Python生成器讀取大檔案

青穗黃發表於2018-10-29
# 500G一行的超大文字檔案,有分隔符{|}
def myreadlines(f,newline):
    buf=""
    while True:
        while newline in buf:
            pos = buf.index(newline)
            yield buf[:pos]
            buf = buf[pos+len(newline):]
        chunk =f.read(4096*10)
        if not chunk:
            # 說明已經讀到了檔案結尾
            yield buf
            break
        buf += chunk

with open("input.txt") as f:
    for line in myreadlines(f, "{|}"):
        print(line)
複製程式碼

相關文章