分布式爬虫处理Redis里的数据操作步骤

# process_youyuan_mongodb.py
# -*- coding: utf-8 -*-
import json
import redis
import pymongo
def main():
 # 指定Redis数据库信息
 rediscli = redis.StrictRedis(host='192.168.199.108', port=6379, db=0)
 # 指定MongoDB数据库信息
 mongocli = pymongo.MongoClient(host='localhost', port=27017)
 # 创建数据库名
 db = mongocli['youyuan']
 # 创建表名
 sheet = db['beijing_18_25']
 while True:
 # FIFO模式为 blpop，LIFO模式为 brpop，获取键值
 source, data = rediscli.blpop(["youyuan:items"])
 item = json.loads(data)
 sheet.insert(item)
 try:
  print u"Processing: %(name)s %(link)s>" % item
 except KeyError:
  print u"Error procesing: %r" % item
if __name__ == '__main__':
 main()

#process_youyuan_mysql.py
# -*- coding: utf-8 -*-
import json
import redis
import MySQLdb
def main():
 # 指定redis数据库信息
 rediscli = redis.StrictRedis(host='192.168.199.108', port = 6379, db = 0)
 # 指定mysql数据库
 mysqlcli = MySQLdb.connect(host='127.0.0.1', user='power', passwd='xxxxxxx', db = 'youyuan', port=3306, use_unicode=True)
 while True:
 # FIFO模式为 blpop，LIFO模式为 brpop，获取键值
 source, data = rediscli.blpop(["youyuan:items"])
 item = json.loads(data)
 try:
  # 使用cursor()方法获取操作游标
  cur = mysqlcli.cursor()
  # 使用execute方法执行SQL INSERT语句
  cur.execute("INSERT INTO beijing_18_25 (username, crawled, age, spider, header_url, source, pic_urls, monologue, source_url) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s )", [item['username'], item['crawled'], item['age'], item['spider'], item['header_url'], item['source'], item['pic_urls'], item['monologue'], item['source_url']])
  # 提交sql事务
  mysqlcli.commit()
  #关闭本次操作
  cur.close()
  print "inserted %s" % item['source_url']
 except MySQLdb.Error,e:
  print "Mysql Error %d: %s" % (e.args[0], e.args[1])
if __name__ == '__main__':
 main()