Python常见读写文件操作实例总结【文本、json、csv、pdf等】

f = open("t1.txt","r",encoding="utf-8")

f = open("t122.txt","r",encoding="utf-8")

print(f.read())

f.close()

f = open(r"文件地址","读取方式",encoding="utf-8")

try:
 f = open("t1.txt", "r", encoding="utf-8")
 print(f.read())
finally:
 if f:
  f.close() 

with open("t1.txt", "r", encoding="utf-8") as f:
 print(f.read())

for line in f.readlines():
 #把末尾的'\n'删掉
 print(line.strip())

f = open("tigle.jpg", "rb")
print(f.read())
b'\xff\xd8\xff\xe1\x00\x18Exif\x00\x00...' # 十六进制表示的字节

f = open('/user/demo/gbk.txt','r',encoding = 'gbk')
f.read()
'测试'

f = open('/users/demo/gbk.txt','r',encoding = 'gbk',errors = 'ignore')

f = open("/users/demo/test.txt",'w')
f.write('hello, world!')
f.close()

with open('/users/demo/test.txt', 'w') as f:
 f.write('hello, world')

with open('/users/demo/test.txt', 'a') as f:
 f.write('hello, world')

from io import StringIO
f = StringIO()
f.write("hello")
f.write(" ")
f.write('world')
#获取写入后的str
print(f.getvalue())

from io import StringIO
f = StringIO("Hello\nHi\nGoodBye!")
while True:
 s = f.readline()
 if s == '':
  break
 # 去掉换行符
 print(s.strip())

from io import BytesIO
f = BytesIO()
f.write("中文".encode('utf-8'))
print(f.getvalue())

from io import BytesIO
f = BytesIO(b'\xe4\xb8\xad\xe6\x96\x87')
d = f.read()
print(d)
print(d.decode())

dict1 = {name:"lili",age:18}

import pickle
d = dict({"name":"lili","age":18})
#pickle.dumps()方法把任意对象序列化成一个bytes，然后就可以把bytes写入文件
print(pickle.dumps(d))
#把序列化后的对象写入文件
f = open("t1.txt",'wb')
#参数一：要写入的对象， 参数二：写入文件的对象
pickle.dump(d,f)
f.close()
#从文件中读取序列化后的对象
f2 = open("t1.txt","rb")
#pickle.load()反序列化对象
d = pickle.load(f2)
f2.close()
print(d)
print(type(d))

import json
dict1 = {"name":"lili","age":18}
ji = json.dumps(dict1)
print(type(ji))
with open("dd.txt","w") as f:
 json.dump(dict1,f)
with open("dd.txt","r",encoding="utf-8") as f:
 du = json.load(f)
 print(du)
 print(type(du))

import json
class Student(object):
 def __init__(self, name, age, score):
  self.name = name
  self.age = age
  self.score = score
# 将student对象转换为dict
def student2dict(std):
 return {
  'name': std.name,
  'age': std.age,
  'score': std.score
 }
s = Student('Bob', 20, 88)
# 参数一：要传入的对象 参数二：将对象转为dict的函数
d = json.dumps(s, default=student2dict)
# 将dict转为对象
def dict2student(d):
 return Student(d['name'], d['age'], d['score'])
jsonStr = '{"age": 20, "score": 88, "name": "Bob"}'
# json反序列化为一个对象
# 参数一：json字符串，参数二：dict转为对象的函数
print(json.loads(jsonStr, object_hook=dict2student))
# 写入文件
with open("t1.txt","w") as f:
 f.write(d)
 #或者直接使用下面的语句
 #json.dump(s,f,default=student2dict)
# 读取文件
with open("t1.txt","r",encoding="utf-8") as f:
 du = json.load(f,object_hook=dict2student)
print(du)

import csv
def readCsv(path):
 #列表
 infoList = []
 #以只读的形式打开文件
 with open(path, 'r') as f:
  #读取文件的内容
  allFileInfo = csv.reader(f)
  #将获取到的内容逐行追加到列表中
  for row in allFileInfo:
   infoList.append(row)
 return infoList
path = r"C:\Users\xlg\Desktop\001.csv"
info = readCsv(path)

import csv
#以写的方式打开文件
def writeCsv(path,data):
 with open(path,'w',newline='') as f:
  writer = csv.writer(f)
  for rowData in data:
   print("rowData =", rowData)
   #按行写入
   writer.writerow(rowData)
path = r"C:\Users\xlg\Desktop\002.csv"
writeCsv(path,[[1,2,3],[4,5,6],[7,8,9]])

import sys
import importlib
importlib.reload(sys)
from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter #解释器
from pdfminer.converter import PDFPageAggregator #转换器
from pdfminer.layout import LTTextBoxHorizontal, LAParams #布局
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed #是否允许pdf和text转换
def readPDF(path, toPath):
 #以二进制形式打开pdf文件
 f = open(path, "rb")
 #创建一个pdf文档分析器
 parser = PDFParser(f)
 #创建pdf文档
 pdfFile = PDFDocument()
 #链接分析器与文档对象
 parser.set_document(pdfFile)
 pdfFile.set_parser(parser)
 #提供初始化密码
 pdfFile.initialize()
 #检测文档是否提供txt转换
 if not pdfFile.is_extractable:
  raise PDFTextExtractionNotAllowed
 else:
  #解析数据
  #数据管理器
  manager = PDFResourceManager()
  #创建一个PDF设备对象
  laparams = LAParams()
  device = PDFPageAggregator(manager, laparams=laparams)
  #解释器对象
  interpreter = PDFPageInterpreter(manager, device)
  #开始循环处理，每次处理一页
  for page in pdfFile.get_pages():
   interpreter.process_page(page)
   layout = device.get_result()
   for x in layout:
    if (isinstance(x, LTTextBoxHorizontal)):
     with open(toPath, "a") as f:
      str = x.get_text()
      #print(str)
      f.write(str+"\n")
path = r"0319开始.pdf"
toPath = r"n.txt"
readPDF(path, toPath)