使用 PyMongo 精通 MongoDB：您的 NoSQL 数据库操作综合指南

            pip install pymongo

            

              
                Copy
              
            
          

            
from pymongo import MongoClient

# Establish a connection to the default MongoDB port (27017) on localhost
client = MongoClient('mongodb://localhost:27017/')

# You can also specify host and port explicitly
# client = MongoClient('localhost', 27017)

print("Connected successfully!")

            

              
                Copy
              
            
          

            
from pymongo import MongoClient

# Replace with your actual connection string from MongoDB Atlas
# Example: "mongodb+srv://your_username:your_password@your_cluster_url/your_database?retryWrites=true&w=majority"
uri = "YOUR_MONGODB_ATLAS_CONNECTION_STRING"

client = MongoClient(uri)

print("Connected to MongoDB Atlas successfully!")

            

              
                Copy
              
            
          

            
# Accessing a database (e.g., 'mydatabase')
db = client['mydatabase']
# Alternatively:
db = client.mydatabase

# Accessing a collection within the database (e.g., 'users')
users_collection = db['users']
# Alternatively:
users_collection = db.users

print(f"Accessed database: {db.name}")
print(f"Accessed collection: {users_collection.name}")

            

              
                Copy
              
            
          

            
# Sample user document
new_user = {
    "name": "Alice Smith",
    "age": 30,
    "email": "alice.smith@example.com",
    "city": "New York"
}

# Insert the document
insert_result = users_collection.insert_one(new_user)

print(f"Inserted document ID: {insert_result.inserted_id}")

            

              
                Copy
              
            
          

            
# List of new user documents
new_users = [
    {
        "name": "Bob Johnson",
        "age": 25,
        "email": "bob.johnson@example.com",
        "city": "London"
    },
    {
        "name": "Charlie Brown",
        "age": 35,
        "email": "charlie.brown@example.com",
        "city": "Tokyo"
    }
]

# Insert the documents
insert_many_result = users_collection.insert_many(new_users)

print(f"Inserted document IDs: {insert_many_result.inserted_ids}")

            

              
                Copy
              
            
          

            
# Find a user by name
found_user = users_collection.find_one({"name": "Alice Smith"})

if found_user:
    print(f"Found user: {found_user}")
else:
    print("User not found.")

            

              
                Copy
              
            
          

            
# Find all users aged 30 or older
# The query document { "age": { "$gte": 30 } } uses the $gte (greater than or equal to) operator
users_over_30 = users_collection.find({"age": {"$gte": 30}})

print("Users aged 30 or older:")
for user in users_over_30:
    print(user)

# Find all users in London
users_in_london = users_collection.find({"city": "London"})
print("Users in London:")
for user in users_in_london:
    print(user)

            

              
                Copy
              
            
          

            
# Find users named 'Alice Smith' AND aged 30
alice_and_30 = users_collection.find({"name": "Alice Smith", "age": 30})
print("Alice aged 30:")
for user in alice_and_30:
    print(user)

# Example using $or operator
users_in_ny_or_london = users_collection.find({"$or": [{"city": "New York"}, {"city": "London"}]})
print("Users in New York or London:")
for user in users_in_ny_or_london:
    print(user)

            

              
                Copy
              
            
          

            
# Find all users, but only return their 'name' and 'email' fields
# The `_id` field is returned by default, set `_id: 0` to exclude it
user_names_emails = users_collection.find({}, {"_id": 0, "name": 1, "email": 1})

print("User names and emails:")
for user in user_names_emails:
    print(user)

# Find users in London, returning only 'name' and 'city'
london_users_projection = users_collection.find({ "city": "London" }, { "name": 1, "city": 1, "_id": 0 })
print("London users (name and city):")
for user in london_users_projection:
    print(user)

            

              
                Copy
              
            
          

            
# Update Alice Smith's age to 31
update_result_one = users_collection.update_one(
    {"name": "Alice Smith"},
    {"$set": {"age": 31}}
)

print(f"Matched {update_result_one.matched_count} document(s) and modified {update_result_one.modified_count} document(s).")

# Verify the update
alice_updated = users_collection.find_one({"name": "Alice Smith"})
print(f"Alice after update: {alice_updated}")

            

              
                Copy
              
            
          

            
# Increase the age of all users by 1
update_result_many = users_collection.update_many(
    {},
    {"$inc": {"age": 1}}
)

print(f"Matched {update_result_many.matched_count} document(s) and modified {update_result_many.modified_count} document(s).")

# Verify updates for some users
print("Users after age increment:")
print(users_collection.find_one({"name": "Alice Smith"}))
print(users_collection.find_one({"name": "Bob Johnson"}))

            

              
                Copy
              
            
          

            
new_charlie_data = {
    "name": "Charles Brown",
    "occupation": "Artist",
    "city": "Tokyo"
}

replace_result = users_collection.replace_one({"name": "Charlie Brown"}, new_charlie_data)

print(f"Matched {replace_result.matched_count} document(s) and modified {replace_result.modified_count} document(s).")

print("Charlie after replacement:")
print(users_collection.find_one({"name": "Charles Brown"}))

            

              
                Copy
              
            
          

            
# Delete the user named 'Bob Johnson'
delete_result_one = users_collection.delete_one({"name": "Bob Johnson"})

print(f"Deleted {delete_result_one.deleted_count} document(s).")

# Verify deletion
bob_deleted = users_collection.find_one({"name": "Bob Johnson"})
print(f"Bob after deletion: {bob_deleted}")

            

              
                Copy
              
            
          

            
# Delete all users older than 35
delete_result_many = users_collection.delete_many({"age": {"$gt": 35}})

print(f"Deleted {delete_result_many.deleted_count} document(s).")

            

              
                Copy
              
            
          

            
# Example: Drop the 'old_logs' collection if it exists
if "old_logs" in db.list_collection_names():
    db.drop_collection("old_logs")
    print("Dropped 'old_logs' collection.")
else:
    print("'old_logs' collection does not exist.")

            

              
                Copy
              
            
          

            
# First, let's add some more data for a better example
more_users = [
    {"name": "David Lee", "age": 28, "city": "New York"},
    {"name": "Eva Green", "age": 32, "city": "London"},
    {"name": "Frank Black", "age": 22, "city": "New York"}
]
users_collection.insert_many(more_users)

# Aggregation pipeline
pipeline = [
    {
        "$group": {
            "_id": "$city",  # Group by the 'city' field
            "average_age": {"$avg": "$age"}, # Calculate average age
            "count": {"$sum": 1} # Count documents in each group
        }
    },
    {
        "$sort": {"average_age": -1} # Sort by average_age in descending order
    }
]

average_ages_by_city = list(users_collection.aggregate(pipeline))

print("Average age by city:")
for result in average_ages_by_city:
    print(result)

            

              
                Copy
              
            
          

            
# Create an index on the 'email' field
# The value 1 indicates ascending order. -1 indicates descending order.
index_name = users_collection.create_index([("email", 1)])

print(f"Created index: {index_name}")

# You can also create compound indexes (indexes on multiple fields)
# users_collection.create_index([("city", 1), ("age", -1)])

# To view existing indexes:
# print(list(users_collection.index_information()))

            

              
                Copy
              
            
          

            
# First, create a geospatial index on the 'location' field
# Ensure the 'location' field stores GeoJSON Point objects
# users_collection.create_index([("location", "2dsphere")])

# Sample document with GeoJSON location
user_with_location = {
    "name": "Global Explorer",
    "location": {
        "type": "Point",
        "coordinates": [-74.0060, 40.7128] # [longitude, latitude] for New York
    }
}

# Insert the document (assuming index is created)
# users_collection.insert_one(user_with_location)

# Query for documents within a certain radius (e.g., 10,000 meters from a point)
# This requires the geospatial index to be created first
# search_point = {"type": "Point", "coordinates": [-74.0060, 40.7128]}
# nearby_users = users_collection.find({
#     "location": {
#         "$nearSphere": {
#             "$geometry": {
#                 "type": "Point",
#                 "coordinates": [-74.0060, 40.7128]
#             },
#             "$maxDistance": 10000 # in meters
#         }
#     }
# })

# print("Users near New York:")
# for user in nearby_users:
#     print(user)

            

              
                Copy
              
            
          

            
# Create a text index (can be on multiple string fields)
# text_index_name = users_collection.create_index([("name", "text"), ("city", "text")])
# print(f"Created text index: {text_index_name}")

# Perform a text search
# search_results = users_collection.find({"$text": {"$search": "New York"}})
# print("Search results for 'New York':")
# for result in search_results:
#     print(result)

            

              
                Copy