noham/papeer
1
0
Fork 0
mirror of https://github.com/NohamR/papeer.git synced 2026-05-25 04:17:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

add html format, handle lazy loading images

Browse Source
This commit is contained in:
lapwat
2022-08-09 18:21:18 +02:00
parent 97e7d7a5bb
commit d73ae0a73b
8 changed files with 137 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
book/scraper_test.go
View File

@@ -68,7 +68,7 @@ func TestContent(t *testing.T) {
c := NewChapterFromURL("https://books.lapw.at/", "", []*ScrapeConfig{config}, 0, func(index int, name string) {})
got := c.Content()
want := "<div id=\"readability-page-1\" class=\"page\">\n \n <main>\n \n <article>\n \n <ul>\n \n <li>\n <a href=\"https://books.lapw.at/posts/ren%C3%A9-descartes-discours-de-la-m%C3%A9thode/\">Discours de la Méthode</a>\n <span>\n <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n <title>clock</title>\n <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 98 min read -\n 1637\n </span>\n </li>\n \n <li>\n <a href=\"https://books.lapw.at/posts/adam-wiggins-the-twelve-factor-app/\">The Twelve-Factor App</a>\n <span>\n <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n <title>clock</title>\n <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 22 min read -\n 2011\n </span>\n </li>\n \n </ul>\n \n\n\n\n </article>\n\n </main>\n \n\n</div>"
want := "\n \n <main>\n \n <article>\n \n <ul>\n \n <li>\n <a href=\"https://books.lapw.at/posts/ren%C3%A9-descartes-discours-de-la-m%C3%A9thode/\">Discours de la Méthode</a>\n <span>\n <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n <title>clock</title>\n <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 98 min read -\n 1637\n </span>\n </li>\n \n <li>\n <a href=\"https://books.lapw.at/posts/adam-wiggins-the-twelve-factor-app/\">The Twelve-Factor App</a>\n <span>\n <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n <title>clock</title>\n <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 22 min read -\n 2011\n </span>\n </li>\n \n </ul>\n \n\n\n\n </article>\n\n </main>\n \n\n"
if got != want {
t.Errorf("got %v, wanted %v", got, want)