home · contact · privacy
Use BeautifulSoup for HTML parsing.
authorChristian Heller <c.heller@plomlompom.de>
Tue, 19 Jan 2016 21:46:30 +0000 (22:46 +0100)
committerChristian Heller <c.heller@plomlompom.de>
Tue, 19 Jan 2016 21:46:30 +0000 (22:46 +0100)
plomlombot.py
requirements.txt

index f7c7e32..3e4734f 100755 (executable)
@@ -7,8 +7,7 @@ import select
 import time
 import re
 import requests
 import time
 import re
 import requests
-import html
-import html.parser
+import bs4
 
 # Defaults, may be overwritten by command line arguments.
 SERVER = "irc.freenode.net"
 
 # Defaults, may be overwritten by command line arguments.
 SERVER = "irc.freenode.net"
@@ -18,23 +17,6 @@ USERNAME = "plomlombot"
 NICKNAME = USERNAME
 
 
 NICKNAME = USERNAME
 
 
-class HTMLParser(html.parser.HTMLParser):
-    def __init__(self, html, tag):
-        super().__init__()
-        self._tag_to_check = tag
-        self._tag = ""
-        self.data = ""
-        self.feed(html)
-    def handle_starttag(self, tag, attrs):
-        if self.data == "" and tag == self._tag_to_check:
-            self._tag = tag
-    def handle_endtag(self, tag):
-        self._tag = ""
-    def handle_data(self, data):
-        if self._tag != "":
-            self.data = data
-
-
 class ExceptionForRestart(Exception):
     pass
 
 class ExceptionForRestart(Exception):
     pass
 
@@ -135,10 +117,11 @@ def lineparser_loop(io, nickname):
                         requests.exceptions.InvalidSchema) as error:
                     notice("TROUBLE FOLLOWING URL: " + str(error))
                     continue
                         requests.exceptions.InvalidSchema) as error:
                     notice("TROUBLE FOLLOWING URL: " + str(error))
                     continue
-                content = r.text
-                title = HTMLParser(content, "title").data
-                title = html.unescape(title)
-                notice("PAGE TITLE FOR URL: " + title)
+                title = bs4.BeautifulSoup(r.text).title
+                if title:
+                    notice("PAGE TITLE FOR URL: " + title.string)
+                else:
+                    notice("PAGE HAS NO TITLE TAG")
 
         sender = ""
         for rune in tokens[0]:
 
         sender = ""
         for rune in tokens[0]:
index ca0dee4..5263dff 100644 (file)
@@ -1 +1,2 @@
+beautifulsoup4==4.4.1
 requests==2.9.1
 requests==2.9.1