From: Christian Heller Date: Tue, 19 Jan 2016 21:05:49 +0000 (+0100) Subject: Use request library to simplify page retrieval code. X-Git-Url: https://plomlompom.com/repos/%7B%7Bprefix%7D%7D/add_task?a=commitdiff_plain;h=a7db2ddce21f684abf6d835e9450fcf370caa5f2;p=plomlombot-irc.git Use request library to simplify page retrieval code. --- diff --git a/plomlombot.py b/plomlombot.py index 9e9d0a4..f7c7e32 100755 --- a/plomlombot.py +++ b/plomlombot.py @@ -6,8 +6,7 @@ import datetime import select import time import re -import urllib.request -import http.client +import requests import html import html.parser @@ -129,26 +128,14 @@ 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) + content = r.text title = HTMLParser(content, "title").data title = html.unescape(title) notice("PAGE TITLE FOR URL: " + title) diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..ca0dee4 --- /dev/null +++ b/requirements.txt @@ -0,0 +1 @@ +requests==2.9.1