datから取得するので人大杉回避する

2ch.py

#!/usr/bin/env python
# -*- encoding:utf8 -*-
import sys
import pykf
import urllib2
from pyquery import PyQuery as pq
reload(sys)
sys.setdefaultencoding('utf-8')
BBS_LIST = "http://www.zonubbs.net/bbsmenu.html"

def get_bbslist():
    txt = urllib2.urlopen(BBS_LIST).read()
    n =  pq(unicode(txt, "sjis", "ignore"))("a")
    return [ ( n.eq(i).text(), n.eq(i).attr.href )
            for i in range(n.length)]

def get_boards(url):
    n =  pq( unicode(urllib2.urlopen(url+"subback.html").read(),
             "sjis", "ignore"))("#trad a")
    return [ ( n.eq(i).text(), n.eq(i).attr.href )
            for i in range(n.length)]

def get_boards_test():
    url = "http://toki.2ch.net/nandemo/"
    bs =  get_boards(url)
    for i in bs:
        print i[0], i[1]

def get_daturl(url):
    surl = url.split("/")
    url = "/".join(surl[0:-2])
    return url+"/dat/"+surl[-2]+".dat"

def get_dat(url):
    url = get_daturl(url)
    txt = unicode(urllib2.urlopen(url).read(), "sjis", "ignore").split("\n")
    items = []
    for a in txt:
        sitem =  a.split("<>")
        if len(sitem) > 3:
            items.append({
                "name":sitem[0],
                "date":sitem[2],
                "content":sitem[3].replace("<br>", "\n")
                })
        else:
            print "None"
    return items

def test():
    from random import randint
    area = randint(0, 130)
    bbs = get_bbslist()
    for title, baseurl in bbs[area:area+3]:
        print title, baseurl
        boards = get_boards(baseurl)
        if boards:
            for title, link in boards[:3]:
                print "++ " + title,baseurl+link
                arts = get_dat(baseurl+link)
                for i in arts[0:5]:
                    print "-----", i["date"], i["content"]

test()