質問編集履歴
4
かんせーい
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -162,3 +162,160 @@
|
|
|
162
162
|
|
|
163
163
|
-----------------------
|
|
164
164
|
ATTACH_FILE_NAME:
|
|
165
|
+
|
|
166
|
+
|
|
167
|
+
|
|
168
|
+
↓完成！！！！🌟
|
|
169
|
+
```Python
|
|
170
|
+
|
|
171
|
+
import sys
|
|
172
|
+
import email
|
|
173
|
+
from email.header import decode_header
|
|
174
|
+
import datetime
|
|
175
|
+
import glob
|
|
176
|
+
import openpyxl
|
|
177
|
+
|
|
178
|
+
class MailParser(object):
|
|
179
|
+
"""
|
|
180
|
+
メールファイルのパスを受け取り、それを解析するクラス
|
|
181
|
+
"""
|
|
182
|
+
|
|
183
|
+
def __init__(self, mail_file_path):
|
|
184
|
+
self.mail_file_path = mail_file_path
|
|
185
|
+
# emlファイルからemail.message.Messageインスタンスの取得
|
|
186
|
+
with open(mail_file_path, 'rb') as email_file:
|
|
187
|
+
self.email_message = email.message_from_bytes(email_file.read())
|
|
188
|
+
self.subject = None
|
|
189
|
+
self.to_address = None
|
|
190
|
+
self.cc_address = None
|
|
191
|
+
self.from_address = None
|
|
192
|
+
self.body = ""
|
|
193
|
+
self.date = None
|
|
194
|
+
# 添付ファイル関連の情報
|
|
195
|
+
# {name: file_name, data: data}
|
|
196
|
+
self.attach_file_list = []
|
|
197
|
+
# emlの解釈
|
|
198
|
+
self._parse()
|
|
199
|
+
|
|
200
|
+
def get_attr_data(self):
|
|
201
|
+
"""
|
|
202
|
+
メールデータの取得
|
|
203
|
+
"""
|
|
204
|
+
result = """\
|
|
205
|
+
日時: {}
|
|
206
|
+
FROM: {}
|
|
207
|
+
TO: {}
|
|
208
|
+
CC: {}
|
|
209
|
+
-----------------------
|
|
210
|
+
本文:
|
|
211
|
+
{}
|
|
212
|
+
-----------------------
|
|
213
|
+
ATTACH_FILE_NAME:
|
|
214
|
+
{}
|
|
215
|
+
""".format(
|
|
216
|
+
self.date,
|
|
217
|
+
self.from_address,
|
|
218
|
+
self.to_address,
|
|
219
|
+
self.cc_address,
|
|
220
|
+
self.body,
|
|
221
|
+
",".join([ x["name"] for x in self.attach_file_list])
|
|
222
|
+
)
|
|
223
|
+
return result
|
|
224
|
+
|
|
225
|
+
|
|
226
|
+
def _parse(self):
|
|
227
|
+
"""
|
|
228
|
+
メールファイルの解析
|
|
229
|
+
__init__内で呼び出している
|
|
230
|
+
"""
|
|
231
|
+
self.subject = self._get_decoded_header("Subject")
|
|
232
|
+
self.to_address = self._get_decoded_header("To")
|
|
233
|
+
self.cc_address = self._get_decoded_header("Cc")
|
|
234
|
+
self.from_address = self._get_decoded_header("From")
|
|
235
|
+
# 変更したところ
|
|
236
|
+
self.date = datetime.datetime.strptime(
|
|
237
|
+
self._get_decoded_header("Date"),
|
|
238
|
+
"%a, %d %b %Y %H:%M:%S %z"
|
|
239
|
+
)
|
|
240
|
+
|
|
241
|
+
# メッセージ本文部分の処理
|
|
242
|
+
for part in self.email_message.walk():
|
|
243
|
+
# ContentTypeがmultipartの場合は実際のコンテンツはさらに
|
|
244
|
+
# 中のpartにあるので読み飛ばす
|
|
245
|
+
if part.get_content_maintype() == 'multipart':
|
|
246
|
+
continue
|
|
247
|
+
# ファイル名の取得
|
|
248
|
+
attach_fname = part.get_filename()
|
|
249
|
+
# ファイル名がない場合は本文のはず
|
|
250
|
+
if not attach_fname:
|
|
251
|
+
charset = str(part.get_content_charset())
|
|
252
|
+
if charset:
|
|
253
|
+
self.body += part.get_payload(decode=True).decode(charset, errors="replace")
|
|
254
|
+
else:
|
|
255
|
+
self.body += part.get_payload(decode=True)
|
|
256
|
+
else:
|
|
257
|
+
# ファイル名があるならそれは添付ファイルなので
|
|
258
|
+
# データを取得する
|
|
259
|
+
self.attach_file_list.append({
|
|
260
|
+
"name": attach_fname,
|
|
261
|
+
"data": part.get_payload(decode=True)
|
|
262
|
+
})
|
|
263
|
+
|
|
264
|
+
def _get_decoded_header(self, key_name):
|
|
265
|
+
"""
|
|
266
|
+
ヘッダーオブジェクトからデコード済の結果を取得する
|
|
267
|
+
"""
|
|
268
|
+
ret = ""
|
|
269
|
+
|
|
270
|
+
# 該当項目がないkeyは空文字を戻す
|
|
271
|
+
raw_obj = self.email_message.get(key_name)
|
|
272
|
+
if raw_obj is None:
|
|
273
|
+
return ""
|
|
274
|
+
# デコードした結果をunicodeにする
|
|
275
|
+
for fragment, encoding in decode_header(raw_obj):
|
|
276
|
+
if not hasattr(fragment, "decode"):
|
|
277
|
+
ret += fragment
|
|
278
|
+
continue
|
|
279
|
+
# encodeがなければとりあえずUTF-8でデコードする
|
|
280
|
+
if encoding:
|
|
281
|
+
ret += fragment.decode(encoding)
|
|
282
|
+
else:
|
|
283
|
+
ret += fragment.decode("UTF-8")
|
|
284
|
+
return ret
|
|
285
|
+
|
|
286
|
+
if __name__ == "__main__":
|
|
287
|
+
# ブックを取得
|
|
288
|
+
book = openpyxl.load_workbook(r'C:\Users\ああああ\Desktop\あああ\あああああ.xlsx')
|
|
289
|
+
# シートを取得
|
|
290
|
+
sheet = book['Sheet1']
|
|
291
|
+
|
|
292
|
+
tifCounter = len(glob.glob1("./mail","*.eml"))
|
|
293
|
+
print("🙌総メール件数",tifCounter,"件🙌")
|
|
294
|
+
|
|
295
|
+
i=2
|
|
296
|
+
for mail_file_path in glob.glob('./mail/*'):
|
|
297
|
+
try:
|
|
298
|
+
result = MailParser(mail_file_path)
|
|
299
|
+
# セルへ書き込む
|
|
300
|
+
sheet.cell(row=i, column=1).value = i-1
|
|
301
|
+
sheet.cell(row=i, column=2).value = result.date.replace(tzinfo=None)
|
|
302
|
+
sheet.cell(row=i, column=4).value = result.from_address.split("<")[0]
|
|
303
|
+
sheet.cell(row=i, column=5).value = result.from_address[:-1].split("<")[1]
|
|
304
|
+
sheet.cell(row=i, column=6).value = result.body
|
|
305
|
+
|
|
306
|
+
print(i-1,"件目💕書き込んだよ😘")
|
|
307
|
+
print(mail_file_path)
|
|
308
|
+
print()
|
|
309
|
+
except ValueError:
|
|
310
|
+
print(i-1,"件目エラーだよ😒")
|
|
311
|
+
print(mail_file_path)
|
|
312
|
+
print("👿👿👿👿👿👿👿👿👿👿👿👿👿👿")
|
|
313
|
+
print()
|
|
314
|
+
|
|
315
|
+
i+=1
|
|
316
|
+
|
|
317
|
+
# 保存する
|
|
318
|
+
book.save(r'C:\Users\ああああ\Desktop\あああ\あああああ.xlsx')
|
|
319
|
+
print("終わったよ😍")
|
|
320
|
+
|
|
321
|
+
```
|
3
ファイル
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -121,7 +121,7 @@
|
|
|
121
121
|
print(tifCounter)
|
|
122
122
|
for mail_file_path in glob.glob('./mail/*'):
|
|
123
123
|
# ブックを取得
|
|
124
|
-
book = openpyxl.load_workbook(r'C:\Users\
|
|
124
|
+
book = openpyxl.load_workbook(r'C:\Users\Desktop')
|
|
125
125
|
# シートを取得
|
|
126
126
|
sheet = book['Sheet1']
|
|
127
127
|
# セルへ書き込む
|
2
フォルダ名
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -121,14 +121,14 @@
|
|
|
121
121
|
print(tifCounter)
|
|
122
122
|
for mail_file_path in glob.glob('./mail/*'):
|
|
123
123
|
# ブックを取得
|
|
124
|
-
book = openpyxl.load_workbook(r'C:\Users\mediamagic\Desktop
|
|
124
|
+
book = openpyxl.load_workbook(r'C:\Users\mediamagic\Desktop')
|
|
125
125
|
# シートを取得
|
|
126
126
|
sheet = book['Sheet1']
|
|
127
127
|
# セルへ書き込む
|
|
128
128
|
sheet['A1'] = 'ナンバー'
|
|
129
129
|
sheet['B1'] = 100
|
|
130
130
|
# 保存する
|
|
131
|
-
book.save(r'C:\Users\
|
|
131
|
+
book.save(r'C:\Users\)
|
|
132
132
|
|
|
133
133
|
result = MailParser(mail_file_path).get_attr_data()
|
|
134
134
|
|
1
下に追加しましたー！！！！
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -146,3 +146,19 @@
|
|
|
146
146
|
|
|
147
147
|
https://teratail.com/questions/09h52spph2wsst
|
|
148
148
|
↑↑ここの回答者さんが説明を書いてくれてます〜。
|
|
149
|
+
|
|
150
|
+
|
|
151
|
+
print結果
|
|
152
|
+
|
|
153
|
+
総メール件数 1 件
|
|
154
|
+
日時: 2022-06-21 17:46:21+09:00
|
|
155
|
+
FROM: たこ焼きくん <aaaaa@aaaa.aaa>
|
|
156
|
+
TO: cccc@ccccc.cccc
|
|
157
|
+
CC:
|
|
158
|
+
-----------------------
|
|
159
|
+
本文:
|
|
160
|
+
はまやらわ
|
|
161
|
+
|
|
162
|
+
|
|
163
|
+
-----------------------
|
|
164
|
+
ATTACH_FILE_NAME:
|