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
#!/usr/bin/python
#
# Download each Flickr photo's information
# to <PHOTOID>.XML in the current working directory.
# Files already created will be skipped on subsequent runs.
#
#
# The files you get will contain data like:
#
# <?xml version="1.0" encoding="utf-8" ?>
# <rsp stat="ok">
# <photo id="xxxxxxxxxx" secret="xxxxxxxxxx" server="xxxx" farm="x" dateuploaded="1186256580" isfavorite="0" license="1" rotation="0" originalsecret="989af4e697" originalformat="jpg" views="2">
#         <owner nsid="xxxxxxxx@N00" username="your username" realname="your realname" location="somewhere" />
#         <title>Photo Title</title>
#         <description>Photo Description</description>
#         <visibility ispublic="0" isfriend="1" isfamily="1" />
#         <dates posted="1186256580" taken="2007-08-04 15:41:26" takengranularity="0" lastupdate="1186256660" />
#         <permissions permcomment="3" permaddmeta="1" />
#         <editability cancomment="1" canaddmeta="1" />
#         <comments>0</comments>
#         <notes />
#         <tags>
#                 <tag id="xxxxxxx-xxxxxxxxx-xxxx" author="xxxxxxxx2@N00" raw="yourtag" machine_tag="0">yourtag</tag>
#                 <tag id="xxxxxxx-xxxxxxxxx-xxxx" author="xxxxxxxx2@N00" raw="yourothertag" machine_tag="0">yourothertag</tag>
#         </tags>
#         <urls>
#                 <url type="photopage">http://www.flickr.com/photos/yourusername/xxxxxxxxxx/</url>
#         </urls>
# </photo>
# </rsp>
#
# Main loop copyright Dave Findlay 2007. Do with it what you wish.
# See "Flickr API Implementation" section below for its copyright and licensing info.
#

def main(argv):
    # flickr auth information:
    flickrUsername = "YOUR_USERNAME"
    
    # you need to apply for a Flickr API key at:
    # http://www.flickr.com/services/api/keys/apply/
    # Once approved you'll get your API key and shared secret and
    # can insert them below.
    flickrAPIKey = "YOUR_API_KEY"
    flickrSecret = "YOUR_SECRET"
    
    # we need a browser the first time so that the user can
    # authorize our access to their photos on Flickr
    browserToUse = "/Applications/Firefox.app/Contents/MacOS/firefox"

    print "Connecting to Flickr..."
    fapi = FlickrAPI(flickrAPIKey, flickrSecret)
    # get token, including asking user's permission if necessary
    token = fapi.getToken(browser=browserToUse, perms="read")
    rsp = fapi.people_findByUsername(api_key=flickrAPIKey, username=flickrUsername)
    fapi.testFailure(rsp)
    userid = rsp.user[0]["id"]
    print "Connected."
    
    #
    # Now walk the photo ids in chronological date-taken order,
    # retrieving the photos in smallish chunks so as not to
    # annoy the server too much
    #
    cpage = 1

    while 1:
         rsp = fapi.photos_search(api_key=flickrAPIKey,
                                  auth_token=token,
                                  user_id=userid,
                                  per_page="100",
                                  page=str(cpage),
                                  sort="date-taken-asc")
         fapi.testFailure(rsp)

         npages = int(rsp.photos[0]["pages"])
         for i in range(len(rsp.photos[0].photo)):
             photo_id = rsp.photos[0].photo[i]["id"] + ".xml"

             if os.path.isfile(photo_id):
                 print "Already got info for",photo_id, "                    \r",
             else:
                 print "Getting data for", photo_id,"                    "
                 photorsp = fapi.photos_getInfo(api_key=flickrAPIKey, auth_token=token, photo_id=str(photo_id))
                 fapi.testFailure(photorsp)

                 # write the photo's XML data to a file
                 file = open(photo_id, "w")
                 file.write(photorsp.xml)
                 file.close

         cpage += 1
         if cpage > npages:
             break

    print "Done."
    return 0


#
# Flickr API implementation
#
# Inspired largely by Michele Campeotto's flickrclient and Aaron Swartz'
# xmltramp... but I wanted to get a better idea of how python worked in
# those regards, so I mostly worked those components out for myself.
#
# http://micampe.it/things/flickrclient
# http://www.aaronsw.com/2002/xmltramp/
#
# Release 1: initial release
# Release 2: added upload functionality
# Release 3: code cleanup, convert to doc strings
# Release 4: better permission support
# Release 5: converted into fuller-featured "flickrapi"
# Release 6: fix upload sig bug (thanks Deepak Jois), encode test output
# Release 7: fix path construction, Manish Rai Jain's improvements, exceptions
#
# Work by (or inspired by) Manish Rai Jain <[email protected]>:
#
#    improved error reporting, proper multipart MIME boundary creation,
#    use of urllib2 to allow uploads through a proxy, upload accepts
#    raw data as well as a filename
#
# Copyright 2005 Brian "Beej Jorgensen" Hall <[email protected]>
#
#    This work is licensed under the Creative Commons
#    Attribution License.  To view a copy of this license,
#    visit http://creativecommons.org/licenses/by/2.5/ or send
#    a letter to Creative Commons, 543 Howard Street, 5th
#    Floor, San Francisco, California, 94105, USA.
#
# This license says that I must be credited for any derivative works.
# You do not need to credit me to simply use the FlickrAPI classes in
# your Python scripts--you only need to credit me if you're taking this
# FlickrAPI class and modifying it or redistributing it.
#
# Previous versions of this API were granted to the public domain.
# You're free to use those as you please.
#
# Beej Jorgensen, Maintainer, November 2005
# [email protected]
#

import sys
import md5
import string
import urllib
import urllib2
import mimetools
import httplib
import os.path
import xml.dom.minidom
import re

########################################################################
# Exceptions
########################################################################

class UploadException(Exception):
    pass

########################################################################
# XML functionality
########################################################################

#-----------------------------------------------------------------------
class XMLNode:
    """XMLNode -- generic class for holding an XML node

    xmlStr = \"\"\"<xml foo="32">
    <name bar="10">Name0</name>
    <name bar="11" baz="12">Name1</name>
    </xml>\"\"\"

    f = XMLNode.parseXML(xmlStr)

    print f.elementName              # xml
    print f['foo']                   # 32
    print f.name                     # [<name XMLNode>, <name XMLNode>]
    print f.name[0].elementName      # name
    print f.name[0]["bar"]           # 10
    print f.name[0].elementText      # Name0
    print f.name[1].elementName      # name
    print f.name[1]["bar"]           # 11
    print f.name[1]["baz"]           # 12

    """

    def __init__(self):
        """Construct an empty XML node."""
        self.elementName=""
        self.elementText=""
        self.attrib={}
        self.xml=""

    def __setitem__(self, key, item):
        """Store a node's attribute in the attrib hash."""
        self.attrib[key] = item

    def __getitem__(self, key):
        """Retrieve a node's attribute from the attrib hash."""
        return self.attrib[key]

    #-----------------------------------------------------------------------
    @classmethod
    def parseXML(cls, xmlStr, storeXML=True):
        """Convert an XML string into a nice instance tree of XMLNodes.

        xmlStr -- the XML to parse
        storeXML -- if True, stores the XML string in the root XMLNode.xml

        """

        def __parseXMLElement(element, thisNode):
            """Recursive call to process this XMLNode."""
            thisNode.elementName = element.nodeName

            #print element.nodeName

            # add element attributes as attributes to this node
            for i in range(element.attributes.length):
                an = element.attributes.item(i)
                thisNode[an.name] = an.nodeValue

            for a in element.childNodes:
                if a.nodeType == xml.dom.Node.ELEMENT_NODE:

                    child = XMLNode()
                    try:
                        list = getattr(thisNode, a.nodeName)
                    except AttributeError:
                        setattr(thisNode, a.nodeName, [])

                    # add the child node as an attrib to this node
                    list = getattr(thisNode, a.nodeName);
                    #print "appending child: %s to %s" % (a.nodeName, thisNode.elementName)
                    list.append(child);

                    __parseXMLElement(a, child)

                elif a.nodeType == xml.dom.Node.TEXT_NODE:
                    thisNode.elementText += a.nodeValue
            
            return thisNode
        dom = xml.dom.minidom.parseString(xmlStr)

        # get the root
        rootNode = XMLNode()
        if storeXML: rootNode.xml = xmlStr

        return __parseXMLElement(dom.firstChild, rootNode)

########################################################################
# Flickr functionality
########################################################################

#-----------------------------------------------------------------------
class FlickrAPI:
    """Encapsulated flickr functionality.

    Example usage:

      flickr = FlickrAPI(flickrAPIKey, flickrSecret)
      rsp = flickr.auth_checkToken(api_key=flickrAPIKey, auth_token=token)

    """
    flickrHost = "flickr.com"
    flickrRESTForm = "/services/rest/"
    flickrAuthForm = "/services/auth/"
    flickrUploadForm = "/services/upload/"

    #-------------------------------------------------------------------
    def __init__(self, apiKey, secret):
        """Construct a new FlickrAPI instance for a given API key and secret."""
        self.apiKey = apiKey
        self.secret = secret

        self.__handlerCache={}

    #-------------------------------------------------------------------
    def __sign(self, data):
        """Calculate the flickr signature for a set of params.

        data -- a hash of all the params and values to be hashed, e.g.
                {"api_key":"AAAA", "auth_token":"TTTT"}

        """
        dataName = self.secret
        keys = data.keys()
        keys.sort()
        for a in keys: dataName += (a + data[a])
        #print dataName
        hash = md5.new()
        hash.update(dataName)
        return hash.hexdigest()

    #-------------------------------------------------------------------
    def __getattr__(self, method, **arg):
        """Handle all the flickr API calls.
        
        This is Michele Campeotto's cleverness, wherein he writes a
        general handler for methods not defined, and assumes they are
        flickr methods.  He then converts them to a form to be passed as
        the method= parameter, and goes from there.

        http://micampe.it/things/flickrclient

        My variant is the same basic thing, except it tracks if it has
        already created a handler for a specific call or not.

        example usage:

            flickr.auth_getFrob(api_key="AAAAAA")
            rsp = flickr.favorites_getList(api_key=flickrAPIKey, \\
                auth_token=token)

        """

        if not self.__handlerCache.has_key(method):
            def handler(_self = self, _method = method, **arg):
                _method = "flickr." + _method.replace("_", ".")
                url = "http://" + FlickrAPI.flickrHost + \
                    FlickrAPI.flickrRESTForm
                arg["method"] = _method
                postData = urllib.urlencode(arg) + "&api_sig=" + \
                    _self.__sign(arg)
                #print "--url---------------------------------------------"
                #print url
                #print "--postData----------------------------------------"
                #print postData
                f = urllib.urlopen(url, postData)
                data = f.read()
                #print "--response----------------------------------------"
                #print data
                f.close()
                return XMLNode.parseXML(data, True)

            self.__handlerCache[method] = handler;

        return self.__handlerCache[method]
    
    #-------------------------------------------------------------------
    def __getAuthURL(self, perms, frob):
        """Return the authorization URL to get a token.

        This is the URL the app will launch a browser toward if it
        needs a new token.
            
        perms -- "read", "write", or "delete"
        frob -- picked up from an earlier call to FlickrAPI.auth_getFrob()

        """

        data = {"api_key": self.apiKey, "frob": frob, "perms": perms}
        data["api_sig"] = self.__sign(data)
        url = "http://%s%s?%s" % (FlickrAPI.flickrHost, \
            FlickrAPI.flickrAuthForm, urllib.urlencode(data))
                return url

    #-------------------------------------------------------------------
    def upload(self, filename=None, jpegData=None, **arg):
        """Upload a file to flickr.

        Be extra careful you spell the parameters correctly, or you will
        get a rather cryptic "Invalid Signature" error on the upload!

        Supported parameters:

        One of filename or jpegData must be specified by name when 
        calling this method:

        filename -- name of a file to upload
        jpegData -- array of jpeg data to upload

        api_key
        auth_token
        title
        description
        tags -- space-delimited list of tags, "tag1 tag2 tag3"
        is_public -- "1" or "0"
        is_friend -- "1" or "0"
        is_family -- "1" or "0"

        """

        if filename == None and jpegData == None or \
            filename != None and jpegData != None:

            raise UploadException("filename OR jpegData must be specified")

        # verify key names
        for a in arg.keys():
            if a != "api_key" and a != "auth_token" and a != "title" and \
                a != "description" and a != "tags" and a != "is_public" and \
                a != "is_friend" and a != "is_family":

                sys.stderr.write("FlickrAPI: warning: unknown parameter " \
                    "\"%s\" sent to FlickrAPI.upload\n" % (a))
        
        arg["api_sig"] = self.__sign(arg)
        url = "http://" + FlickrAPI.flickrHost + FlickrAPI.flickrUploadForm

        # construct POST data
        boundary = mimetools.choose_boundary()
        body = ""

        # required params
        for a in ('api_key', 'auth_token', 'api_sig'):
            body += "--%s\r\n" % (boundary)
            body += "Content-Disposition: form-data; name=\""+a+"\"\r\n\r\n"
            body += "%s\r\n" % (arg[a])

        # optional params
        for a in ('title', 'description', 'tags', 'is_public', \
            'is_friend', 'is_family'):

            if arg.has_key(a):
                body += "--%s\r\n" % (boundary)
                body += "Content-Disposition: form-data; name=\""+a+"\"\r\n\r\n"
                body += "%s\r\n" % (arg[a])

        body += "--%s\r\n" % (boundary)
        body += "Content-Disposition: form-data; name=\"photo\";"
        body += " filename=\"%s\"\r\n" % filename
        body += "Content-Type: image/jpeg\r\n\r\n"

        #print body

        if filename != None:
            fp = file(filename, "rb")
            data = fp.read()
            fp.close()
        else:
            data = jpegData

        postData = body.encode("utf_8") + data + \
            ("--%s--" % (boundary)).encode("utf_8")

        request = urllib2.Request(url)
        request.add_data(postData)
        request.add_header("Content-Type", \
            "multipart/form-data; boundary=%s" % boundary)
        response = urllib2.urlopen(request)
        rspXML = response.read()

        return XMLNode.parseXML(rspXML)


    #-----------------------------------------------------------------------
    @classmethod
    def testFailure(cls, rsp, exit=True):
        """Exit app if the rsp XMLNode indicates failure."""
                if not rsp:
                        sys.sysstderr.write("\n\nnull response\n")
                        if exit: sys.exit(1)

        if rsp['stat'] == "fail":
            sys.stderr.write("\n\n%s\n" % (cls.getPrintableError(rsp)))
            if exit: sys.exit(1)

    #-----------------------------------------------------------------------
    @classmethod
    def getPrintableError(cls, rsp):
        """Return a printed error message string."""
        return "%s: error %s: %s" % (rsp.elementName, \
            cls.getRspErrorCode(rsp), cls.getRspErrorMsg(rsp))

    #-----------------------------------------------------------------------
    @classmethod
    def getRspErrorCode(cls, rsp):
        """Return the error code of a response, or 0 if no error."""
        if rsp['stat'] == "fail":
            return rsp.err[0]['code']

        return 0

    #-----------------------------------------------------------------------
    @classmethod
    def getRspErrorMsg(cls, rsp):
        """Return the error message of a response, or "Success" if no error."""
        if rsp['stat'] == "fail":
            return rsp.err[0]['msg']

        return "Success"

    #-----------------------------------------------------------------------
    def __getCachedTokenPath(self):
        """Return the directory holding the app data."""
        return os.path.expanduser(os.path.sep.join(["~", ".flickr", \
            self.apiKey]))

    #-----------------------------------------------------------------------
    def __getCachedTokenFilename(self):
        """Return the full pathname of the cached token file."""
        return os.path.sep.join([self.__getCachedTokenPath(), "auth.xml"])

    #-----------------------------------------------------------------------
    def __getCachedToken(self):
        """Read and return a cached token, or None if not found.

        The token is read from the cached token file, which is basically the
        entire RSP response containing the auth element.
        """

        try:
            f = file(self.__getCachedTokenFilename(), "r")
            
            data = f.read()
            f.close()

            rsp = XMLNode.parseXML(data)

            return rsp.auth[0].token[0].elementText

        except IOError:
            return None

    #-----------------------------------------------------------------------
    def __setCachedToken(self, xml):
        """Cache a token for later use.

        The cached tag is stored by simply saving the entire RSP response
        containing the auth element.

        """

        path = self.__getCachedTokenPath()
        if not os.path.exists(path):
            os.makedirs(path)

        f = file(self.__getCachedTokenFilename(), "w")
        f.write(xml)
        f.close()


    #-----------------------------------------------------------------------
    def getToken(self, perms="read", browser="lynx"):
        """Get a token either from the cache, or make a new one from the
        frob.

        This first attempts to find a token in the user's token cache on
        disk.
        
        If that fails (or if the token is no longer valid based on
        flickr.auth.checkToken) a new frob is acquired.  The frob is
        validated by having the user log into flickr (with lynx), and
        subsequently a valid token is retrieved.

        The newly minted token is then cached locally for the next run.

        perms--"read", "write", or "delete"
        browser--whatever browser should be used in the system() call

        """
        
        # see if we have a saved token
        token = self.__getCachedToken()

        # see if it's valid
        if token != None:
            rsp = self.auth_checkToken(api_key=self.apiKey, auth_token=token)
            if rsp['stat'] != "ok":
                token = None
            else:
                # see if we have enough permissions
                tokenPerms = rsp.auth[0].perms[0].elementText
                if tokenPerms == "read" and perms != "read": token = None
                elif tokenPerms == "write" and perms == "delete": token = None

        # get a new token if we need one
        if token == None:
            # get the frob
            rsp = self.auth_getFrob(api_key=self.apiKey)
            self.testFailure(rsp)

            frob = rsp.frob[0].elementText

            # validate online
                        url = self.__getAuthURL(perms, frob)
                        cmd = "%s \"%s\"" % (browser, url)
            os.system(cmd)

            # get a token
            rsp = self.auth_getToken(api_key=self.apiKey, frob=frob)
            self.testFailure(rsp)

            token = rsp.auth[0].token[0].elementText

            # store the auth info for next time
            self.__setCachedToken(rsp.xml)

        return token

# run the main if we're not being imported:
if __name__ == "__main__": sys.exit(main(sys.argv))