1、txt
①读取全部内容
txt_filename = './files/python_baidu.txt'# 打开文件file_obj = open(txt_filename, 'r', encoding='utf-8')# 读取整个文件内容all_content = file_obj.read()# 关闭文件file_obj.close()print(all_content)
②按行读取
txt_filename = './files/python_baidu.txt'# 打开文件file_obj = open(txt_filename, 'r', encoding='utf-8')# 逐行读取line1 = file_obj.readline()print(line1)# 继续读下一行，游标自动指向第二行line2 = file_obj.readline()print(line2)# 关闭文件file_obj.close()
③读取返回列表
txt_filename = './files/python_baidu.txt'# 打开文件file_obj = open(txt_filename, 'r', encoding='utf-8')lines = file_obj.readlines()for i, line in enumerate(lines):print ('{}: {}'.format(i, line))# 关闭文件file_obj.close()
④写操作
txt_filename = './files/test_write.txt'# 打开文件file_obj = open(txt_filename, 'w', encoding='utf-8')# 写入全部内容file_obj.write("《Python数据分析》")file_obj.close()
⑤按行写入
txt_filename = './files/test_write.txt'# 打开文件file_obj = open(txt_filename, 'w', encoding='utf-8')# 写入字符串列表lines = ['这是第%i行\n' %n for n in range(100)]file_obj.writelines(lines)file_obj.close()
⑦with
txt_filename = './files/test_write.txt'with open(txt_filename, 'r', encoding='utf-8') as f_obj:print(f_obj.read())#不需要关闭，会自动异常处理
2、CSV（以纯文本存储表格，逗号为分隔符）
①pandas读CSV
import pandas as pdfilename = './files/gender_country.csv'df = pd.read_csv(filename, encoding='utf-16')print(type(df))print(df.head())#head预览前五行
②pandas写入CSV
filename = './files/pandas_output.csv'df.to_csv(filename, index=None, encoding='utf-8')
3、JSON {key1：val1，key2：val2}
①读取
import jsonfilename = './files/global_temperature.json'with open(filename, 'r') as f_obj:json_data = json.load(f_obj)# 返回值是dict类型print(type(json_data))
②读取keys和values
#print(json_data['data'].keys())print(json_data['data'].values())
③转换成CSV
year_str_lst = json_data['data'].keys()#读出来都是stryear_lst = [int(year_str) for year_str in year_str_lst]#如果有数字，转换成intprint(year_lst）
import pandas as pd# 构建 dataframeyear_se = pd.Series(year_lst, name = 'year')#得到一维列数据temp_se = pd.Series(temp_lst, name = 'temperature')result_df = pd.concat([year_se, temp_se], axis = 1)#得到二维dataframe，axis为0是两列竖着排，1是并排放print(result_df.head())# 保存csvresult_df.to_csv('./files/json_to_csv.csv', index = None)#index=none没有行索引
④写成json
book_dict = [{'书名':'无声告白', '作者':'伍绮诗'}, {'书名':'我不是潘金莲', '作者':'刘震云'}, {'书名':'沉默的大多数 (王小波集)', '作者':'王小波'}]filename = './files/json_output.json'with open(filename, 'w', encoding='utf-8') as f_obj:f_obj.write(json.dumps(book_dict, ensure_ascii=False))
4、sqlite
import sqlite3db_path = './files/test.sqlite'conn = sqlite3.connect(db_path)cur = conn.cursor()conn.text_factory = str # 处理中文cur.execute("DROP TABLE IF EXISTS book")cur.execute("CREATE TABLE book(id INT, name TEXT, price DOUBLE)")#逐条插入数据cur.execute("INSERT INTO book VALUES(1,'肖秀荣考研书系列:肖秀荣()考研政治命题人终极预测4套卷',14.40)")cur.execute("INSERT INTO book VALUES(2,'法医秦明作品集:幸存者+清道夫+尸语者+无声的证词+第十一根手指(套装共5册) (两种封面随机发货)',100.00)")cur.execute("INSERT INTO book VALUES(3,'活着本来单纯:丰子恺散文漫画精品集(收藏本)',30.90)")cur.execute("INSERT INTO book VALUES(4,'自在独行:贾平凹的独行世界',26.80)")cur.execute("INSERT INTO book VALUES(5,'当你的才华还撑不起你的梦想时',23.00)")cur.execute("INSERT INTO book VALUES(6,'巨人的陨落(套装共3册)',84.90)")cur.execute("INSERT INTO book VALUES(7,'孤独深处(收录雨果奖获奖作品《北京折叠》)',21.90)")cur.execute("INSERT INTO book VALUES(8,'世界知名企业员工指定培训教材:所谓情商高,就是会说话',22.00)")#批量插入数据books = ((9, '人间草木', 30.00),(10,'你的善良必须有点锋芒', 20.50),(11, '这么慢,那么美', 24.80),(12, '考拉小巫的英语学习日记:写给为梦想而奋斗的人(全新修订版)', 23.90))#元组里套元组cur.executemany("INSERT INTO book VALUES(?, ?, ?)", books)#提交mit()#查找数据cur.execute('SELECT * FROM book')rows = cur.fetchall()# 通过索引号访问for row in rows:print('序号: {}, 书名: {}, 价格: {}'.format(row[0], row[1], row[2]))#关闭conn.close()
