def extract_students_mail_and_name_from_gmail(user=None, pwd=None, server="imap.gmail.com",
mailfolder=["ensae/actuariat"],
date="1-Jan-2016", fLOG=noLOG):
"""
Extracts mails and names from a mail box.
@param user user of the gmail inbox
@param pwd password of the gmail inbox
@param server gmail server, it should be ``"imap.gmail.com"``,
it works with others mail servers using the *IMAP* protocol
@param mailfolder folder in your inbox to look into,
there can be several
@param date when to start looking (do not change the format,
look at the default value)
@param fLOG logging function
@return list of dictionary ``[{"name": ..., "mail": ...}]``
"""
box = MailBoxImap(user, pwd, server, ssl=True, fLOG=fLOG)
box.login()
emails, suggestions = grab_addresses(
box, mailfolder, date, names=True, fLOG=fLOG)
box.logout()
rows = []
for mail in emails:
el = {"mail": mail}
if mail in suggestions:
el["name"] = ";".join(sorted(suggestions[mail]))
rows.append(el)
return rows
def should_bemocked_test_fetch_mail(self):
imap = MailBoxImap("somebody", "pwd", "imap.gmail.com", True)
imap.login()
iter = imap.enumerate_search_subject("subject", "inbox")
for m in iter:
m.dump(iter, "destination")
imap.logout()
def test_mailbox_extended(self):
fLOG(
__file__,
self._testMethodName,
OutputPrint=__name__ == "__main__")
if is_travis_or_appveyor():
warnings.warn("requires a password")
return
now = datetime.datetime.now()
now -= datetime.timedelta(1)
date = now.strftime("%d-%b-%Y")
if "DOUZE2016" in os.environ.get("COMPUTERNAME", ""):
# does not work on the remote build server
return
with warnings.catch_warnings():
warnings.simplefilter('ignore', DeprecationWarning)
import keyring
user = keyring.get_password("gmail", "pymmails,user")
code = keyring.get_password("gmail", "pymmails,pwd")
box = MailBoxImap(user, code, "imap.gmail.com", ssl=True, fLOG=fLOG)
box.login()
mails = box.enumerate_mails_in_folder("inbox", date=date)
li = list(mails)
self.assertTrue(len(li) > 0)
box.logout()
issues = []
for mail in li:
name = mail.get_name()
if "=?" in mail:
issues.append(name)
fr = mail.get_from()
frm = [_ for _ in fr if _]
if "=?" in frm[0]:
issues.append(name)
if "@" not in fr[1]:
issues.append(name)
if len(issues) > 0:
raise Exception("Issues with\n{0}".format(
"\n".join(str(_) for _ in issues)))
def test_mailbox(self):
fLOG(
__file__,
self._testMethodName,
OutputPrint=__name__ == "__main__")
if is_travis_or_appveyor():
warnings.warn("requires a password")
return
with warnings.catch_warnings():
warnings.simplefilter('ignore', DeprecationWarning)
import keyring
code = keyring.get_password("sdut", "pymmails")
box = MailBoxImap("unittest.sdpython", code,
"imap.gmail.com", ssl=True, fLOG=fLOG)
box.login()
mails = box.enumerate_mails_in_folder("test4", date="1-Jan-2016")
li = list(mails)
self.assertEqual(len(li), 3)
box.logout()
def test_mailbox_dump(self):
fLOG(
__file__,
self._testMethodName,
OutputPrint=__name__ == "__main__")
if is_travis_or_appveyor():
warnings.warn("requires a password")
return
with warnings.catch_warnings():
warnings.simplefilter('ignore', DeprecationWarning)
import keyring
code = keyring.get_password("sdut", "pymmails")
temp = get_temp_folder(__file__, "temp_dump")
box = MailBoxImap("unittest.sdpython", code,
"imap.gmail.com", ssl=True, fLOG=fLOG)
render = EmailMessageRenderer()
box.login()
mails = box.enumerate_mails_in_folder("test4", date="1-Jan-2016")
for mail in mails:
mail.dump(render, location=temp, fLOG=fLOG)
render.flush()
box.logout()
def extract_students_mail_and_name_from_gmail(user=None,
pwd=None,
server="imap.gmail.com",
mailfolder=["ensae/actuariat"],
date="1-Jan-2016",
fLOG=noLOG):
"""
Extract mails and names from a mail box
@param user user of the gmail inbox
@param pwd password of the gmail inbox
@param server gmail server, it should be ``"imap.gmail.com"``,
it works with others mail servers using the *IMAP* protocol
@param mailfolder folder in your inbox to look into,
there can be several
@param date when to start looking (do not change the format,
look at the default value)
@param fLOG logging function
@return list of dictionary ``[{"name": ..., "mail": ...}]``
"""
box = MailBoxImap(user, pwd, server, ssl=True, fLOG=fLOG)
box.login()
emails, suggestions = grab_addresses(box,
mailfolder,
date,
names=True,
fLOG=fLOG)
box.logout()
rows = []
for mail in emails:
el = {"mail": mail}
if mail in suggestions:
el["name"] = ";".join(sorted(suggestions[mail]))
rows.append(el)
return rows
"*****@*****.**",
"*****@*****.**",
]
###############
# gather mails
fLOG("fetch mails")
if os.path.exists(filename_mails):
with open(filename_mails, "r", encoding="utf8") as f:
lines = f.readlines()
emails = [l.strip("\r\t\n ") for l in lines]
else:
box = MailBoxImap(user, pwd, server, ssl=True, fLOG=fLOG)
box.login()
emails = grab_addresses(box, mailfolder, date, fLOG=fLOG)
box.logout()
emails = list(
sorted(
set([
_.strip("<>").lower() for _ in emails if _ not in skip_address
])))
with open(filename_mails, "w", encoding="utf8") as f:
f.write("\n".join(emails))
#####################
# create a dataframe
import pandas
def extract_students_mails_from_gmail_and_stores_in_folders(folder=".", filemails="emails.txt",
user=None, pwd=None, server="imap.gmail.com",
mailfolder=[
"ensae/ENSAE_2016_3A"],
date="1-Jan-2016", zipfilename="projet_3A_2016.zip",
zipencpwd=b"sixteenbyteskeys", dataframe=None,
columns={
"name": "nom_prenom", "group": "groupe", "subject": "sujet"},
skip_names=None, process_name=None,
title="List of emails", nolink_if=None, fLOG=fLOG):
"""
The scenario is the following:
* You are the teacher.
* Students started their projects at date *t*.
* They can work alone or by group.
* They send mails, you reply.
* Their address mail follows the convention: ``<first name>.<last name>@anything``
so it is to associate a mail address to a student name.
* You move every mail you received in a separate folder in your inbox.
* Sometime, you send a mail to everybody.
* Finally they send their project with attachments.
* You want to store everything (mails and attachements) in folders, one per group.
* You want a summary of what was received.
* You want to build a zip file to share their work with others teachers.
* You want to update the folder if a new mail was sent.
This function looks into a folder of your inbox and grabs every mails and
attachements from a groups of students.
@param folder where to store the results
@param filemails files used to store students address,
the operation is done once, remove the file
to force the function to rebuild the information.
@param user user of the gmail inbox
@param pwd password of the gmail inbox
@param server gmail server, it should be ``"imap.gmail.com"``,
it works with others mail servers using the *IMAP* protocol
@param mailfolder folder in your inbox to look into,
there can be several
@param date when to start looking (do not change the format,
look at the default value)
@param zipfilename name of the zip file to create
@param zipencpwd the zip file is also encrypted for a safer share with this key
and function `encrypt_stream <http://www.xavierdupre.fr/app/pyquickhelper/helpsphinx/
pyquickhelper/filehelper/encryption.html#pyquickhelper.filehelper.encryption.encrypt_stream>`_.
@param dataframe dataframe which contains the definition of students groups
@param columns columns the function will look into, students names, group definition
(a unique number for all students in the same group), subject
@param skip_names list of names to skip
@param process_name to operate a transformation before matching students names with
their emails
@param title each group folder contains a html file connecting them,
this is its title
@param nolink_if The summary extracts links from url, it skips the urls which
contains on the substrings included in that list (None to use a default set)
@param fLOG logging function
@return @see cl ProjectsRepository
By default, Gmail does not let you programmatically access you own inbox,
you need to modify your gmail parameters to let this function do so.
"""
folder = os.path.abspath(".")
filemails = os.path.join(folder, filemails)
zipfilename = os.path.join(folder, zipfilename)
zipfilenameenc = zipfilename + ".enc"
# load the groups
if isinstance(dataframe, pandas.DataFrame):
df = dataframe
elif dataframe.endswith("xlsx"):
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] read dataframe", dataframe)
df = pandas.read_excel(dataframe)
else:
df = pandas.read_csv(dataframe, sep="\t", encoding="utf8")
# check mails
if "mail" not in columns:
if os.path.exists(filemails):
fLOG(
"[extract_students_mails_from_gmail_and_stores_in_folders] read addresses from ", filemails)
with open(filemails, "r", encoding="utf8") as f:
lines = f.readlines()
emails = [li.strip("\r\t\n ") for li in lines]
else:
fLOG(
"[extract_students_mails_from_gmail_and_stores_in_folders] mine address ")
box = MailBoxImap(user, pwd, server, ssl=True, fLOG=fLOG)
box.login()
emails = grab_addresses(box, mailfolder, date, fLOG=fLOG)
box.logout()
with open(filemails, "w", encoding="utf8") as f:
f.write("\n".join(emails))
else:
# nothing to do mail already present
emails = set(df[columns["mail"]])
# we remove empty names
df = df[~df[columns["name"]].isnull()].copy()
if process_name:
df[columns["name"]] = df[columns["name"]].apply(
lambda f: process_name(f))
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] create groups folders in", folder)
proj = ProjectsRepository(folder, fLOG=fLOG)
proj = ProjectsRepository.create_folders_from_dataframe(df, folder,
col_subject=columns[
"subject"], fLOG=fLOG, col_group=columns["group"],
col_student=columns[
"name"], email_function=emails, skip_if_nomail=False,
col_mail=columns["mail"], must_have_email=True, skip_names=skip_names)
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] nb groups", len(
proj.Groups))
# gathers mails
email_renderer = EmailMessageRenderer(tmpl=template_email_html_short,
fLOG=fLOG)
renderer = EmailMessageListRenderer(title=title, email_renderer=email_renderer,
fLOG=fLOG)
box = MailBoxImap(user, pwd, server, ssl=True, fLOG=fLOG)
box.login()
proj.dump_group_mails(renderer, group=None, mailbox=box, subfolder=mailfolder,
date=date, overwrite=False, skip_if_empty=True)
box.logout()
# cleaning files
for group in proj.Groups:
files = list(proj.enumerate_group_files(group))
att = [_ for _ in files if ".html" in _]
if len(att) <= 1:
fLOG(
"[extract_students_mails_from_gmail_and_stores_in_folders] remove '{}'".format(group))
proj.remove_group(group)
# unzip files and convert notebooks
for group in proj.Groups:
proj.unzip_convert(group)
summary = os.path.join(folder, "index.html")
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] write summary '{}'".format(summary))
if os.path.exists(summary):
os.remove(summary)
proj.write_run_command()
proj.write_summary(nolink_if=nolink_if)
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] zip everything in", zipfilename)
if os.path.exists(zipfilename):
os.remove(zipfilename)
proj.zip_group(None, zipfilename,
addition=["index.html", "mail_style.css", "emails.txt"])
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] encrypt the zip file in '{}'.".format(
zipfilenameenc))
if os.path.exists(zipfilenameenc):
os.remove(zipfilenameenc)
encrypt_stream(zipencpwd, zipfilename, zipfilenameenc, chunksize=2 ** 30)
return proj
"*****@*****.**",
"*****@*****.**",
]
###############
# gather mails
fLOG("fetch mails")
if os.path.exists(filename_mails):
with open(filename_mails, "r", encoding="utf8") as f:
lines = f.readlines()
emails = [l.strip("\r\t\n ") for l in lines]
else:
box = MailBoxImap(user, pwd, server, ssl=True, fLOG=fLOG)
box.login()
emails = grab_addresses(box, mailfolder, date, fLOG=fLOG)
box.logout()
emails = list(sorted(set([_.strip("<>").lower()
for _ in emails if _ not in skip_address])))
with open(filename_mails, "w", encoding="utf8") as f:
f.write("\n".join(emails))
#####################
# create a dataframe
import pandas
rows = [{"nom_prenom": mail, "sujet": "octobre", "groupe": i + 1}
for i, mail in enumerate(emails)]
df = pandas.DataFrame(rows)
def extract_students_mails_from_gmail_and_stores_in_folders(folder=".", filemails="emails.txt",
user=None, pwd=None, server="imap.gmail.com",
mailfolder=[
"ensae/ENSAE_2016_3A"],
date="1-Jan-2016", zipfilename="projet_3A_2016.zip",
zipencpwd=b"sixteenbyteskeys", dataframe=None,
columns={
"name": "nom_prenom", "group": "groupe", "subject": "sujet"},
skip_names=None, process_name=None,
title="List of emails", nolink_if=None, fLOG=fLOG):
"""
The scenario is the following:
* You are the teacher.
* Students started their projects at date *t*.
* They can work alone or by group.
* They send mails, you reply.
* Their address mail follows the convention: ``<first name>.<last name>@anything``
so it is to associate a mail address to a student name.
* You move every mail you received in a separate folder in your inbox.
* Sometime, you send a mail to everybody.
* Finally they send their project with attachments.
* You want to store everything (mails and attachements) in folders, one per group.
* You want a summary of what was received.
* You want to build a zip file to share their work with others teachers.
* You want to update the folder if a new mail was sent.
This function looks into a folder of your inbox and grabs every mails and
attachements from a groups of students.
@param folder where to store the results
@param filemails files used to store students address,
the operation is done once, remove the file
to force the function to rebuild the information.
@param user user of the gmail inbox
@param pwd password of the gmail inbox
@param server gmail server, it should be ``"imap.gmail.com"``,
it works with others mail servers using the *IMAP* protocol
@param mailfolder folder in your inbox to look into,
there can be several
@param date when to start looking (do not change the format,
look at the default value)
@param zipfilename name of the zip file to create
@param zipencpwd the zip file is also encrypted for a safer share with this key
and function `encrypt_stream <http://www.xavierdupre.fr/app/pyquickhelper/helpsphinx/
pyquickhelper/filehelper/encryption.html#pyquickhelper.filehelper.encryption.encrypt_stream>`_.
@param dataframe dataframe which contains the definition of students groups
@param columns columns the function will look into, students names, group definition
(a unique number for all students in the same group), subject
@param skip_names list of names to skip
@param process_name to operate a transformation before matching students names with
their emails
@param title each group folder contains a html file connecting them,
this is its title
@param nolink_if The summary extracts links from url, it skips the urls which
contains on the substrings included in that list (None to use a default set)
@param fLOG logging function
@return @see cl ProjectsRepository
By default, Gmail does not let you programmatically access you own inbox,
you need to modify your gmail parameters to let this function do so.
"""
folder = os.path.abspath(".")
filemails = os.path.join(folder, filemails)
zipfilename = os.path.join(folder, zipfilename)
zipfilenameenc = zipfilename + ".enc"
# load the groups
if isinstance(dataframe, pandas.DataFrame):
df = dataframe
elif dataframe.endswith("xlsx"):
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] read dataframe", dataframe)
df = pandas.read_excel(dataframe)
else:
df = pandas.read_csv(dataframe, sep="\t", encoding="utf8")
# check mails
if "mail" not in columns:
if os.path.exists(filemails):
fLOG(
"[extract_students_mails_from_gmail_and_stores_in_folders] read addresses from ", filemails)
with open(filemails, "r", encoding="utf8") as f:
lines = f.readlines()
emails = [l.strip("\r\t\n ") for l in lines]
else:
fLOG(
"[extract_students_mails_from_gmail_and_stores_in_folders] mine address ")
box = MailBoxImap(user, pwd, server, ssl=True, fLOG=fLOG)
box.login()
emails = grab_addresses(box, mailfolder, date, fLOG=fLOG)
box.logout()
with open(filemails, "w", encoding="utf8") as f:
f.write("\n".join(emails))
else:
# nothing to do mail already present
emails = set(df[columns["mail"]])
# we remove empty names
df = df[~df[columns["name"]].isnull()].copy()
if process_name:
df[columns["name"]] = df[columns["name"]].apply(
lambda f: process_name(f))
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] create groups folders in", folder)
proj = ProjectsRepository(folder, fLOG=fLOG)
proj = ProjectsRepository.create_folders_from_dataframe(df, folder,
col_subject=columns[
"subject"], fLOG=fLOG, col_group=columns["group"],
col_student=columns[
"name"], email_function=emails, skip_if_nomail=False,
col_mail=columns["mail"], must_have_email=True, skip_names=skip_names)
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] nb groups", len(
proj.Groups))
# gathers mails
email_renderer = EmailMessageRenderer(tmpl=template_email_html_short,
fLOG=fLOG)
renderer = EmailMessageListRenderer(title=title, email_renderer=email_renderer,
fLOG=fLOG)
box = MailBoxImap(user, pwd, server, ssl=True, fLOG=fLOG)
box.login()
proj.dump_group_mails(renderer, group=None, mailbox=box, subfolder=mailfolder,
date=date, overwrite=False, skip_if_empty=True)
box.logout()
# cleaning files
for group in proj.Groups:
files = list(proj.enumerate_group_files(group))
att = [_ for _ in files if ".html" in _]
if len(att) <= 1:
fLOG(
"[extract_students_mails_from_gmail_and_stores_in_folders] remove ", group)
proj.remove_group(group)
# unzip files and convert notebooks
for group in proj.Groups:
proj.unzip_convert(group)
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] summary ")
summary = os.path.join(folder, "index.html")
if os.path.exists(summary):
os.remove(summary)
proj.write_summary(nolink_if=nolink_if)
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] zip everything in", zipfilename)
if os.path.exists(zipfilename):
os.remove(zipfilename)
proj.zip_group(None, zipfilename,
addition=["index.html", "mail_style.css", "emails.txt"])
fLOG("[extract_students_mails_from_gmail_and_stores_in_folders] encrypt the zip file in", zipfilenameenc)
if os.path.exists(zipfilenameenc):
os.remove(zipfilenameenc)
encrypt_stream(zipencpwd, zipfilename, zipfilenameenc, chunksize=2 ** 30)
return proj