initial commit

bot.py

+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+
+# twisted imports
+from twisted.words.protocols import irc
+from twisted.internet import reactor, protocol
+from twisted.python import log
+
+# system imports
+import time, sys
+
+import legifrance
+import random
+import re
+
+class MessageLogger:
+    
+    def log(self, message):
+        print message
+
+class MmBot(irc.IRCClient):
+    
+    def __init__(self):
+        self.nickname = 'legifrance'
+        self.codes = legifrance.codes('legifrance.conf')
+        self.view = {}
+
+    def connectionMade(self):
+        irc.IRCClient.connectionMade(self)
+        self.logger = MessageLogger()
+        self.logger.log("[connected at %s]" % 
+                        time.asctime(time.localtime(time.time())))
+
+    def connectionLost(self, reason):
+        irc.IRCClient.connectionLost(self, reason)
+        self.logger.log("[disconnected at %s]" % 
+                        time.asctime(time.localtime(time.time())))
+
+    # callbacks for events
+
+    def signedOn(self):
+        """Called when bot has succesfully signed on to server."""
+        self.join(self.factory.channel)
+
+    def kickedFrom(self, channel, kicker, message):
+        self.logger.log("[kicked from %s by %s at %s]" % 
+                ( channel, kicker,
+                        time.asctime(time.localtime(time.time())))
+                )
+
+    def joined(self, channel):
+        """This will get called when the bot joins the channel."""
+        self.logger.log("[I have joined %s]" % channel)
+
+    def privmsg(self, user, channel, msg):
+        """This will get called when the bot receives a message."""
+        user = user.split('!', 1)[0]
+        self.logger.log("<%s> %s" % (user, msg))
+        
+        # Check to see if they're sending me a private message
+        if channel == self.nickname:
+            if re.match('help',msg):
+                rep = "Commandes disponnibles en query:\n"
+                rep+= " - list\n"
+                rep+= " - add <codename> <codeid> (e.g. \"add CP LEGITEXT000006070719\")\n"
+                rep+= " - expire <codename> (e.g. \"expire CP\")\n"
+                rep+= " - reloadconf\n"
+                rep+= " - join <channel>\n"
+                rep+= "Commandes disponnibles sur les chans:\n"
+                rep+= " - !legifrance join <channel>\n"
+                rep+= " - !legifrance part\n"
+                self.msg(user, rep)
+
+            if re.match('list',msg):
+                rep = "Codes disponnibles :\n"
+                for c in self.codes.conf['codeids'].keys():
+                    rep += ' - %s : %s\n' % (c,self.codes.conf['codeids'][c])
+                self.msg(user, rep)
+
+            a=re.match('add ([A-Za-z0-9]+) ([A-Za-z0-9]+)', msg)
+            if a:
+                codename = a.groups()[0]
+                codeid = a.groups()[1]
+                if self.codes.conf['codeids'].has_key(codename):
+                    self.msg(user, "Ce code existe.")
+                else:
+                    self.codes.conf['codeids'][codename]=codeid
+                    self.codes.conf.write()
+                    self.msg(user, "done")
+
+            a=re.match('expire ([A-Za-z0-9]+)', msg)
+            if a:
+                codename = a.groups()[0]
+                if not self.codes.conf['codeids'].has_key(codename):
+                    self.msg(user, "Ce code n'existe pas.")
+                if self.codes.force_code_reload(codename):
+                    self.msg(user, "done")
+                else:
+                    self.msg(user, "nothing to do")
+
+            if re.match('reloadconf', msg):
+                self.codes.conf.reload()
+                self.msg(user, "done")
+
+            a=re.match('join (#[A-Za-z0-9-]+)', msg)
+            if a:
+                self.join(a.groups()[0])
+
+        else:
+            # public
+            
+            a=re.match('!legifrance join (#[A-Za-z0-9-]+)', msg)
+            if a:
+                self.join(a.groups()[0])
+
+            if re.match('!legifrance part', msg):
+                self.part(channel)
+
+            # coeur de metier
+            m = msg
+            while True:
+                a = re.match('.*?\[([A-Za-z0-9]+) ([^ \]]+)\]', m)
+                if a is None:
+                    break
+                codename = a.groups()[0]
+                codeid = a.groups()[1]
+
+                trop_jeune = False
+                if self.view.has_key( (channel,codename,codeid) ):
+                    if time.time()-self.view[(channel,codename,codeid)] < 300:
+                        trop_jeune = True
+
+                if not trop_jeune:
+                    link = self.codes.get(codename,codeid)
+                    if not link is None:
+                        self.msg(channel,'[%s %s]: %s' % (codename, codeid, link))
+                        self.view[(channel,codename,codeid)] = time.time()
+                m= re.sub('\[([A-Za-z0-9]+) ([^ \]]+)\]','',m,1)
+
+
+    def action(self, user, channel, msg):
+        """This will get called when the bot sees someone do an action."""
+        user = user.split('!', 1)[0]
+        self.logger.log("* %s %s" % (user, msg))
+
+    def irc_NICK(self, prefix, params):
+        """Called when an IRC user changes their nickname."""
+        old_nick = prefix.split('!')[0]
+        new_nick = params[0]
+        self.logger.log("%s is now known as %s" % (old_nick, new_nick))
+
+
+class MmBotFactory(protocol.ClientFactory):
+
+    def __init__(self):
+        self.channel = "#legitest"
+
+    def buildProtocol(self, addr):
+        p = MmBot()
+        p.factory = self
+        return p
+
+    def clientConnectionLost(self, connector, reason):
+        connector.connect()
+
+    def clientConnectionFailed(self, connector, reason):
+        print "connection failed:", reason
+        reactor.stop()
+
+
+if __name__ == '__main__':
+    log.startLogging(sys.stdout)
+    
+    f = MmBotFactory()
+
+    reactor.connectTCP("irc.crans.org", 6667, f)
+
+    reactor.run()

legifrance.conf

+expire = 2592000
+[codeids]
+CP = LEGITEXT000006070719
+CPP = LEGITEXT000006071154
+CC = LEGITEXT000006070721
+CPC = LEGITEXT000006070716
+CR = LEGITEXT000006071367
+CConso = LEGITEXT000006069565
+CD = LEGITEXT000006071307
+CGI = LEGITEXT000006069577
+CMF = LEGITEXT000006072026
+CPCE = LEGITEXT000006070987

legifrance.py

+import requests
+import re
+import time
+import configobj
+
+def get_code(codename,codeids):
+
+    if not codeids.has_key(codename):
+        return None
+
+    codeid = codeids[codename]
+
+    r=requests.get('https://www.legifrance.gouv.fr/affichCode.do?cidTexte='+codeid)
+
+    reg = '^.*?href="(affichCode\.do[^"]*idSectionTA[^"]*)"'
+    c=r.content
+    links=set()
+
+    while True:
+        a = re.match(reg,c,re.DOTALL)
+        if a is None:
+            break
+        l1 = 'https://www.legifrance.gouv.fr/'+a.groups()[0]
+        l1 = re.sub('&','&',l1)
+        links.add(l1)
+        c = re.sub('href=','',c,1)
+
+    articles = {}
+
+    for link in links:
+        r = requests.get(link)
+        
+        reg = '^.*?<a href="(affichCodeArticle\.do[^"]*idArticle[^"]*)" title="En savoir plus sur l\'article ([^"]+)"'
+        c=r.content
+
+        while True:
+            a = re.match(reg, c, re.DOTALL)
+            if a is None:
+                break
+            l1 = 'https://www.legifrance.gouv.fr/'+a.groups()[0]
+            l1 = re.sub('&amp;','&',l1)
+            l1 = re.sub(';jsessionid=[^\?]*\?','?',l1)
+            l1 = re.sub('&dateTexte=[^&]*','',l1)
+            articles[a.groups()[1]] = l1
+            c = re.sub('href=','',c,1)
+
+    return articles
+
+class codes:
+
+    def __init__(self,conffile):
+        self.codes = {}
+        self.conf = configobj.ConfigObj(conffile)
+
+    def get(self,codename,codearticle):
+
+        t = time.time()
+
+        if self.codes.has_key(codename):
+            if t - self.codes[codename]['timestamp'] > self.conf['expire']:
+                del self.codes[codename]
+        if self.codes.has_key(codename):
+            pass
+        else:
+            articles = get_code(codename,self.conf['codeids'])
+            if not articles is None:
+                self.codes[codename] = {'timestamp':t, 'articles':articles}
+
+        if self.codes.has_key(codename):
+            if self.codes[codename]['articles'].has_key(codearticle):
+                return self.codes[codename]['articles'][codearticle]
+        return None
+
+    def force_code_reload(self,codename):
+        if self.codes.has_key(codename):
+            self.codes[codename]['timestamp']=0
+            return True
+        return False
+        
+
+
+    
+
+
+