use dateutil to parse rfc3339 datetime strings in <time> elements, if they are present.

tge/scrapers/yuku.py

@@ -1,7 +1,11 @@
 from ..model import User, Category, Forum, Board, Post, Thread
 from urllib.parse import urlparse
+from time import strptime, mktime
+import dateutil.parser
 from pyquery import PyQuery as pq
 
+time_format = "%b %d %y %I:%M %p"
+
 def can_scrape_url (url):
     return ".fr.yuku.com" in url
 
@@ -76,6 +80,11 @@ def scrape_thread (url):
         else:
             signature = None
 
+        if date_element.find("time"):
+            timestamp = dateutil.parser.parse(date_element.text()).timestamp()
+        else:
+            timestamp = mktime(strptime(date_element.text(), time_format))
+
         thread.children.append(Post(
             author=User(
                 name=user_header.find("p > a").eq(0).text(),
@@ -84,7 +93,7 @@ def scrape_thread (url):
                 subtitle=user_header.find(".custom_title").text(),
                 signature=signature
             ),
-            timestamp=date_element.text(),
+            timestamp=timestamp,
             body=post_content_container.html().strip()
         ))