X-Git-Url: https://plomlompom.com/repos/%7B%7Bdb.prefix%7D%7D/task?a=blobdiff_plain;f=plomlombot.py;h=fe9c6d8d283a3a7d33fec14903c9534819ea2642;hb=60133e10b2df0c671574e294e835d39b8cbf23a2;hp=5fcd517a95f563cfba7a00146d1e6359780a0472;hpb=20c385a79d109d1da623c517c9458d02e79c343c;p=plomlombot-irc.git
diff --git a/plomlombot.py b/plomlombot.py
index 5fcd517..fe9c6d8 100755
--- a/plomlombot.py
+++ b/plomlombot.py
@@ -6,8 +6,12 @@ import datetime
import select
import time
import re
-import urllib.request
-import html
+import requests
+import bs4
+import random
+import hashlib
+import os
+import plomsearch
# Defaults, may be overwritten by command line arguments.
SERVER = "irc.freenode.net"
@@ -66,7 +70,11 @@ class IO:
self._pingtest(send_ping)
return None
self.last_pong = time.time()
- received_runes = self.socket.recv(1024).decode("UTF-8")
+ received_bytes = self.socket.recv(1024)
+ try:
+ received_runes = received_bytes.decode("UTF-8")
+ except UnicodeDecodeError:
+ received_runes = received_bytes.decode("latin1")
if len(received_runes) == 0:
print("SOCKET CONNECTION BROKEN")
raise ExceptionForRestart
@@ -98,30 +106,109 @@ def lineparser_loop(io, nickname):
def act_on_privmsg(tokens):
+ 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]
+
+ def handle_url(url, show_url=False):
+
+ def mobile_twitter_hack(url):
+ re1 = 'https?://(mobile.twitter.com/)[^/]+(/status/)'
+ re2 = 'https?://mobile.twitter.com/([^/]+)/status/' \
+ + '([^\?/]+)'
+ m = re.search(re1, url)
+ if m and m.group(1) == 'mobile.twitter.com/' \
+ and m.group(2) == '/status/':
+ m = re.search(re2, url)
+ url = 'https://twitter.com/' + m.group(1) + '/status/' \
+ + m.group(2)
+ handle_url(url, True)
+ return True
+
try:
- webpage = urllib.request.urlopen(url, timeout=15)
- except (urllib.error.HTTPError, urllib.error.URLError,
- UnicodeError) as error:
- print("TROUBLE FOLLOWING URL: " + str(error))
- continue
- charset = webpage.info().get_content_charset()
- if not charset:
- charset = "utf-8"
- content_type = webpage.info().get_content_type()
- if content_type not in ('text/html', 'text/xml',
- 'application/xhtml+xml'):
- print("TROUBLE INTERPRETING URL: bad content type "
- + content_type)
- continue
- content = webpage.read().decode(charset)
- title = str(content).split('
')[1].split('')[0]
- title = html.unescape(title)
- io.send_line("PRIVMSG " + target + " :page title for url: "
- + title)
+ 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))
+ return
+ if mobile_twitter_hack(url):
+ return
+ title = bs4.BeautifulSoup(r.text).title
+ if title:
+ prefix = "PAGE TITLE: "
+ if show_url:
+ prefix = "PAGE TITLE FOR <" + url + ">: "
+ notice(prefix + title.string.strip())
+ else:
+ notice("PAGE HAS NO TITLE TAG")
+
+ matches = re.findall("(https?://[^\s>]+)", msg)
+ for i in range(len(matches)):
+ handle_url(matches[i])
+
+ 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 and tokens[1] != "search") or \
+ (len(tokens) == 2 and
+ (tokens[1] == "search" or not tokens[1].isdigit())):
+ notice("SYNTAX: !quote [int] OR !quote search QUERY")
+ notice("QUERY may be a boolean grouping of quoted or "\
+ + "unquoted search terms, examples:")
+ notice("!quote search foo")
+ notice("!quote search foo AND (bar OR NOT baz)")
+ notice("!quote search \"foo\\\"bar\" AND "\
+ + "('NOT\"' AND \"'foo'\" OR 'bar\\'baz')")
+ 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
+ elif len(tokens) > 2:
+ query = str.join(" ", tokens[2:])
+ try:
+ results = plomsearch.search(query, lines)
+ except plomsearch.LogicParserError as err:
+ notice("FAILED QUERY PARSING: " + str(err))
+ return
+ if len(results) == 0:
+ notice("NO QUOTES MATCHING QUERY")
+ else:
+ for result in results:
+ notice("QUOTE #" + str(result[0] + 1) + " : "
+ + result[1])
+ return
+ else:
+ i = random.randrange(len(lines))
+ notice("QUOTE #" + str(i + 1) + ": " + lines[i])
sender = ""
for rune in tokens[0]:
@@ -139,6 +226,7 @@ def lineparser_loop(io, nickname):
if receiver != nickname:
target = receiver
msg = str.join(" ", tokens[3:])[1:]
+ command_check(msg)
url_check(msg)
while True: