使用crc校验生成permlink

背景

hexo-addrlink插件采用对文件名使用crc32的方式

这种方式不允许不同文件夹内有同名文件

因此需要进行改进

脚本

对绝对路径使用crc校验，这样便可允许不同文件名

import zlib
import sys
import os
import time
# 用于生成新博客，带永久链接，crc32算法
filePath = sys.argv[1] + ".md"
title = filePath[filePath.rfind('/') + 1:len(filePath) - 3]
if not os.path.exists(filePath):
    os.system(r"touch {}".format(filePath))
    print(filePath, "has been touched")
else:
    raise FileExistsError("file "+filePath+" aready exists!")
file_mtime = time.localtime(os.stat(filePath).st_mtime)
date_str = time.strftime("%Y-%m-%d %H:%M:%S", file_mtime)

rel_path = os.path.relpath(filePath, start="/Users/raccoon/blogs/source/_posts")
rel_path = rel_path[:rel_path.rfind('/')].replace("/", ", ")
catstr = "categories: [" + rel_path + "]\n"

with open(filePath, "w") as w_file:
    w_file.write("---\n")
    w_file.write("addrlink: " + addrlink + "\n")
    w_file.write("title: " + title + "\n")
    w_file.write("date: " + date_str + "\n")
    w_file.write("updated: " + date_str + "\n")
    w_file.write("tags: \n")
    w_file.write(catstr)
    w_file.write("hidden: false\n")
    w_file.write("password: \n")
    w_file.write("cover: \n")
    w_file.write("description: \n")
    w_file.write("---\n\n")

对已写的博客新增addrlink字段

import zlib
import sys
import os
import time
# 用于强制将未生成addrlink的都打上标记
# 遍历_posts目录及其子目录下的所有文件
posts_dir = "source/_posts"
for root, dirs, files in os.walk(posts_dir):
    dirs.sort()
    for file in sorted(files):
        filePath = os.path.join(root, file)
        filePath = os.path.abspath(filePath)
        if not filePath.endswith(".md"):
            continue
        addrlink = hex(zlib.crc32(str.encode(filePath)))[2:]
        title = filePath[filePath.rfind('/') + 1:len(filePath) - 3]
        file_mtime = time.localtime(os.stat(filePath).st_mtime)
        date_str = time.strftime("%Y-%m-%d %H:%M:%S", file_mtime)

        rel_path = os.path.relpath(filePath, start="/Users/raccoon/blogs/source/_posts")
        rel_path = rel_path[:rel_path.rfind('/')].replace("/", ", ")
        catstr = "categories: [" + rel_path + "]\n"
        with open(filePath, "r") as r_file:
            lines = r_file.readlines()
        with open(filePath, "w") as w_file:
            for line in lines:
                if line.startswith("title"):
                    w_file.write("addrlink: " + addrlink + "\n")
                    print(addrlink, "has been written to", filePath)
                    w_file.write(line)
                else:
                    w_file.write(line)

消除上面的脚本对各个文件写入，改变了更新时间的副作用

# 用于将head写入mtime强制（通常用于在脚本执行后, 确认此次脚本涉及的文件均为进行实质性内容更改，可进行mtime的修正）

import os
import time

if __name__ == "__main__":

    posts_dir = "source/_posts"

    # 遍历_posts目录及其子目录下的所有文件
    for root, dirs, files in os.walk(posts_dir):
        dirs.sort()
        for file in sorted(files):
            file_path = os.path.join(root, file)
            file_path = os.path.abspath(file_path)
            if not file_path.endswith(".md"):
                continue
            with open(file_path, 'r') as r_file:
                lines = r_file.readlines()
            for line in lines:
                if line.startswith("updated"):
                    timestr = line.replace("updated: ", "").strip()
                    date_time = time.strptime(timestr, "%Y-%m-%d %H:%M:%S")
                    touch_str = time.strftime("%Y%m%d%H%M", date_time)
                    touch_cmd = "touch -mt " + touch_str + " " + file_path 
                    ls_cmd = "ls -l " + file_path
                    os.system(touch_cmd)
                    print(touch_str, "has been forced added to", file_path, "Result:")
                    os.system(ls_cmd)

检查crc是否有重复

import os
from collections import Counter
# 找出crc32重复元素
posts_dir = "source/_posts"
for root, dirs, files in os.walk(posts_dir):
    dirs.sort()
    for file in sorted(files):
        filePath = os.path.join(root, file)
        filePath = os.path.abspath(filePath)
        if not filePath.endswith(".md"):
            continue
        with open(filePath, "r") as file:
            lines = file.readlines()
        for line in lines:
            if line.startswith("addrlink: "):
                addrlinklist.append(line.replace("addrlink: ", "").strip())
                break
b = dict(Counter(addrlinklist))
print({key:value for key,value in b.items() if value > 1})