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

#
#SMS test via Google Voice
#
#John Nagle
#   nagle@animats.com
#
import googlevoice
import sys
import BeautifulSoup


def extractsms(htmlsms) :
    """
    extractsms  --  extract SMS messages from BeautifulSoup tree of Google Voice SMS HTML.

    Output is a list of dictionaries, one per message.
    """
    msgitems = []										# accum message items here
    #	Extract all conversations by searching for a DIV with an ID at top level.
    tree = BeautifulSoup.BeautifulSoup(htmlsms)			# parse HTML into tree
    conversations = tree.findAll("div",attrs={"id" : True},recursive=False)
    for conversation in conversations :
        #	For each conversation, extract each row, which is one SMS message.
        rows = conversation.findAll(attrs={"class" : "gc-message-sms-row"})
        for row in rows :								# for all rows
            #	For each row, which is one message, extract all the fields.
            msgitem = {"id" : conversation["id"]}		# tag this message with conversation ID
            spans = row.findAll("span",attrs={"class" : True}, recursive=False)
            for span in spans :							# for all spans in row
                cl = span["class"].replace('gc-message-sms-', '')
                msgitem[cl] = (" ".join(span.findAll(text=True))).strip()	# put text in dict
            msgitems.append(msgitem)					# add msg dictionary to list
    return msgitems
    
voice = googlevoice.Voice()
voice.login()

for msg in extractsms(voice.sms_html()):
    print str(msg)