Last active
December 4, 2015 17:27
-
-
Save alaminopu/c2e5e7bf9cfaec7fcbe2 to your computer and use it in GitHub Desktop.
Export yahoo mail to Excel file.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python | |
| import imaplib, email | |
| import xlsxwriter | |
| from BeautifulSoup import BeautifulSoup | |
| # email login section | |
| username = 'your email username' | |
| password = 'your password' | |
| url = "imap.mail.yahoo.com" | |
| email_account = imaplib.IMAP4_SSL(url) | |
| typ, accountDetails = email_account.login(username, password) | |
| if typ != 'OK': | |
| print 'Not able to sign in!' | |
| else: | |
| print 'Logged in' | |
| # Selecting | |
| email_account.select() | |
| typ, data = email_account.search(None, 'ALL') | |
| if typ != 'OK': | |
| print 'Error Searching inbox' | |
| else: | |
| print 'Searching Successful' | |
| # Excel sheet opening | |
| workbook = xlsxwriter.Workbook('emails.xlsx') | |
| worksheet = workbook.add_worksheet() | |
| # writing headers of excel sheet | |
| worksheet.write(0,0, 'SL') | |
| worksheet.write(0,1, 'From') | |
| worksheet.write(0,2, 'Subject') | |
| worksheet.write(0,3, 'Message') | |
| sl = 0 | |
| row = 1 | |
| col = 0 | |
| # email scrapping section | |
| for num in data[0].split(): | |
| # typ, data = email_account.fetch(num, '(BODY[HEADER.FIELDS (FROM TO SUBJECT)])') | |
| # recip,send,subj = data[0][1].split("\r\n")[:3] | |
| # print recip | |
| # print send | |
| # print subj | |
| typ, data = email_account.fetch(num, '(RFC822)') | |
| if typ != 'OK': | |
| print 'Error fetching mail.' | |
| msg = email.message_from_string(data[0][1]) | |
| # wring to worksheet | |
| sl = sl + 1 | |
| worksheet.write(row , col, str(sl)) | |
| worksheet.write(row, col+1, msg['From']) | |
| worksheet.write(row, col+2, msg['Subject']) | |
| for part in msg.walk(): | |
| if part.get_content_maintype() == 'multipart': | |
| cleantext = BeautifulSoup(part.as_string()).text | |
| worksheet.write(row, col+3 , cleantext) | |
| continue | |
| if part.get('Content-Disposition') is None: | |
| #print part.as_string() | |
| cleantext = BeautifulSoup(part.as_string()).text | |
| worksheet.write(row, col+3 , cleantext) | |
| continue | |
| row = row +1 | |
| # closing part | |
| workbook.close() | |
| email_account.close() | |
| email_account.logout() | |
| print "Done!" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
parsing HTML can be done with BeautifulSoup