X-Git-Url: https://plomlompom.com/repos/foo.html?a=blobdiff_plain;f=plomlombot.py;h=b45c67a7aa12feeee10695c218f6a05dfe1d1912;hb=d74caeac225204bc1f9e5a978678f741ac7dfaf3;hp=9e9d0a44ce21bc1d07204dcb9780c54ac1b31d0e;hpb=9260bc740d86b0b83d90c31eea2f898dfb2cf594;p=plomlombot-irc.git
diff --git a/plomlombot.py b/plomlombot.py
index 9e9d0a4..b45c67a 100755
--- a/plomlombot.py
+++ b/plomlombot.py
@@ -6,10 +6,11 @@ import datetime
import select
import time
import re
-import urllib.request
-import http.client
-import html
-import html.parser
+import requests
+import bs4
+import random
+import hashlib
+import os
# Defaults, may be overwritten by command line arguments.
SERVER = "irc.freenode.net"
@@ -19,23 +20,6 @@ USERNAME = "plomlombot"
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
@@ -121,37 +105,66 @@ def lineparser_loop(io, nickname):
def act_on_privmsg(tokens):
- def url_check(msg):
-
- def notice(msg):
- io.send_line("NOTICE " + target + " :" + msg)
+ def notice(msg):
+ io.send_line("NOTICE " + target + " :" + msg)
+ def url_check(msg):
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.InvalidURL,
+ 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 = 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: " + title.string.strip())
+ else:
+ notice("PAGE HAS NO TITLE TAG")
+
+ def command_check(msg):
+ if msg[0] != "!":
+ return
+ tokens = msg[1:].split()
+ hash_string = hashlib.md5(target.encode("utf-8")).hexdigest()
+ quotesfile_name = "quotes_" + hash_string
+ if tokens[0] == "addquote":
+ if not os.access(quotesfile_name, os.F_OK):
+ quotesfile = open(quotesfile_name, "w")
+ quotesfile.write("QUOTES FOR " + target + ":\n")
+ quotesfile.close()
+ quotesfile = open(quotesfile_name, "a")
+ quotesfile.write(str.join(" ", tokens[1:]) + "\n")
+ quotesfile.close()
+ quotesfile = open(quotesfile_name, "r")
+ lines = quotesfile.readlines()
+ quotesfile.close()
+ notice("ADDED QUOTE #" + str(len(lines) - 1))
+ elif tokens[0] == "quote":
+ if len(tokens) > 2 or \
+ (len(tokens) == 2 and not tokens[1].isdigit()):
+ notice("SYNTAX: !quote [int]")
+ return
+ if not os.access(quotesfile_name, os.F_OK):
+ notice("NO QUOTES AVAILABLE")
+ return
+ quotesfile = open(quotesfile_name, "r")
+ lines = quotesfile.readlines()
+ quotesfile.close()
+ lines = lines[1:]
+ if len(tokens) == 2:
+ i = int(tokens[1])
+ if i == 0 or i > len(lines):
+ notice("THERE'S NO QUOTE OF THAT INDEX")
+ return
+ i = i - 1
+ else:
+ i = random.randrange(len(lines))
+ notice("QUOTE #" + str(i + 1) + ": " + lines[i])
sender = ""
for rune in tokens[0]:
@@ -169,6 +182,7 @@ def lineparser_loop(io, nickname):
if receiver != nickname:
target = receiver
msg = str.join(" ", tokens[3:])[1:]
+ command_check(msg)
url_check(msg)
while True: