.text-bold")+" "+el.ChildText("span:contains('%')")) }) }) sc.OnHTML("div#repository-container-header", func(e *colly.HTMLElement) { Scrape.Parent = e.ChildText("span.text-small a") }) sc.OnHTML("summary[title*='Switch branches or tags']", func(e *colly.HTMLElement) { Scrape.DefaultBranch = e.ChildText("span.css-truncate-target") }) sc.OnHTML("div.js-details-container div.Details-content--hidden-not-important", func(e *colly.HTMLElement) { e.ForEach("div.js-navigation-item", func(i int, el *colly.HTMLElement) { var FileType string if el.ChildAttr("div.flex-shrink-0 svg", "aria-label") == "Directory" { FileType = "dir" } else { FileType = "file" } repoFilesArray = append(repoFilesArray, RepoFiles{ Name: el.ChildText("div.flex-auto span.d-block a.js-navigation-open"), Path: el.ChildText("div.flex-auto span.d-block a.js-navigation-open"), Type: FileType, Fullname: Scrape.Fullname, DefaultBranch: Scrape.DefaultBranch, }) }) }) sc.Visit("https://github.com/" + c.Params("user") + "/" + c.Params("repo") + "/") // Add scrape-based info to repoArray repoArray = append(repoArray, Scrape) // README var readmee string err := requests. URL("https://raw.githubusercontent.com/" + c.Params("user") + "/" + c.Params("repo") + "/" + Scrape.DefaultBranch + "/" + Scrape.Readme). ToString(&readmee). Fetch(context.Background()) if err != nil { readmee = "" log.Println(err) } mightBeUnsafe := markdown.ToHTML([]byte(readmee), nil, nil) // Trust Nobody readmeOutput := utils.UGCPolicy().SanitizeBytes(mightBeUnsafe) return c.Render("repo", fiber.Map{ "title": "Repository " + c.Params("user") + "/" + c.Params("repo"), "repo": repoArray, "files": repoFilesArray, "readme": string(readmeOutput), }) }