Python爬虫之使用MongoDB存储数据的实现

pip install pymongo

import pymongo
client = pymongo.MongoClient("mongodb://localhost:27017/")

import pymongo
client = pymongo.MongoClient("mongodb://localhost:27017/")
# 创建数据库
mydb = client["testdb"]
# 创建集合
mycol = mydb["testcol"]

import pymongo
client = pymongo.MongoClient("mongodb://localhost:27017/")
mydb = client["testdb"]
mycol = mydb["testcol"]
# 插入一条数据
mydict = { "name": "John", "address": "Highway 37" }
x = mycol.insert_one(mydict)
# 插入多条数据
mylist = [
  { "name": "Amy", "address": "Apple st 652" },
  { "name": "Hannah", "address": "Mountain 21" },
  { "name": "Michael", "address": "Valley 345" },
  { "name": "Sandy", "address": "Ocean blvd 2" },
  { "name": "Betty", "address": "Green Grass 1" },
  { "name": "Richard", "address": "Sky st 331" },
  { "name": "Susan", "address": "One way 98" },
  { "name": "Vicky", "address": "Yellow Garden 2" },
  { "name": "Ben", "address": "Park Lane 38" },
  { "name": "William", "address": "Central st 954" },
  { "name": "Chuck", "address": "Main Road 989" },
  { "name": "Viola", "address": "Sideway 1633"}
]
x = mycol.insert_many(mylist)

import pymongo
client = pymongo.MongoClient("mongodb://localhost:27017/")
mydb = client["testdb"]
mycol = mydb["testcol"]
# 查询所有数据
for x in mycol.find():
  print(x)
# 查询name为John的数据
myquery = { "name": "John" }
mydoc = mycol.find(myquery)
for x in mydoc:
  print(x)

import pymongo
client = pymongo.MongoClient(“mongodb://localhost:27017/”)
mydb = client[“testdb”]
mycol = mydb[“testcol”]

myquery = { “name”: “John” }
newvalues = { “$set”: { “address”: “Canyon 123” } }
mycol.update_one(myquery, newvalues)

myquery = { “address”: { “regex": "^S" } } newvalues = { "set”: { “name”: “Minnie” } }
x = mycol.update_many(myquery, newvalues)
print(x.modified_count, “文档已修改”)

import pymongo
client = pymongo.MongoClient("mongodb://localhost:27017/")
mydb = client["testdb"]
mycol = mydb["testcol"]
# 删除一条数据
myquery = { "address": "Mountain 21" }
mycol.delete_one(myquery)
# 删除多条数据
myquery = { "name": {"$regex": "^S"} }
x = mycol.delete_many(myquery)
print(x.deleted_count, "文档已删除")