1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104
|
# libgmail -- Gmail access via Python
#
# Version: 0.0.9 (XX October 2004)
#
# Author: follower@myrealbox.com
#
# License: GPL 2.0
#
# Thanks:
# * Live HTTP Headers <http://livehttpheaders.mozdev.org/>
# * Gmail <http://gmail.google.com/>
# * Google Blogoscoped <http://blog.outer-court.com/>
# * ClientCookie <http://wwwsearch.sourceforge.net/ClientCookie/>
# (There when I needed it...)
# * The *first* big G. :-)
#
# NOTE:
# You should ensure you are permitted to use this script before using it
# to access Google's Gmail servers.
#
#
# Gmail Implementation Notes
# ==========================
#
# * Folders contain message threads, not individual messages. At present I
# do not know any way to list all messages without processing thread list.
#
from constants import *
import os
import re
import urllib
import urllib2
import logging
import mimetypes
from email.MIMEBase import MIMEBase
from email.MIMEText import MIMEText
from email.MIMEMultipart import MIMEMultipart
#logging.getLogger().setLevel(logging.DEBUG)
URL_LOGIN = "https://www.google.com/accounts/ServiceLoginBoxAuth"
URL_GMAIL = "https://gmail.google.com/gmail"
# TODO: Get these on the fly?
STANDARD_FOLDERS = [U_INBOX_SEARCH, U_STARRED_SEARCH,
U_ALL_SEARCH, U_DRAFTS_SEARCH,
U_SENT_SEARCH, U_SPAM_SEARCH]
# Constants with names not from the Gmail Javascript:
# TODO: Move to `constants.py`?
U_SAVEDRAFT_VIEW = "sd"
D_DRAFTINFO = "di"
# NOTE: All other DI_* field offsets seem to match the MI_* field offsets
DI_BODY = 19
versionWarned = False # If the Javascript version is different have we
# warned about it?
RE_SPLIT_PAGE_CONTENT = re.compile("D\((.*?)\);", re.DOTALL)
def _parsePage(pageContent):
"""
Parse the supplied HTML page and extract useful information from
the embedded Javascript.
"""
# Note: We use the easiest thing that works here and no longer
# extract the Javascript code we want from the page first.
items = (re.findall(RE_SPLIT_PAGE_CONTENT, pageContent))
# TODO: Check we find something?
itemsDict = {}
namesFoundTwice = []
for item in items:
item = item.strip()[1:-1]
name, value = (item.split(",", 1) + [""])[:2]
name = name[1:-1] # Strip leading and trailing single or double quotes.
try:
# By happy coincidence Gmail's data is stored in a form
# we can turn into Python data types by simply evaluating it.
# TODO: Parse this better/safer?
# TODO: Handle "mb" mail bodies better as they can be anything.
if value != "": # Empty strings aren't parsed successfully.
parsedValue = eval(value.replace("\n","").replace(",,",",None,").replace(",,",",None,")) # Yuck! Need two ",," replaces to handle ",,," overlap. TODO: Tidy this up... TODO: It appears there may have been a change in the number & order of at least the CS_* values, investigate.
else:
parsedValue = value
except SyntaxError:
logging.warning("Could not parse item `%s` as it was `%s`." %
(name, value))
else:
if itemsDict.has_key(name):
# This handles the case where a name key is used more than
# once (e.g. mail items, mail body) and automatically
# places the values into list.
# TODO: Check this actually works properly, it's early... :-)
if (name in namesFoundTwice):
itemsDict[name].append(parsedValue)
else:
itemsDict[name] = [itemsDict[name], parsedValue]
namesFoundTwice.append(name)
else:
itemsDict[name] = parsedValue
global versionWarned
if itemsDict[D_VERSION] != js_version and not versionWarned:
logging.debug("Live Javascript and constants file versions differ.")
versionWarned = True
return itemsDict
class CookieJar:
"""
A rough cookie handler, intended to only refer to one domain.
Does no expiry or anything like that.
(The only reason this is here is so I don't have to require
the `ClientCookie` package.)
"""
def __init__(self):
"""
"""
self._cookies = {}
def extractCookies(self, response, nameFilter = None):
"""
"""
# TODO: Do this all more nicely?
for cookie in response.headers.getheaders('Set-Cookie'):
name, value = (cookie.split("=", 1) + [""])[:2]
logging.debug("Extracted cookie `%s`" % (name))
if not nameFilter or name in nameFilter:
self._cookies[name] = value.split(";")[0]
logging.debug("Stored cookie `%s` value `%s`" %
(name, self._cookies[name]))
def addCookie(self, name, value):
"""
"""
self._cookies[name] = value
def setCookies(self, request):
"""
"""
request.add_header('Cookie',
";".join(["%s=%s" % (k,v)
for k,v in self._cookies.items()]))
def _buildURL(**kwargs):
"""
"""
return "%s?%s" % (URL_GMAIL, urllib.urlencode(kwargs))
def _paramsToMime(params, filenames, files):
"""
"""
mimeMsg = MIMEMultipart("form-data")
for name, value in params.iteritems():
mimeItem = MIMEText(value)
mimeItem.add_header("Content-Disposition", "form-data", name=name)
# TODO: Handle this better...?
for hdr in ['Content-Type','MIME-Version','Content-Transfer-Encoding']:
del mimeItem[hdr]
mimeMsg.attach(mimeItem)
if filenames or files:
filenames = filenames or []
files = files or []
for idx, item in enumerate(filenames + files):
# TODO: This is messy, tidy it...
if isinstance(item, str):
# We assume it's a file path...
filename = item
contentType = mimetypes.guess_type(filename)[0]
payload = open(filename, "rb").read()
else:
# We assume it's an `email.Message.Message` instance...
# TODO: Make more use of the pre-encoded information?
filename = item.get_filename()
contentType = item.get_content_type()
payload = item.get_payload(decode=True)
if not contentType:
contentType = "application/octet-stream"
mimeItem = MIMEBase(*contentType.split("/"))
mimeItem.add_header("Content-Disposition", "form-data",
name="file%s" % idx, filename=filename)
# TODO: Encode the payload?
mimeItem.set_payload(payload)
# TODO: Handle this better...?
for hdr in ['MIME-Version','Content-Transfer-Encoding']:
del mimeItem[hdr]
mimeMsg.attach(mimeItem)
del mimeMsg['MIME-Version']
return mimeMsg
class GmailLoginFailure(Exception):
"""
Raised whenever the login process fails--could be wrong username/password,
or Gmail service error, for example.
"""
class GmailAccount:
"""
"""
def __init__(self, name = "", pw = "", state = None):
"""
"""
# TODO: Change how all this is handled?
if name and pw:
self.name = name
self._pw = pw
self._cookieJar = CookieJar()
elif state:
# TODO: Check for stale state cookies?
self.name, self._cookieJar = state.state
else:
raise ValueError("GmailAccount must be instantiated with " \
"either GmailSessionState object or name " \
"and password.")
self._cachedQuotaInfo = None
self._cachedLabelNames = None
def login(self):
"""
"""
# TODO: Throw exception if we were instantiated with state?
data = urllib.urlencode({'continue': URL_GMAIL,
'service': 'mail',
'Email': self.name,
'Passwd': self._pw,
'null': 'Sign+in'})
headers = {'Host': 'www.google.com',
'User-Agent': 'User-Agent: Mozilla/5.0 (compatible;)'}
req = urllib2.Request(URL_LOGIN, data=data, headers=headers)
pageData = self._retrievePage(req)
# TODO: Tidy this up?
# This requests the page that provides the required "GV" cookie.
RE_PAGE_REDIRECT = 'top\.location\W=\W"CheckCookie\?continue=([^"]+)'
# TODO: Catch more failure exceptions here...?
try:
redirectURL = urllib.unquote(re.search(RE_PAGE_REDIRECT,
pageData).group(1))
except AttributeError:
raise GmailLoginFailure
# We aren't concerned with the actual content of this page,
# just the cookie that is returned with it.
pageData = self._retrievePage(redirectURL)
def _retrievePage(self, urlOrRequest):
"""
"""
if not isinstance(urlOrRequest, urllib2.Request):
req = urllib2.Request(urlOrRequest)
else:
req = urlOrRequest
self._cookieJar.setCookies(req)
resp = urllib2.urlopen(req)
pageData = resp.read()
# Extract cookies here
self._cookieJar.extractCookies(resp)
# TODO: Enable logging of page data for debugging purposes?
return pageData
def _parsePage(self, urlOrRequest):
"""
Retrieve & then parse the requested page content.
"""
items = _parsePage(self._retrievePage(urlOrRequest))
# Automatically cache some things like quota usage.
# TODO: Cache more?
# TODO: Expire cached values?
# TODO: Do this better.
try:
self._cachedQuotaInfo = items[D_QUOTA]
except KeyError:
pass
try:
self._cachedLabelNames = [category[CT_NAME]
for category in items[D_CATEGORIES]]
except KeyError:
pass
return items
def _parseSearchResult(self, searchType, start = 0, **kwargs):
"""
"""
params = {U_SEARCH: searchType,
U_START: start,
U_VIEW: U_THREADLIST_VIEW,
}
params.update(kwargs)
return self._parsePage(_buildURL(**params))
def _parseThreadSearch(self, searchType, allPages = False, **kwargs):
"""
Only works for thread-based results at present. # TODO: Change this?
"""
start = 0
threadsInfo = []
# Option to get *all* threads if multiple pages are used.
while (start == 0) or (allPages and
len(threadsInfo) < threadListSummary[TS_TOTAL]):
items = self._parseSearchResult(searchType, start, **kwargs)
#TODO: Handle single & zero result case better? Does this work?
try:
threads = items[D_THREAD]
except KeyError:
break
else:
if type(threads[0]) not in [tuple, list]:#TODO:Urgh,change!
threadsInfo.append(threads)
else:
# Note: This also handles when more than one "t"
# "DataPack" is on a page.
threadsInfo.extend(_splitBunches(threads))
# TODO: Check if the total or per-page values have changed?
threadListSummary = items[D_THREADLIST_SUMMARY]
threadsPerPage = threadListSummary[TS_NUM]
start += threadsPerPage
# TODO: Record whether or not we retrieved all pages..?
return GmailSearchResult(self, (searchType, kwargs), threadsInfo)
def _retrieveJavascript(self, version = ""):
"""
Note: `version` seems to be ignored.
"""
return self._retrievePage(_buildURL(view = U_PAGE_VIEW,
name = "js",
ver = version))
def getMessagesByFolder(self, folderName, allPages = False):
"""
Folders contain conversation/message threads.
`folderName` -- As set in Gmail interface.
Returns a `GmailSearchResult` instance.
*** TODO: Change all "getMessagesByX" to "getThreadsByX"? ***
"""
return self._parseThreadSearch(folderName, allPages = allPages)
def getMessagesByQuery(self, query, allPages = False):
"""
Returns a `GmailSearchResult` instance.
"""
return self._parseThreadSearch(U_QUERY_SEARCH, q = query,
allPages = allPages)
def getQuotaInfo(self, refresh = False):
"""
Return MB used, Total MB and percentage used.
"""
# TODO: Change this to a property.
if not self._cachedQuotaInfo or refresh:
# TODO: Handle this better...
self.getMessagesByFolder(U_INBOX_SEARCH)
return self._cachedQuotaInfo[:3]
def getLabelNames(self, refresh = False):
"""
"""
# TODO: Change this to a property?
if not self._cachedLabelNames or refresh:
# TODO: Handle this better...
self.getMessagesByFolder(U_INBOX_SEARCH)
return self._cachedLabelNames
def getMessagesByLabel(self, label, allPages = False):
"""
"""
return self._parseThreadSearch(U_CATEGORY_SEARCH,
cat=label, allPages = allPages)
def getRawMessage(self, msgId):
"""
"""
return self._retrievePage(
_buildURL(view=U_ORIGINAL_MESSAGE_VIEW, th=msgId))
def getUnreadMsgCount(self):
"""
"""
# TODO: Clean up queries a bit..?
items = self._parseSearchResult(U_QUERY_SEARCH,
q = "is:" + U_AS_SUBSET_UNREAD)
return items[D_THREADLIST_SUMMARY][TS_TOTAL_MSGS]
def _getActionToken(self):
"""
"""
try:
at = self._cookieJar._cookies[ACTION_TOKEN_COOKIE]
except KeyError:
self.getLabelNames(True)
at = self._cookieJar._cookies[ACTION_TOKEN_COOKIE]
return at
def sendMessage(self, msg, asDraft = False, _extraParams = None):
"""
`msg` -- `GmailComposedMessage` instance.
`_extraParams` -- Dictionary containing additional parameters
to put into POST message. (Not officially
for external use, more to make feature
additional a little easier to play with.)
Note: Now returns `GmailMessageStub` instance with populated
`id` (and `_account`) fields on success or None on failure.
"""
# TODO: Handle drafts separately?
params = {U_VIEW: [U_SENDMAIL_VIEW, U_SAVEDRAFT_VIEW][asDraft],
U_REFERENCED_MSG: "",
U_THREAD: "",
U_DRAFT_MSG: "",
U_COMPOSEID: "1",
U_ACTION_TOKEN: self._getActionToken(),
U_COMPOSE_TO: msg.to,
U_COMPOSE_CC: msg.cc,
U_COMPOSE_BCC: msg.bcc,
"subject": msg.subject,
"msgbody": msg.body,
}
if _extraParams:
params.update(_extraParams)
# Amongst other things, I used the following post to work out this:
# <http://groups.google.com/groups?
# selm=mailman.1047080233.20095.python-list%40python.org>
mimeMessage = _paramsToMime(params, msg.filenames, msg.files)
#### TODO: Ughh, tidy all this up & do it better...
## This horrible mess is here for two main reasons:
## 1. The `Content-Type` header (which also contains the boundary
## marker) needs to be extracted from the MIME message so
## we can send it as the request `Content-Type` header instead.
## 2. It seems the form submission needs to use "\r\n" for new
## lines instead of the "\n" returned by `as_string()`.
## I tried changing the value of `NL` used by the `Generator` class
## but it didn't work so I'm doing it this way until I figure
## out how to do it properly. Of course, first try, if the payloads
## contained "\n" sequences they got replaced too, which corrupted
## the attachments. I could probably encode the submission,
## which would probably be nicer, but in the meantime I'm kludging
## this workaround that replaces all non-text payloads with a
## marker, changes all "\n" to "\r\n" and finally replaces the
## markers with the original payloads.
## Yeah, I know, it's horrible, but hey it works doesn't it? If you've
## got a problem with it, fix it yourself & give me the patch!
##
origPayloads = {}
FMT_MARKER = "&&&&&&%s&&&&&&"
for i, m in enumerate(mimeMessage.get_payload()):
if not isinstance(m, MIMEText): #Do we care if we change text ones?
origPayloads[i] = m.get_payload()
m.set_payload(FMT_MARKER % i)
mimeMessage.epilogue = ""
msgStr = mimeMessage.as_string()
contentTypeHeader, data = msgStr.split("\n\n", 1)
contentTypeHeader = contentTypeHeader.split(":", 1)
data = data.replace("\n", "\r\n")
for k,v in origPayloads.iteritems():
data = data.replace(FMT_MARKER % k, v)
####
req = urllib2.Request(_buildURL(search = "undefined"), data = data)
req.add_header(*contentTypeHeader)
items = self._parsePage(req)
# TODO: Check composeid?
result = None
resultInfo = items[D_SENDMAIL_RESULT]
if resultInfo[SM_SUCCESS]:
result = GmailMessageStub(id = resultInfo[SM_NEWTHREADID],
_account = self)
return result
def trashMessage(self, msg):
"""
"""
# TODO: Decide if we should make this a method of `GmailMessage`.
# TODO: Should we check we have been given a `GmailMessage` instance?
params = {
U_ACTION: U_DELETEMESSAGE_ACTION,
U_ACTION_MESSAGE: msg.id,
U_ACTION_TOKEN: self._getActionToken(),
}
items = self._parsePage(_buildURL(**params))
# TODO: Mark as trashed on success?
return (items[D_ACTION_RESULT][AR_SUCCESS] == 1)
def _doThreadAction(self, actionId, thread):
"""
"""
# TODO: Decide if we should make this a method of `GmailThread`.
# TODO: Should we check we have been given a `GmailThread` instance?
params = {
U_SEARCH: U_ALL_SEARCH, #TODO:Check this search value always works.
U_VIEW: U_UPDATE_VIEW,
U_ACTION: actionId,
U_ACTION_THREAD: thread.id,
U_ACTION_TOKEN: self._getActionToken(),
}
items = self._parsePage(_buildURL(**params))
return (items[D_ACTION_RESULT][AR_SUCCESS] == 1)
def trashThread(self, thread):
"""
"""
# TODO: Decide if we should make this a method of `GmailThread`.
# TODO: Should we check we have been given a `GmailThread` instance?
result = self._doThreadAction(U_MARKTRASH_ACTION, thread)
# TODO: Mark as trashed on success?
return result
def _createUpdateRequest(self, actionId): #extraData):
"""
Helper method to create a Request instance for an update (view)
action.
Returns populated `Request` instance.
"""
params = {
U_VIEW: U_UPDATE_VIEW,
}
data = {
U_ACTION: actionId,
U_ACTION_TOKEN: self._getActionToken(),
}
#data.update(extraData)
req = urllib2.Request(_buildURL(**params),
data = urllib.urlencode(data))
return req
# TODO: Extract additional common code from handling of labels?
def createLabel(self, labelName):
"""
"""
req = self._createUpdateRequest(U_CREATECATEGORY_ACTION + labelName)
# Note: Label name cache is updated by this call as well. (Handy!)
items = self._parsePage(req)
return (items[D_ACTION_RESULT][AR_SUCCESS] == 1)
def deleteLabel(self, labelName):
"""
"""
# TODO: Check labelName exits?
req = self._createUpdateRequest(U_DELETECATEGORY_ACTION + labelName)
# Note: Label name cache is updated by this call as well. (Handy!)
items = self._parsePage(req)
return (items[D_ACTION_RESULT][AR_SUCCESS] == 1)
def renameLabel(self, oldLabelName, newLabelName):
"""
"""
# TODO: Check oldLabelName exits?
req = self._createUpdateRequest("%s%s^%s" % (U_RENAMECATEGORY_ACTION,
oldLabelName, newLabelName))
# Note: Label name cache is updated by this call as well. (Handy!)
items = self._parsePage(req)
return (items[D_ACTION_RESULT][AR_SUCCESS] == 1)
def storeFile(self, filename, label = None):
"""
"""
# TODO: Handle files larger than single attachment size.
# TODO: Allow file data objects to be supplied?
FILE_STORE_VERSION = "FSV_01"
FILE_STORE_SUBJECT_TEMPLATE = "%s %s" % (FILE_STORE_VERSION, "%s")
subject = FILE_STORE_SUBJECT_TEMPLATE % os.path.basename(filename)
msg = GmailComposedMessage(to="", subject=subject, body="",
filenames=[filename])
draftMsg = self.sendMessage(msg, asDraft = True)
if draftMsg and label:
draftMsg.addLabel(label)
return draftMsg
def _splitBunches(infoItems):
"""
Utility to help make it easy to iterate over each item separately,
even if they were bunched on the page.
"""
result= []
# TODO: Decide if this is the best approach.
for group in infoItems:
if type(group) == tuple:
result.extend(group)
else:
result.append(group)
return result
class GmailSearchResult:
"""
"""
def __init__(self, account, search, threadsInfo):
"""
`threadsInfo` -- As returned from Gmail but unbunched.
"""
self._account = account
self.search = search # TODO: Turn into object + format nicely.
self._threads = [GmailThread(self, thread)
for thread in threadsInfo]
def __iter__(self):
"""
"""
return iter(self._threads)
def __len__(self):
"""
"""
return len(self._threads)
from cPickle import load, dump
class GmailSessionState:
"""
"""
def __init__(self, account = None, filename = ""):
"""
"""
if account:
self.state = (account.name, account._cookieJar)
elif filename:
self.state = load(open(filename, "rb"))
else:
raise ValueError("GmailSessionState must be instantiated with " \
"either GmailAccount object or filename.")
def save(self, filename):
"""
"""
dump(self.state, open(filename, "wb"), -1)
class _LabelHandlerMixin(object):
"""
Note: Because a message id can be used as a thread id this works for
messages as well as threads.
"""
def addLabel(self, labelName):
"""
"""
# Note: It appears this also automatically creates new labels.
result = self._account._doThreadAction(U_ADDCATEGORY_ACTION+labelName,
self)
# TODO: Update list of attached labels?
return result
def removeLabel(self, labelName):
"""
"""
# TODO: Check label is already attached?
# Note: An error is not generated if the label is not already attached.
result = \
self._account._doThreadAction(U_REMOVECATEGORY_ACTION+labelName,
self)
# TODO: Update list of attached labels?
return result
class GmailThread(_LabelHandlerMixin):
"""
Note: As far as I can tell, the "canonical" thread id is always the same
as the id of the last message in the thread. But it appears that
the id of any message in the thread can be used to retrieve
the thread information.
"""
def __init__(self, parent, threadInfo):
"""
"""
# TODO Handle this better?
self._parent = parent
self._account = self._parent._account
self.id = threadInfo[T_THREADID] # TODO: Change when canonical updated?
self.subject = threadInfo[T_SUBJECT_HTML]
self.snippet = threadInfo[T_SNIPPET_HTML]
#self.extraSummary = threadInfo[T_EXTRA_SNIPPET] #TODO: What is this?
# TODO: Store other info?
# Extract number of messages in thread/conversation.
self._authors = threadInfo[T_AUTHORS_HTML]
self.info = threadInfo
try:
# TODO: Find out if this information can be found another way...
# (Without another page request.)
self._length = int(re.search("\((\d+?)\)\Z",
self._authors).group(1))
except AttributeError:
# If there's no message count then the thread only has one message.
self._length = 1
# TODO: Store information known about the last message (e.g. id)?
self._messages = []
def __len__(self):
"""
"""
return self._length
def __iter__(self):
"""
"""
if not self._messages:
self._messages = self._getMessages(self)
return iter(self._messages)
def __getattr__(self, name):
"""
Dynamically dispatch some interesting thread properties.
"""
attrs = { 'unread': T_UNREAD,
'star': T_STAR,
'date': T_DATE_HTML,
'authors': T_AUTHORS_HTML,
'flags': T_FLAGS,
'subject': T_SUBJECT_HTML,
'snippet': T_SNIPPET_HTML,
'categories': T_CATEGORIES,
'attach': T_ATTACH_HTML,
'matching_msgid': T_MATCHING_MSGID,
'extra_snippet': T_EXTRA_SNIPPET }
if name in attrs:
return self.info[ attrs[name] ];
raise AttributeError("no attribute %s" % name)
def _getMessages(self, thread):
"""
"""
# TODO: Do this better.
# TODO: Specify the query folder using our specific search?
items = self._account._parseSearchResult(U_QUERY_SEARCH,
view = U_CONVERSATION_VIEW,
th = thread.id,
q = "in:anywhere")
result = []
# TODO: Handle this better?
# Note: This handles both draft & non-draft messages in a thread...
for key, isDraft in [(D_MSGINFO, False), (D_DRAFTINFO, True)]:
try:
msgsInfo = items[key]
except KeyError:
# No messages of this type (e.g. draft or non-draft)
continue
else:
# TODO: Handle special case of only 1 message in thread better?
if type(msgsInfo) != type([]):
msgsInfo = [msgsInfo]
result += [GmailMessage(thread, msg, isDraft = isDraft)
for msg in msgsInfo]
return result
# TODO: Add property to retrieve list of labels for this message.
class GmailMessageStub(_LabelHandlerMixin):
"""
Intended to be used where not all message information is known/required.
NOTE: This may go away.
"""
# TODO: Provide way to convert this to a full `GmailMessage` instance
# or allow `GmailMessage` to be created without all info?
def __init__(self, id = None, _account = None):
"""
"""
self.id = id
self._account = _account
class GmailMessage(object):
"""
"""
def __init__(self, parent, msgData, isDraft = False):
"""
Note: `msgData` can be from either D_MSGINFO or D_DRAFTINFO.
"""
# TODO: Automatically detect if it's a draft or not?
# TODO Handle this better?
self._parent = parent
self._account = self._parent._account
self.id = msgData[MI_MSGID]
self.number = msgData[MI_NUM]
self.subject = msgData[MI_SUBJECT]
self.attachments = [GmailAttachment(self, attachmentInfo)
for attachmentInfo in msgData[MI_ATTACHINFO]]
# TODO: Populate additional fields & cache...(?)
# TODO: Handle body differently if it's from a draft?
self.isDraft = isDraft
self._source = None
def _getSource(self):
"""
"""
if not self._source:
# TODO: Do this more nicely...?
# TODO: Strip initial white space & fix up last line ending
# to make it legal as per RFC?
self._source = self._account.getRawMessage(self.id)
return self._source
source = property(_getSource, doc = "")
class GmailAttachment:
"""
"""
def __init__(self, parent, attachmentInfo):
"""
"""
# TODO Handle this better?
self._parent = parent
self._account = self._parent._account
self.id = attachmentInfo[A_ID]
self.filename = attachmentInfo[A_FILENAME]
self.mimetype = attachmentInfo[A_MIMETYPE]
self.filesize = attachmentInfo[A_FILESIZE]
self._content = None
def _getContent(self):
"""
"""
if not self._content:
# TODO: Do this a more nicely...?
self._content = self._account._retrievePage(
_buildURL(view=U_ATTACHMENT_VIEW, disp="attd",
attid=self.id, th=self._parent._parent.id))
return self._content
content = property(_getContent, doc = "")
def _getFullId(self):
"""
Returns the "full path"/"full id" of the attachment. (Used
to refer to the file when forwarding.)
The id is of the form: "<thread_id>_<msg_id>_<attachment_id>"
"""
return "%s_%s_%s" % (self._parent._parent.id,
self._parent.id,
self.id)
_fullId = property(_getFullId, doc = "")
class GmailComposedMessage:
"""
"""
def __init__(self, to, subject, body, cc = None, bcc = None,
filenames = None, files = None):
"""
`filenames` - list of the file paths of the files to attach.
`files` - list of objects implementing sub-set of
`email.Message.Message` interface (`get_filename`,
`get_content_type`, `get_payload`). This is to
allow use of payloads from Message instances.
TODO: Change this to be simpler class we define ourselves?
"""
self.to = to
self.subject = subject
self.body = body
self.cc = cc
self.bcc = bcc
self.filenames = filenames
self.files = files
if __name__ == "__main__":
import sys
from getpass import getpass
try:
name = sys.argv[1]
except IndexError:
name = raw_input("Gmail account name: ")
pw = getpass("Password: ")
ga = GmailAccount(name, pw)
print "\nPlease wait, logging in..."
try:
ga.login()
except GmailLoginFailure:
print "\nLogin failed. (Wrong username/password?)"
else:
print "Login successful.\n"
# TODO: Use properties instead?
quotaInfo = ga.getQuotaInfo()
quotaMbUsed = quotaInfo[QU_SPACEUSED]
quotaMbTotal = quotaInfo[QU_QUOTA]
quotaPercent = quotaInfo[QU_PERCENT]
print "%s of %s used. (%s)\n" % (quotaMbUsed, quotaMbTotal, quotaPercent)
searches = STANDARD_FOLDERS + ga.getLabelNames()
while 1:
try:
print "Select folder or label to list: (Ctrl-C to exit)"
for optionId, optionName in enumerate(searches):
print " %d. %s" % (optionId, optionName)
name = searches[int(raw_input("Choice: "))]
if name in STANDARD_FOLDERS:
result = ga.getMessagesByFolder(name, True)
else:
result = ga.getMessagesByLabel(name, True)
print
if len(result):
for thread in result:
print
print thread.id, len(thread), thread.subject
for msg in thread:
print " ", msg.id, msg.number, msg.subject
#print msg.source
else:
print "No threads found in `%s`." % name
print
except KeyboardInterrupt:
break
print "\n\nDone."
|