run.py 文件源码

def run(self, args, opts):
        self.set_pages(opts.pages)
        self.settings.set('GOOD_ONLY', opts.good_only)
        self.settings.set('SEE_LZ', opts.see_lz)
        if opts.filter:
            try:
                opts.filter = eval('filter.' + opts.filter)
            except:
                raise UsageError("Invalid filter function name!")
        self.settings.set("FILTER", opts.filter)
        cfg = config.config()
        if len(args) >= 3:
            raise UsageError("Too many arguments!")

        self.settings.set('MYSQL_HOST', cfg.config['MYSQL_HOST'])
        self.settings.set('MYSQL_USER', cfg.config['MYSQL_USER'])
        self.settings.set('MYSQL_PASSWD', cfg.config['MYSQL_PASSWD'])

        tbname = cfg.config['DEFAULT_TIEBA']
        if len(args) >= 1:
            tbname = args[0]
        if isinstance(tbname, unicode):
            tbname = tbname.encode('utf8')

        dbname = None    
        for key in cfg.config['MYSQL_DBNAME'].keys():
            if key.encode('utf8') == tbname:
                dbname = cfg.config['MYSQL_DBNAME'][key]
        if len(args) >= 2:
            dbname = args[1]
            cfg.config['MYSQL_DBNAME'][tbname.decode('utf8')] = dbname
        if not dbname:
            raise UsageError("Please input database name!")

        self.settings.set('TIEBA_NAME', tbname, priority='cmdline')
        self.settings.set('MYSQL_DBNAME', dbname, priority='cmdline')

        config.init_database(cfg.config['MYSQL_HOST'], cfg.config['MYSQL_USER'], cfg.config['MYSQL_PASSWD'], dbname)

        log = config.log(tbname, dbname, self.settings['BEGIN_PAGE'], opts.good_only, opts.see_lz)
        self.settings.set('SIMPLE_LOG', log)

        self.crawler_process.crawl('tieba', **opts.spargs)
        self.crawler_process.start()

        cfg.save()