Use html5lib for BeautifulSoup parsing.

diff --git a/plomlombot.py b/plomlombot.py
index 1be105cbdf51325b4817177cb34f29860c57ac1a..6f6d33994255504e2ac4903cbe254d623db5fbdc 100755 (executable)
--- a/plomlombot.py
+++ b/plomlombot.py
@@ -322,7 +322,7 @@ def handle_url(url, notice, show_url=False):
         return
     if mobile_twitter_hack(url):
         return
         return
     if mobile_twitter_hack(url):
         return

-    title = bs4.BeautifulSoup(r.text, "html.parser").title
+    title = bs4.BeautifulSoup(r.text, "html5lib").title

     if title:
         prefix = "PAGE TITLE: "
         if show_url:
     if title:
         prefix = "PAGE TITLE: "
         if show_url:

diff --git a/requirements.txt b/requirements.txt
index 5263dff39003e50a9e6985d6d52abac8a644c1af..ed55ed599099a97fd80cac7795590c42114d6cf2 100644 (file)
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,4 @@
 beautifulsoup4==4.4.1
 requests==2.9.1
 beautifulsoup4==4.4.1
 requests==2.9.1

+html5lib==0.9999999
+six==1.10.0