python 读取文件 下载文件

---

按行读取，大文件

def do_readline(path: str):
    r"""
    :param path: 文件路径
    """
    with open(path, "r", encoding='utf-8') as file_handler:
        line = file_handler.readline()
        while line:
            print(line)
            line = file_handler.readline()

按块读取，大文件

def do_read_chunks(path, chunk_size=1024*1024):
    r"""
    :param path: 文件路径
    :param chunk_size: 块大小
    """
    file_object = open(path)
    while True:
        chunk_data = file_object.read(chunk_size)
        if not chunk_data:
            break
        yield chunk_data

if __name__ == "__main__":
	file_path = 'D:/file_path.txt'
	for chunk in do_read_chunks(file_path):
		print(chunk) 

读取所有行

def do_readlines(path: str):
    r"""
    :param path: 文件路径
    """
    with open(path, "r", encoding='utf-8') as file_handler:
        lines = file_handler.readlines()
        for line in lines:
            print(line)
            print(line.strip()) # 去除行尾换行 \n

一次性, 二进制读取

def do_read_bytes(path: str):
    r"""
    :param path: 文件路径
    """
    with open(path, "rb") as file_handler:
        lines = file_handler.read()
        print(str(lines, encoding='utf-8'))

一次性, 二进制迭代器读取

• for 迭代中 file_handler 被视为一个迭代器, 会自动的采用缓冲IO和内存管理, 可用来处理大文件

def do_read_bytes_itr(path: str):
    r"""
    :param path: 文件路径
    """
    with open(path, "rb") as file_handler:
        for data in file_handler:
            print(data)
            print(str(data, encoding='utf-8'))

下载大文件

import requests
import shutil

def download_file(url):
    local_filename = url.split('/')[-1]
    with requests.get(url, stream=True) as rps:
        with open(local_filename, 'wb') as f:
            shutil.copyfileobj(rps.raw, f)
    return local_filename

• 使用 stream

import requests

def download_file_stream(url):
    local_filename = url.split('/')[-1]
	try:
		with requests.get(url, stream=True) as resp:
			resp.raise_for_status()
			with open(local_filename, 'wb') as f:
				for chunk in resp.iter_content(chunk_size=4096): 
					f.write(chunk)
	except:
		
    return local_filename