def reply_status(self, response): #重新返回首页,对特别是需要回复的模块特别有用,而不需要回复的帖子缺对性能是个损失. #查询回复状态 success = u'非常感谢,你的回复已经发布'.encode('gbk', 'ignore') status = re.findall(success, response.body) username_sql = sql.select_accountbyusername(self.username, self.platform) #回复数量限制 failture = u'对不起,您所在的用户组每小时限制发帖 '.encode('gbk', 'ignore') failture_status = re.findall(failture, response.body, re.I) if failture_status: return if status: log.msg('reply success', log.INFO) reply_nums = handle_db(username_sql)['data'][0] self.point_num = reply_nums[5] self.reply_num = reply_nums[-2] self.reply_num += 1 self.point_num += 1 #回复成功.账号reply_num+1,积分+1 try: update_replynum = sql.update_account_username(self.username, self.platform, self.reply_num, self.point_num) update_success = handle_db(update_replynum) log.msg(('<username: %s \'s integral is : +1 ,now integral is %s>' % (self.username, self.reply_num)), log.INFO) except Exception, e: log.msg(str(traceback.print_exc()), log.ERROR)
def get_apk(self, response): filename = ''.join([str(random.randrange(1,100000)), '.apk']) # if os.path.exists(''.join([os.getcwd(), os.sep, 'gfan', os.sep, 'download', os.sep, time.strftime('%Y-%m-%d'),os.sep])) is False: # os.mkdir(''.join([os.getcwd(), os.sep, 'gfan', os.sep, 'download', os.sep, time.strftime('%Y-%m-%d'),os.sep])) #调用新建文件夹的方法 down_dir = utils.make_spiderdir(self.platform, 'download') #解码:有的文件可能是utf-8编码,解为unicode try: filename = filename.decode('utf-8', 'ignore') except: pass filename = ''.join([down_dir, os.sep, str(time.time()).split('.')[0], filename]) open(filename, 'wb').write(response.body) #下载后在存数据库,确保准确性 topic_url = response.request.meta['topic_url'] hashurl = sql.hash_topic(topic_url) updatedate = time.strftime('%Y-%m-%d %H:%M:%S') filename = filename.replace('\\', '\\\\') insert_sql = sql.insert_softwareinfo(self.platform, hashurl, topic_url, updatedate, filename) status = handle_db(insert_sql) log.msg(str(status), log.DEBUG) #更新topic数据库表 update_topic_url = sql.topicurl_withcrawed(topic_url) status = handle_db(update_topic_url) log.msg(str(status), log.DEBUG) #能进入本方法执行,表示已经下载了该response.积分-1 account_sql = sql.select_accountbyusername(self.username, self.platform) point_num = handle_db(account_sql)['data'][0][5] point_num -= 1 #然后执行更新 update_account_pointsql = sql.update_account_point(self.username, self.platform, point_num) n = handle_db(update_account_pointsql) if n['errorNo'] == 0: log.msg(('<username: %s \'s integral is : -1 ,now integral is %s>' % (self.username, self.reply_num)), log.INFO) try: autocopy.copy(filename, self.platform) log.msg('copy job is successed', log.INFO) except: log.msg(str(traceback.print_exc()), log.ERROR) log.msg('copy job is failture', log.ERROR) request_topic = self.repeat_reply(response) return request_topic
def reply_status(self, response): #重新返回首页,对特别是需要回复的模块特别有用,而不需要回复的帖子缺对性能是个损失. #查询回复状态 success = u'非常感谢,你的回复已经发布'.encode('gbk', 'ignore') status = re.findall(success, response.body) username_sql = sql.select_accountbyusername(self.username, self.platform) print 'status', status #回复数量限制 failture = u'对不起,您所在的用户组每小时限制发帖 '.encode('gbk', 'ignore') failture_status = re.findall(failture, response.body, re.I) if failture_status: print u'对不起,您所在的用户组每小时限制发帖 ' return if status: log.msg('reply success', log.INFO) reply_nums = handle_db(username_sql)['data'][0] self.point_num = reply_nums[5] self.reply_num = reply_nums[-2] self.reply_num += 1 self.point_num += 1 #回复成功.账号reply_num+1,积分+1 try: update_replynum = sql.update_account_username(self.username, self.platform, self.reply_num, self.point_num) update_success = handle_db(update_replynum) log.msg(('<username: %s \'s integral is : +1 ,now integral is %s>' % (self.username, self.reply_num)), log.INFO) #回复成功,执行下载 url = response.request.meta['topic_url'] print u'回复成功主题:url---->', url #回复成功,重新进入topic页 self.topic_reply_num -= 1 log.msg(('reply success, will download software%s' % str(self.topic_reply_num)), log.DEBUG) log.msg(str(response), log.DEBUG) request = self.get_down_topic(response, url) return request except Exception, e: log.msg(str(traceback.print_exc()), log.ERROR) #重调get_topic.同时REPLY_NUM-1,当REPLY_NUM<1时,不在做任何事情. self.topic_reply_num -= 1 log.msg(('reply success, will download software', str(self.topic_reply_num)), log.DEBUG) log.msg(str(response), log.DEBUG) request_topic = self.repeat_reply(response) return request_topic
def reply_status(self, response): #重新返回首页,对特别是需要回复的模块特别有用,而不需要回复的帖子缺对性能是个损失. #查询回复状态 success = '非常感谢,您的回复已经发布' status = re.findall(success, response.body) username_sql = sql.select_accountbyusername(self.username, self.platform) if status: log.msg('reply success', log.INFO) reply_nums = handle_db(username_sql)['data'][0] self.point_num = reply_nums[5] self.reply_num = reply_nums[-2] self.reply_num += 1 self.point_num += 1 #回复成功.账号reply_num+1,积分+1 try: update_replynum = sql.update_account_username(self.username, self.platform, self.reply_num, self.point_num) update_success = handle_db(update_replynum) log.msg(('<username: %s \'s integral is : +1 ,now integral is %s>' % (self.username, self.reply_num)), log.INFO) except Exception, e: log.msg(str(traceback.print_exc()), log.ERROR)
def reply_status(self, response): #重新返回首页,对特别是需要回复的模块特别有用,而不需要回复的帖子缺对性能是个损失. #查询回复状态 success = '非常感谢,您的回复已经发布' status = re.findall(success, response.body) print self.username username_sql = sql.select_accountbyusername(self.username, self.platform) if status: print 'reply success' reply_nums = handle_db(username_sql)['data'][0] self.reply_num = reply_nums[-2] self.reply_num += 1 #回复成功.账号reply_num+1 try: now_time = time.strftime('%Y-%m-%d %H:%M:%S') update_replynum = sql.update_account_username(self.username, now_time, self.platform, self.reply_num) update_success = handle_db(update_replynum) print update_success print 'update success! user\'s reply_num + 1' except Exception, e: traceback.print_exc()