NEW: html2text dumps html as plaintext

2023-12-04 15:09:02 +08:00 · 2023-12-04 15:09:02 +08:00 · 41de1c9b5b
commit 41de1c9b5b
parent 6ea0be7698
1 changed files with 6 additions and 0 deletions
--- a/py/html2text.py
+++ b/py/html2text.py
@ -0,0 +1,6 @@
+from urllib import request
+import html2text
+
+url = 'https://duckduckgo.com'
+text = request.urlopen(url).read().decode('utf8') 
+print(html2text.html2text(text))