def get_main_content(self, msg: email.message.EmailMessage):
'''
メール本文、フォーマット、キャラクターセットを取得する。
'''
try:
body_part = msg.get_body()
main_content = body_part.get_content()
format_ = body_part.get_content_type()
charset = body_part.get_content_charset()
except Exception as error:
print(error)
main_content = '解析失敗'
format_ = '不明'
charset = '不明'
# get_bodyでエラーになるのは文字コード設定がおかしいメールを受信した場合なので、
# decodeせずにテキスト部分をそのまま返す。
for part in msg.walk():
if part.get_content_type() == 'text/plain':
format_ = part.get_content_type()
main_content = str(part.get_payload())
charset = part.get_content_charset()
return main_content, format_, charset
def filter_email(eml: email.message.EmailMessage) -> str:
# Get plaintext part
body = eml.get_body("plain")
if body == None:
raise EmailParseException()
# Find a link in the body
link_re = r"(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’]))"
urls = re.findall(link_re, body.get_content())
if len(urls) == 0:
raise LinkNotFoundException()
url: str = urls[0][0]
# Some sites require this header
headers = {
'Accept' : 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.7) Gecko/2009021910 Firefox/3.0.7'
}
# Download the contents at that URL with urllib
request = urllib.request.Request(url, headers=headers)
with urllib.request.urlopen(request) as response:
webpage = response.read()
# Parse with BeautifulSoup
bs = BeautifulSoup(webpage, features='lxml')
content = bs.prettify()
return content
return url
def process_message(uid, msg: email.message.EmailMessage):
try:
raw_date = msg.get('Date')
local_date = None
# Now convert to local date-time
date_tuple = email.utils.parsedate_tz(raw_date)
if date_tuple:
local_date = datetime.datetime.fromtimestamp(
email.utils.mktime_tz(date_tuple))
except:
raw_date = None
local_date = None
links = []
try:
body = msg.get_body(('html', 'plain'))
if body:
if body.get_content_type() == 'text/plain':
links = links_from_plaintext(body.get_content())
elif body.get_content_type() == 'text/html':
links = links_from_html(body.get_content())
except:
pass
try:
msg_to = msg.get('To')
except:
msg_to = None
try:
msg_from = msg.get('From')
except:
msg_from = None
try:
msg_sub = msg.get('Subject')
except:
msg_sub = None
try:
msg_id = msg.get('Message-ID')
except:
msg_id = None
info = {
'uid': uid,
'to': msg_to,
'from': msg_from,
'subject': msg_sub,
'raw_date': raw_date,
'local_date': local_date,
'message-id': msg_id,
'links': links,
'num-links': len(links)
}
return info
