pymongo 是 mongodb 的 python Driver Editor.
记录下学习过程中感觉以后会常用多一些部分,以做参考。
1. 连接数据库
要使用pymongo最先应该做的事就是先连上运行中的 mongod 。
- 创建一个 .py 文件,首先导入 pymongo:
from pymongo import MongoClient
- 创建一个连接到 mongod 到客户端:
client = MongoClient()
或者:
client = MongoClient("mongodb://mongodb0.example.net:27019")
- 连接数据库:
# 假设要连接的数据库名为 primer
db = client.primer
或者:
db = client['primer']
- 连接到对应的数据集:
coll = db.dataset
coll = db['dataset']
至此,已经完整对连接了数据库和数据集,完成了初识化的操作。
2. 插入数据
> insert_one(document)
> insert_many(documents, ordered=True)
-
insert_one(document)
在 pymongo 中的插入函数并不像 mongo shell 中完全一样,所以需要注意一下:
from datetime import datetime
result = db.restaurants.insert_one(
{
"address": {
"street": "2 Avenue",
"zipcode": "10075",
"building": "1480",
"coord": [-73.9557413, 40.7720266]
},
"borough": "Manhattan",
"cuisine": "Italian",
"grades": [
{
"date": datetime.strptime("2014-10-01", "%Y-%m-%d"),
"grade": "A",
"score": 11
},
{
"date": datetime.strptime("2014-01-16", "%Y-%m-%d"),
"grade": "B",
"score": 17
}
],
"name": "Vella",
"restaurant_id": "41704620"
}
)
其中返回的结果:result 中是一个:InsertOneResult 类:
class pymongo.results.InsertOneResult(inserted_id, acknowledged)
其中 inserted_id
是插入的元素多 _id
值。
insert_many(documents, ordered=True)
result = db.test.insert_many([{'x': i} for i in range(2)])
3. 查询数据
> find(filter=None, projection=None, skip=0, limit=0,
no_cursor_timeout=False, cursor_type=CursorType.NON_TAILABLE,
sort=None, allow_partial_results=False, oplog_replay=False,
modifiers=None, manipulate=True)
> find_one(filter_or_id=None, *args, **kwargs)
-
find
find 查询出来的是一个列表集合。
cursor = db.restaurants.find()
for document in cursor:
print(document)
# 查询字段是最上层的
cursor = db.restaurants.find({"borough": "Manhattan"})
# 查询字段在内层嵌套中
cursor = db.restaurants.find({"address.zipcode": "10075"})
- 操作符查询
cursor = db.restaurants.find({"grades.score": {"$gt": 30}})
cursor = db.restaurants.find({"grades.score": {"$lt": 10}})
# AND
cursor = db.restaurants.find({"cuisine": "Italian", "address.zipcode": "10075"})
cursor = db.restaurants.find(
{"$or": [{"cuisine": "Italian"}, {"address.zipcode": "10075"}]})
find_one
返回的是一个JSON式文档,所以可以直接使用!sort
排序时要特别注意,使用的并不是和mongo shell的一样,而是使用了列表,
当排序的标准只有一个,且是递增时,可以直接写在函数参数中:
pymongo.ASCENDING = 1
pymongo.DESCENDING = -1
cursor = db.restaurants.find().sort("borough")
cursor = db.restaurants.find().sort([
("borough", pymongo.ASCENDING),
("address.zipcode", pymongo.DESCENDING)
])
4. 更新文档
更新文档的函数有三个(不能更新 _id
字段)
update_one(filter, update, upsert=False)
update_many(filter, update, upsert=False)
replace_one(filter, replacement, upsert=False)
find_one_and_update(filter, update, projection=None, sort=None, return_document=ReturnDocument.BEFORE, **kwargs)
-
update_one
返回结果是一个:UpdateResult
,如果查找到多个匹配,则只更新
第一个!
result = db.restaurants.update_one(
{"name": "Juni"},
{
"$set": {
"cuisine": "American (New)"
},
"$currentDate": {"lastModified": True}
}
)
result.matched_count
10
result.modified_count
1
-
update_many
查找到多少匹配,就更新多少。
result = db.restaurants.update_many(
{"address.zipcode": "10016", "cuisine": "Other"},
{
"$set": {"cuisine": "Category To Be Determined"},
"$currentDate": {"lastModified": True}
}
)
result.matched_count
20
result.modified_count
20
replace_one
result = db.restaurants.replace_one(
{"restaurant_id": "41704620"},
{
"name": "Vella 2",
"address": {
"coord": [-73.9557413, 40.7720266],
"building": "1480",
"street": "2 Avenue",
"zipcode": "10075"
}
}
)
result.matched_count
1
result.modified_count
1
-
find_one_and_update
返回更新前的文档
db.test.find_one_and_update(
{'_id': 665}, {'$inc': {'count': 1}, '$set': {'done': True}})
{u'_id': 665, u'done': False, u'count': 25}}
5. 删除文档
删除时主要有两个:
> delete_one(filter)
> delete_many(filter)
> drop()
> find_one_and_delete(filter, projection=None, sort=None, **kwargs)
> find_one_and_replace(filter, replacement, projection=None,
> sort=None, return_document=ReturnDocument.BEFORE, **kwargs)
delete_one
result = db.test.delete_one({'x': 1})
result.deleted_count
1
delete_many
result = db.restaurants.delete_many({"borough": "Manhattan"})
result.deleted_count
10259
# 删除全部
result = db.restaurants.delete_many({})
-
drop()
删除整个集合,是drop_collection()
的别名
db.restaurants.drop()
find_one_and_delete
db.test.count({'x': 1})
2
db.test.find_one_and_delete({'x': 1})
{u'x': 1, u'_id': ObjectId('54f4e12bfba5220aa4d6dee8')}
db.test.count({'x': 1})
find_one_and_replace
>>> for doc in db.test.find({}):
... print(doc)
...
{u'x': 1, u'_id': 0}
{u'x': 1, u'_id': 1}
{u'x': 1, u'_id': 2}
>>> db.test.find_one_and_replace({'x': 1}, {'y': 1})
{u'x': 1, u'_id': 0}
>>> for doc in db.test.find({}):
... print(doc)
...
{u'y': 1, u'_id': 0}
{u'x': 1, u'_id': 1}
{u'x': 1, u'_id': 2}
6. 索引操作
索引主要有创建索引和删除索引:
> create_index(keys, **kwargs)
> create_indexes(indexes)
> drop_index(index_or_name)
> drop_indexes()
> reindex()
> list_indexes()
> index_information()
create_index
my_collection.create_index("mike")
my_collection.create_index([("mike", pymongo.DESCENDING),
... ("eliot", pymongo.ASCENDING)])
my_collection.create_index([("mike", pymongo.DESCENDING)],
... background=True)
create_indexes
>>> from pymongo import IndexModel, ASCENDING, DESCENDING
>>> index1 = IndexModel([("hello", DESCENDING),
... ("world", ASCENDING)], name="hello_world")
>>> index2 = IndexModel([("goodbye", DESCENDING)])
>>> db.test.create_indexes([index1, index2])
["hello_world"]
-
drop_index
index_or_name
: 索引编号或者索引的name
my_collection.drop_index("mike")
drop_indexs
删除所有索引reindex
重构索引,尽量少用,如果集合比较大多话,会很耗时耗力.
for index in db.test.list_indexes():
... print(index)
...
SON([(u'v', 1), (u'key', SON([(u'_id', 1)])),
(u'name', u'_id_'), (u'ns', u'test.test')])