traceback.print_exc(file=sys.stdout) print "subject get failed" exit() event_str = remote_resource[10:-25].replace("'",'"').replace('brd:','"brd":').replace('file:','"file":').replace('title:','"title":') event_list = json.loads( event_str ) log.write( "%s - LilyBBS Events fetch successful!\n" % (datetime.now(),) ) f = open(path+'/lastupdate_bbsevent.log', 'w') for i in range(0,len(event_list)): board = event_list[i]['brd'] title = event_list[i]['title'] if title+'\n' not in last_update: print title.encode('UTF-8') link = ''.join( ('http://bbs.nju.edu.cn/bbstcon?board=', event_list[i]['brd'], '&file=', event_list[i]['file']) ) friendly_link = multi_update.short_url( ''.join( ('http://bbs.nju.edu.cn/main.html?bbstcon%3Fboard%3D', event_list[i]['brd'], '%26file%3D', event_list[i]['file'], ) ) ) # generate the thread link ################################################################################ ###---###---### The following codes are the same with p_bbstop10 ###---###---### ### handle Chinese cut off bug in LilyBBS system. Just f**k it! #------UPDATE: move to read_url function------ #page = urllib2.urlopen(link).read() #page = unicode(page, 'gbk', 'ignore') #if page[page.find(u'发信站')-1] != '\n': # page = page.replace(u'发信站:', u'\n发信站:') ### end try: page = pq(url=link, opener=read_url) ('textarea').eq(0).text() except: log.write("%s - source: %s\n%s%s\n" % (datetime.now(), 'LilyBBS TOP10', ' '*29, 'FETCH BBS POST FAILED!!!!!', )) traceback.print_exc(file=sys.stdout) continue
if len(top10_list) != 30: log.write( "%s - LilyBBS TOP10 fetch error!\n" % (datetime.now(),) ) log.close() exit() top10_list.make_links_absolute() log.write( "%s - LilyBBS Top10 fetch successful!\n" % (datetime.now(),) ) f = open(path+'/lastupdate_bbstop10.log', 'w') for i in range(0,30,3): board = pq(top10_list[i]).text() title = "[%s]%s" % ( board, pq(top10_list[i+1]).text(), ) if title not in last_update+db_fetch(): print title.encode('UTF-8') link = pq(top10_list[i+1]).attr.href friendly_link = multi_update.short_url( ''.join( ('http://bbs.nju.edu.cn/main.html?', urllib.pathname2url(link[22:]), ) ) )# generate the thread link try: page = pq(url=link, opener=read_url) ('textarea') except: log.write("%s - source: %s\n%s%s\n" % (datetime.now(), 'LilyBBS TOP10', ' '*29, 'FETCH BBS POST FAILED!!!!!', )) traceback.print_exc(file=sys.stdout) continue original_post = read_post(page,0) author = original_post[0] time = original_post[1] sofa_post = read_post(page, 1) bench_post = read_post(page, 2) floor_post = read_post(page, 3) sofa = ''.join( (u'<li>沙发 ', sofa_post[0], u' 说:', sofa_post[2], '</li>', ) )