| 322 | } |
| 323 | |
| 324 | func parseCopyrightNotices(input string) []CopyrightNotice { |
| 325 | doc, err := html.Parse(strings.NewReader("<ul>" + input + "</ul>")) |
| 326 | if err != nil { |
| 327 | log.Fatal(err) |
| 328 | } |
| 329 | |
| 330 | var notices []CopyrightNotice |
| 331 | |
| 332 | typ := TypeJS |
| 333 | |
| 334 | var f func(*html.Node) |
| 335 | f = func(n *html.Node) { |
| 336 | if n.Type == html.ElementNode && n.Data == "li" { |
| 337 | var notice CopyrightNotice |
| 338 | var aFound bool |
| 339 | |
| 340 | for c := n.FirstChild; c != nil; c = c.NextSibling { |
| 341 | if c.Type == html.ElementNode && c.Data == "a" { |
| 342 | aFound = true |
| 343 | for _, attr := range c.Attr { |
| 344 | if attr.Key == "href" { |
| 345 | notice.URL = attr.Val |
| 346 | } |
| 347 | } |
| 348 | if c.FirstChild != nil && c.FirstChild.Type == html.TextNode { |
| 349 | notice.Name = strings.TrimSpace(c.FirstChild.Data) |
| 350 | } |
| 351 | } else if c.Type == html.TextNode && aFound { |
| 352 | // Anything after <a> is considered the copyright |
| 353 | notice.Copyright = strings.TrimSpace(html.UnescapeString(c.Data)) |
| 354 | notice.Copyright = strings.Trim(notice.Copyright, "., ") |
| 355 | } |
| 356 | if typ == TypeJS && strings.Contains(notice.URL, "AudriusButkevicius") { |
| 357 | typ = TypeKeep |
| 358 | } |
| 359 | notice.Type = typ |
| 360 | var buf strings.Builder |
| 361 | _ = html.Render(&buf, n) |
| 362 | notice.HTML = buf.String() |
| 363 | } |
| 364 | |
| 365 | notice.Copyright = strings.ReplaceAll(notice.Copyright, "©", "©") |
| 366 | notice.HTML = strings.ReplaceAll(notice.HTML, "©", "©") |
| 367 | notices = append(notices, notice) |
| 368 | } |
| 369 | for c := n.FirstChild; c != nil; c = c.NextSibling { |
| 370 | f(c) |
| 371 | } |
| 372 | } |
| 373 | |
| 374 | f(doc) |
| 375 | |
| 376 | return notices |
| 377 | } |
| 378 | |
| 379 | func parseGitHubURL(u string) (string, string) { |
| 380 | parsed, err := url.Parse(u) |