1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
|
import os
import time
import datetime
# import enchant
import jieba
class HugoMarkdown:
# __srcDir = 'I:\src\hugo\docs' #源文章目录
# __desDir = 'I:\src\hugo\9ong\content\post' #目的文件目录
__srcDir = 'I:\src\github-page\docs' #源文章目录
__desDir = 'I:\src\hugo\9ong\content\post' #目的文件目录
__ignoreFile = ["index.md","README.md",'more.md']#文件忽略
__ignoreParentDir = ["docs","post","content","互联网"]#分类忽略（父级目录）
def __init__(self):
print("···HugoMarkdown···\n")
#遍历源日志目录所有文件，批量处理
def scanFiles(self):
print("不再使用，除非有新的md文件目录需要批量转换")
return False
print("开始遍历源文章目录：",self.__srcDir,"\n")
for root,dirs,files in os.walk(self.__srcDir):
for file in files:
print("\n-----开始处理文章：",os.path.join(root,file),"-----\n")
if self.__isIgnoreFile(file):
print("忽略",file,"\n")
continue
fileInfoDict = self.__getFileInfo(root,file)
if (fileInfoDict['fileExt'] != ".md") or (fileInfoDict['parentDir']==''):
print("忽略",file,"\n")
continue
#测试输出
print(fileInfoDict,"\n")
self.__adjustFIleContent(fileInfoDict)
#只循环一次，跳出所有循环
# return
def scanFile(self,filePath):
self.__srcDir = self.__desDir
root = os.path.dirname(filePath)
file = os.path.basename(filePath)
# print(os.path.join(root,file))
# return False
print("\n-----开始处理文章：",os.path.join(root,file),"-----\n")
if self.__isIgnoreFile(file):
print("忽略",file,"\n")
return False
fileInfoDict = self.__getFileInfo(root,file)
if (fileInfoDict['fileExt'] != ".md") or (fileInfoDict['parentDir']==''):
print("忽略",file,"\n")
return False
#测试输出
print(fileInfoDict,"\n")
self.__adjustFIleContent(fileInfoDict)
def __getFileInfo(self,root,file):
print("获取文章信息：\n")
#文件全路径
filePath = os.path.join(root,file)
#文件名、扩展名
filename,fileExt = os.path.splitext(file)
#所在目录及上级目录
parentDir = os.path.basename(root)
grandpaDir = os.path.basename(os.path.dirname(root))
if self.__isIgnoreParentDir(parentDir):
parentDir = ""
if self.__isIgnoreParentDir(grandpaDir):
grandpaDir = ""
#文件相关时间
fileCtime = self.__timeToDate(os.path.getctime(filePath),"%Y-%m-%d")
fileMtime = self.__timeToDate(os.path.getmtime(filePath),"%Y-%m-%d")
return {
"filePath":filePath,
"fileName":filename,
"fileExt":fileExt,
"parentDir":parentDir,
"grandpaDir":grandpaDir,
"fileCtime":fileCtime,
"fileMtime":fileMtime
}
def __isIgnoreParentDir(self,parentDir):
if parentDir in self.__ignoreParentDir:
return True
#调整文章内容 比如meta设置、TOC、MORE设置，
def __adjustFIleContent(self,fileInfoDict):
#读取文章内容 及 关键词
print("读取文章内容...\n")
with open(fileInfoDict['filePath'],"r",encoding="utf-8") as mdFile:
content = mdFile.read().strip()
fileInfoDict['keywords'] = self.__getKeywords(content,fileInfoDict['fileName'])
content = self.__getMmeta(fileInfoDict) + self.__insertMoreToContent(content)
#写入新文件
self.__writeNewMarkdownFile(content,fileInfoDict)
#获取meta
def __getMmeta(self,fileInfoDict):
print("准备文章meta信息：","\n")
meta = ""
metaTitle = "title: \""+fileInfoDict['fileName']+"\"\n"
metaCJK = "isCJKLanguage: true\n"
metaDate = "date: "+fileInfoDict['fileCtime']+"\n"
metaCategories = "categories: \n"
metaParentCategory = ""
metaGrandpaCategory = ""
metaTags = "tags: \n"
metaTagsList = ""
metaKeywords = "keywords: \n"
metaKeywordsList = ""
if fileInfoDict['grandpaDir']!='':
metaGrandpaCategory = "- "+fileInfoDict['grandpaDir']+"\n"
if fileInfoDict['parentDir']!='':
metaParentCategory = "- "+fileInfoDict['parentDir']+"\n"
if fileInfoDict['keywords']:
for word in fileInfoDict['keywords']:
metaTagsList += "- "+word+"\n"
metaKeywordsList += "- "+word+"\n"
meta = "---\n"+metaTitle+metaCJK+metaDate+metaCategories+metaGrandpaCategory+metaParentCategory+metaTags+metaTagsList+metaKeywords+metaKeywordsList+"---\n\n"
print(meta,"\n")
return meta
#插入
到文章
def __insertMoreToContent(self,content):
tocFlag = '<!-- /TOC -->
<!--more-->
'
if (content.find(tocFlag) != -1):
print("发现",tocFlag,"\n")
content = content.replace(tocFlag,tocFlag+"\n"+'<!--more-->'+"\n")
else:
print("没有发现",tocFlag,"\n")
contents = content.splitlines()
contentsLen = len(contents)
if contentsLen>4:
contents[4] = contents[4]+"\n"+'<!--more-->'+"\n"
content = "\n".join(contents)
print("插入<!--more-->...","\n")
return content
def __writeNewMarkdownFile(self,content,fileInfoDict):
relativeFilePath = fileInfoDict['filePath'].replace(self.__srcDir,"")
desFilePath = self.__desDir+relativeFilePath
print("写入新文件：",desFilePath,"\n")
desDirPath = os.path.dirname(desFilePath)
# print("##Final Path："+desFilePath)
# return
if not os.path.exists(desDirPath):
os.makedirs(desDirPath)
with open(desFilePath,"w",encoding="utf-8") as nf:
nf.write(content)
if os.path.exists(desFilePath):
print("----- 完成文章处理：",desFilePath," -----\n")
else:
print("---- 写入新文件失败! -----\n")
def __isIgnoreFile(self,file):
if file in self.__ignoreFile:
return True
#时间戳转换成日期
def __timeToDate(self,timeStamp,format="%Y-%m-%d %H:%M:%S"):
timeArray = time.localtime(timeStamp)
return time.strftime("%Y-%m-%d %H:%M:%S", timeArray)
#获取文章关键词
def __getKeywords(self,content,filename):
keywords = self.__wordStatistics(content,filename)
keywordsList = sorted(keywords.items(), key=lambda item:item[1], reverse=True)
keywordsList = keywordsList[0:50]
keywordsList = self.__filterKeywords(keywordsList,filename)
print("保留关键词：",keywordsList,"\n")
return keywordsList
#词频统计
def __wordStatistics(self,content,filename):
stopwords = open('stopwords.txt', 'r', encoding='utf-8').read().split('\n')[:-1]
words_dict = {}
temp = jieba.cut(content)
for t in temp:
if t in stopwords or t == 'unknow' or t.strip() == "":
continue
if t in words_dict.keys():
words_dict[t] += 1
else:
words_dict[t] = 1
# filenameCuts = jieba.cut(filename)
# for fc in filenameCuts:
# if fc in stopwords or fc == 'unknow' or fc.strip() == "":
# continue
# if fc in words_dict.keys():
# words_dict[fc] += 100
# else:
# words_dict[fc] = 100
return words_dict
#再次过滤关键词：在文件名也就是标题中，且汉字不少于2个，字符串不少于3个，不是纯数字
def __filterKeywords(self,keywordsList,filename):
print("分析文章标签/关键词...\n")
newKeywordsList = []
# print(keywordsList)
# enD = enchant.Dict("en_US")
for word,count in keywordsList:
# print(word,"\t",count)
wordLen = len(word)
if filename.find(word)!=-1:
if self.__isChinese(word) and wordLen<2:
continue
elif wordLen<3:
continue
elif word.isdigit():
continue
else:
newKeywordsList.append(word)
# else:
# if wordLen>1 and self.__isChinese(word) and count>5:
# newKeywordsList.append(word)
# elif wordLen>2 and enD.check(word) and count>5:
# newKeywordsList.append(word)
# else:
# continue
return newKeywordsList
def __isChinese(self,word):
for ch in word:
if '\u4e00' <= ch <= '\u9fff':
return True
return False
if __name__ == '__main__':
hm = HugoMarkdown()
#scanFiles 扫描一个目录下所有文件，批量处理
# hm.scanFiles()
#单独处理一个文件，覆盖原文件，注意保存
theFile = input(r'输入文章绝对路径，比如I:\src\xxx\xxx\content\post\其他\xxx.md：')
hm.scanFile(theFile)
# theFile = r'I:\srcxxx\xxxx\content\post\其他\xxx.md'
|