kjaymiller/eml_to_html.py

## eml_to_html.py
"""
Takes files in a directory and strips out the html
created: 20160503
by: Kevin 'Jay' Miller
kjaymiller@gmail.com

Place this
"""

from os import listdir
import re


def merge_emails(path='.'):
    files = sorted(listdir(path))
    merger = []
    mail_text = re.compile(r'\<\/*html\>', re.M)
    mail_subject = re.compile(r'^Subject: .+$', re.M)

    for email in files:
        with open(email, 'r') as f:

            if email.endswith('.eml'):
                f = f.read()
                subject = (re.search(mail_subject, f).group(0))
                merger.append('<h1>{}</h1>'.format(subject))
                text = re.split(mail_text, f)[-2]
                merger.append(text)

    html = '<html>\n{}</html>'.format(''.join(merger))
    return html


def create_html(html):
    with open('merged_emails.pdf', 'w+') as f:
        f.write(html)


def run():
    html = merge_emails()
    create_html(html)


if __name__ == '__main__':
    run()
	"""
	Takes files in a directory and strips out the html
	created: 20160503
	by: Kevin 'Jay' Miller
	kjaymiller@gmail.com

	Place this
	"""

	from os import listdir
	import re


	def merge_emails(path='.'):
	files = sorted(listdir(path))
	merger = []
	mail_text = re.compile(r'\<\/*html\>', re.M)
	mail_subject = re.compile(r'^Subject: .+$', re.M)

	for email in files:
	with open(email, 'r') as f:

	if email.endswith('.eml'):
	f = f.read()
	subject = (re.search(mail_subject, f).group(0))
	merger.append('<h1>{}</h1>'.format(subject))
	text = re.split(mail_text, f)[-2]
	merger.append(text)

	html = '<html>\n{}</html>'.format(''.join(merger))
	return html


	def create_html(html):
	with open('merged_emails.pdf', 'w+') as f:
	f.write(html)


	def run():
	html = merge_emails()
	create_html(html)


	if __name__ == '__main__':
	run()