MongoDB文档

基本操作 update

// 查找有限个数的数据
for i in item_info.find().limit(300)
      print(i['area'])

// 去掉数据源中带标点符号的数据
for i in item_info.find():
    if i['area']:
        area = [ i for i in i['area'] if i not in punctuation]
   else:
        area = ['不明']
    print(area)

// update 数据数据库
db.collection.update()

e.g. {id:1, name:0, info:3}
update({id:1},  {$set: {name:2}} // 修改id为1的数据，将name改为2

for i in item_info.find():
    if i['area']:
        area = [ i for i in i['area'] if i not in punctuation]
   else:
        area = ['不明']
   
    item_info.update({'_id':i['_id']},{'$set':{'area':area}})

// 获取不重复的area_list
area_list = []
for i in item_info.find():
    area_list.append(i['area][0])
area_index = list(set(area_list))

post_times = []
for index in area_index:
    post_times.append(area_list.count(index)

// 生成charts_data函数
def data_gen(type):
    length = 0
    if length <= len(area_index):
        for area, times in zip(area_index, post_times):
            data = {
                  'name': area,
                  'data': [times],
                  'type': type
            }
            yield data
            length += 1

series = [data for data in data_gen('column')]

charts.plot(series, show='inline', options=dict(title=dict(text='Charts are Awesome!!!')))

基本操作 find

db.collection.find()

e.g.:
 {id:1, name:0, info:3, cate:4}

// 查找id为1的数据，且只查看name和info字段，其余不看
 find({id:1},{name:1, info:1})

result:
    {id:1, name:0, info:3}

// 查看area，不看_id
for i in item_info.find({},{'area':1, '_id':0}).limit(300):
    print(i)

// $slice  $in 用法
for i in item_info.find({'pub_date':{'$in':{'2016.01.12','2016.01.14'}}},{'area':{'$slice':1}, '_id':0, 'price': 0, 'title': 0}).limit(300):
    print(i)

基本操作 aggregate

db.collections.aggregate(pipeline)

pipeline = [
    {$match: ?},
    {$group: ?},
    {$sort: ?},
    {$limit: ?},
    {$skip: ?},
    {$unwind: ?},
    {$redact: ?},
    {$sample: ?},
    {$out: ?}
]

 pipeline = [
    { '$match': { '$and': [ 'pub_date': '2015.12.24'}, {'time': 3} ] } },
    { '$group': { '_id': '$price', 'count': {'$sum': 1} } },
    { '$sort': { 'counts': 1 } }, // -1 表示逆序，从大到小
    { '$limit': 3 }
]
for i in item_info.aggregate(pipeline):
     print(i)

 pipeline2 = [
    { '$match': { '$and': [ 'pub_date': '2015.12.24'}, {'time': 3} ] } },
    { '$group': { '_id': { '$slice':[ 'cates', 2, 1] }, 'count': {'$sum': 1} } },
    { '$sort': { 'counts': 1 } },
    { '$limit': 3 }
]

pipeline3 = [
    {'$match':{'$and':[{'pub_date':{'$gte':'2015.12.25','$lte':'2015.12.27'}},{'area':{'$all':['朝阳']}}]}},
    {'$group':{'_id':{'$slice':['$cates',2,1]},'counts':{'$sum':1}}},
    {'$limit':3}
]

pipeline4 = [
    {'$match':{'$and':[{'pub_date':{'$gte':'2015.12.25','$lte':'2015.12.27'}},
                       {'cates':{'$all':['北京二手手机']}},
                       {'look':{'$nin':['-']}}
                      ]}},
    {'$group':{'_id':'$look','avg_price':{'$avg':'$price'}}},
    {'$sort':{'avg_price':-1}}
]

终端用法

// 启动mongod服务
mongod
mongo

// 数据库操作
show dbs

use ceshi

show collections

db.createCollections('item_info_copy')
{"ok":1}

db.item_info.copyTo('item_info_copy')
WANING: db.eval is deprecated. 

导入导出

如何导出 csv ？

mongoexport -d database -c collection -o output/path.csv

mongoexport -d ceshi -c item_infoZ -o Users/Hou/Desktop/ddd.json