存入MongoDB
- 启动MongoDB数据库:sudo mongod
- 执行下面程序:py2 process_youyuan_mongodb.py
import json
import redis
import pymongo
def main():
rediscli = redis.StrictRedis(host='192.168.199.108', port=6379, db=0)
mongocli = pymongo.MongoClient(host='localhost', port=27017)
db = mongocli['youyuan']
sheet = db['beijing_18_25']
while True:
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()
存入 MySQL
- 启动mysql:mysql.server start(更平台不一样)
- 登录到root用户:mysql -uroot -p
- 创建数据库youyuan:create database youyuan;
- 切换到指定数据库:use youyuan
- 创建表beijing_18_25以及所有字段的列名和数据类型。
- 执行下面程序:py2 process_youyuan_mysql.py
import json
import redis
import MySQLdb
def main():
rediscli = redis.StrictRedis(host='192.168.199.108', port = 6379, db = 0)
mysqlcli = MySQLdb.connect(host='127.0.0.1', user='power', passwd='xxxxxxx', db = 'youyuan', port=3306, use_unicode=True)
while True:
source, data = rediscli.blpop(["youyuan:items"])
item = json.loads(data)
try:
cur = mysqlcli.cursor()
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']])
mysqlcli.commit()
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()