X-Git-Url: https://plomlompom.com/repos/%7B%7Bprefix%7D%7D/edit?a=blobdiff_plain;f=plomlombot.py;h=3e4734fa2ec2403aa093768623e1ca9b189d5cd8;hb=d66da409aaafb766eae1e0af1a9c16ae8520510c;hp=8ac8f01c00cf0cc4e00ad6e4a664a743926ac2f6;hpb=73d956fc4322397624652d1a63341f3092988679;p=plomlombot-irc.git diff --git a/plomlombot.py b/plomlombot.py index 8ac8f01..3e4734f 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -6,9 +6,8 @@ import datetime import select import time import re -import urllib.request -import http.client -import html +import requests +import bs4 # Defaults, may be overwritten by command line arguments. SERVER = "irc.freenode.net" @@ -111,29 +110,18 @@ def lineparser_loop(io, nickname): matches = re.findall("(https?://[^\s>]+)", msg) for i in range(len(matches)): url = matches[i] - request = urllib.request.Request(url, headers={ - "User-Agent": "plomlombot" - }) try: - webpage = urllib.request.urlopen(request, timeout=15) - except (urllib.error.HTTPError, urllib.error.URLError, - UnicodeError, http.client.BadStatusLine) as error: + r = requests.get(url, timeout=15) + except (requests.exceptions.TooManyRedirects, + requests.exceptions.ConnectionError, + requests.exceptions.InvalidSchema) as error: notice("TROUBLE FOLLOWING URL: " + str(error)) continue - charset = webpage.info().get_content_charset() - if not charset: - notice("TROUBLE READING PAGE TITLE: no charset in header") - continue - content_type = webpage.info().get_content_type() - if content_type not in ('text/html', 'text/xml', - 'application/xhtml+xml'): - notice("TROUBLE READING PAGE TITLE: bad content type " - + content_type) - continue - content = webpage.read().decode(charset) - title = str(content).split('