aboutsummaryrefslogtreecommitdiffstats
path: root/gallery_dl/extractor/behance.py
blob: f24059f6417b2a035ebdb36930858636d5813722 (plain) (blame)
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
# -*- coding: utf-8 -*-

# Copyright 2018-2023 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.

"""Extractors for https://www.behance.net/"""

from .common import Extractor, Message
from .. import text, util, exception


class BehanceExtractor(Extractor):
    """Base class for behance extractors"""
    category = "behance"
    root = "https://www.behance.net"
    request_interval = (2.0, 4.0)

    def _init(self):
        self._bcp = self.cookies.get("bcp", domain="www.behance.net")
        if not self._bcp:
            self._bcp = "4c34489d-914c-46cd-b44c-dfd0e661136d"
            self.cookies.set("bcp", self._bcp, domain="www.behance.net")

    def items(self):
        for gallery in self.galleries():
            gallery["_extractor"] = BehanceGalleryExtractor
            yield Message.Queue, gallery["url"], self._update(gallery)

    def galleries(self):
        """Return all relevant gallery URLs"""

    def _request_graphql(self, endpoint, variables):
        url = self.root + "/v3/graphql"
        headers = {
            "Origin": self.root,
            "X-BCP" : self._bcp,
            "X-Requested-With": "XMLHttpRequest",
        }
        data = {
            "query"    : GRAPHQL_QUERIES[endpoint],
            "variables": variables,
        }

        return self.request(url, method="POST", headers=headers,
                            json=data).json()["data"]

    def _update(self, data):
        # compress data to simple lists
        if data["fields"] and isinstance(data["fields"][0], dict):
            data["fields"] = [
                field.get("name") or field.get("label")
                for field in data["fields"]
            ]

        data["owners"] = [
            owner.get("display_name") or owner.get("displayName")
            for owner in data["owners"]
        ]

        tags = data.get("tags") or ()
        if tags and isinstance(tags[0], dict):
            tags = [tag["title"] for tag in tags]
        data["tags"] = tags

        data["date"] = text.parse_timestamp(
            data.get("publishedOn") or data.get("conceived_on") or 0)

        # backwards compatibility
        data["gallery_id"] = data["id"]
        data["title"] = data["name"]
        data["user"] = ", ".join(data["owners"])

        return data


class BehanceGalleryExtractor(BehanceExtractor):
    """Extractor for image galleries from www.behance.net"""
    subcategory = "gallery"
    directory_fmt = ("{category}", "{owners:J, }", "{id} {name}")
    filename_fmt = "{category}_{id}_{num:>02}.{extension}"
    archive_fmt = "{id}_{num}"
    pattern = r"(?:https?://)?(?:www\.)?behance\.net/gallery/(\d+)"
    example = "https://www.behance.net/gallery/12345/TITLE"

    def __init__(self, match):
        BehanceExtractor.__init__(self, match)
        self.gallery_id = match.group(1)

    def _init(self):
        BehanceExtractor._init(self)

        modules = self.config("modules")
        if modules:
            if isinstance(modules, str):
                modules = modules.split(",")
            self.modules = set(modules)
        else:
            self.modules = {"image", "video", "mediacollection", "embed"}

    def items(self):
        data = self.get_gallery_data()
        imgs = self.get_images(data)
        data["count"] = len(imgs)

        yield Message.Directory, data
        for data["num"], (url, module) in enumerate(imgs, 1):
            data["module"] = module
            data["extension"] = (module.get("extension") or
                                 text.ext_from_url(url))
            yield Message.Url, url, data

    def get_gallery_data(self):
        """Collect gallery info dict"""
        url = "{}/gallery/{}/a".format(self.root, self.gallery_id)
        cookies = {
            "gki": '{"feature_project_view":false,'
                   '"feature_discover_login_prompt":false,'
                   '"feature_project_login_prompt":false}',
            "ilo0": "true",
        }
        page = self.request(url, cookies=cookies).text

        data = util.json_loads(text.extr(
            page, 'id="beconfig-store_state">', '</script>'))
        return self._update(data["project"]["project"])

    def get_images(self, data):
        """Extract image results from an API response"""
        if not data["modules"]:
            access = data.get("matureAccess")
            if access == "logged-out":
                raise exception.AuthorizationError(
                    "Mature content galleries require logged-in cookies")
            if access == "restricted-safe":
                raise exception.AuthorizationError(
                    "Mature content blocked in account settings")
            if access and access != "allowed":
                raise exception.AuthorizationError()
            return ()

        result = []
        append = result.append

        for module in data["modules"]:
            mtype = module["__typename"][:-6].lower()

            if mtype not in self.modules:
                self.log.debug("Skipping '%s' module", mtype)
                continue

            if mtype == "image":
                sizes = {
                    size["url"].rsplit("/", 2)[1]: size
                    for size in module["imageSizes"]["allAvailable"]
                }
                size = (sizes.get("source") or
                        sizes.get("max_3840") or
                        sizes.get("fs") or
                        sizes.get("hd") or
                        sizes.get("disp"))
                append((size["url"], module))

            elif mtype == "video":
                try:
                    renditions = module["videoData"]["renditions"]
                except Exception:
                    self.log.warning("No download URLs for video %s",
                                     module.get("id") or "???")
                    continue

                try:
                    url = [
                        r["url"] for r in renditions
                        if text.ext_from_url(r["url"]) != "m3u8"
                    ][-1]
                except Exception as exc:
                    self.log.debug("%s: %s", exc.__class__.__name__, exc)
                    url = "ytdl:" + renditions[-1]["url"]

                append((url, module))

            elif mtype == "mediacollection":
                for component in module["components"]:
                    for size in component["imageSizes"].values():
                        if size:
                            parts = size["url"].split("/")
                            parts[4] = "source"
                            append(("/".join(parts), module))
                            break

            elif mtype == "embed":
                embed = module.get("originalEmbed") or module.get("fluidEmbed")
                if embed:
                    embed = text.unescape(text.extr(embed, 'src="', '"'))
                    module["extension"] = "mp4"
                    append(("ytdl:" + embed, module))

            elif mtype == "text":
                module["extension"] = "txt"
                append(("text:" + module["text"], module))

        return result


class BehanceUserExtractor(BehanceExtractor):
    """Extractor for a user's galleries from www.behance.net"""
    subcategory = "user"
    categorytransfer = True
    pattern = r"(?:https?://)?(?:www\.)?behance\.net/([^/?#]+)/?$"
    example = "https://www.behance.net/USER"

    def __init__(self, match):
        BehanceExtractor.__init__(self, match)
        self.user = match.group(1)

    def galleries(self):
        endpoint = "GetProfileProjects"
        variables = {
            "username": self.user,
            "after"   : "MAo=",  # "0" in base64
        }

        while True:
            data = self._request_graphql(endpoint, variables)
            items = data["user"]["profileProjects"]
            yield from items["nodes"]

            if not items["pageInfo"]["hasNextPage"]:
                return
            variables["after"] = items["pageInfo"]["endCursor"]


class BehanceCollectionExtractor(BehanceExtractor):
    """Extractor for a collection's galleries from www.behance.net"""
    subcategory = "collection"
    categorytransfer = True
    pattern = r"(?:https?://)?(?:www\.)?behance\.net/collection/(\d+)"
    example = "https://www.behance.net/collection/12345/TITLE"

    def __init__(self, match):
        BehanceExtractor.__init__(self, match)
        self.collection_id = match.group(1)

    def galleries(self):
        endpoint = "GetMoodboardItemsAndRecommendations"
        variables = {
            "afterItem": "MAo=",  # "0" in base64
            "firstItem": 40,
            "id"       : int(self.collection_id),
            "shouldGetItems"          : True,
            "shouldGetMoodboardFields": False,
            "shouldGetRecommendations": False,
        }

        while True:
            data = self._request_graphql(endpoint, variables)
            items = data["moodboard"]["items"]

            for node in items["nodes"]:
                yield node["entity"]

            if not items["pageInfo"]["hasNextPage"]:
                return
            variables["afterItem"] = items["pageInfo"]["endCursor"]


GRAPHQL_QUERIES = {
    "GetProfileProjects": """\
query GetProfileProjects($username: String, $after: String) {
  user(username: $username) {
    profileProjects(first: 12, after: $after) {
      pageInfo {
        endCursor
        hasNextPage
      }
      nodes {
        __typename
        adminFlags {
          mature_lock
          privacy_lock
          dmca_lock
          flagged_lock
          privacy_violation_lock
          trademark_lock
          spam_lock
          eu_ip_lock
        }
        colors {
          r
          g
          b
        }
        covers {
          size_202 {
            url
          }
          size_404 {
            url
          }
          size_808 {
            url
          }
        }
        features {
          url
          name
          featuredOn
          ribbon {
            image
            image2x
            image3x
          }
        }
        fields {
          id
          label
          slug
          url
        }
        hasMatureContent
        id
        isFeatured
        isHiddenFromWorkTab
        isMatureReviewSubmitted
        isOwner
        isFounder
        isPinnedToSubscriptionOverview
        isPrivate
        linkedAssets {
          ...sourceLinkFields
        }
        linkedAssetsCount
        sourceFiles {
          ...sourceFileFields
        }
        matureAccess
        modifiedOn
        name
        owners {
          ...OwnerFields
          images {
            size_50 {
              url
            }
          }
        }
        premium
        publishedOn
        stats {
          appreciations {
            all
          }
          views {
            all
          }
          comments {
            all
          }
        }
        slug
        tools {
          id
          title
          category
          categoryLabel
          categoryId
          approved
          url
          backgroundColor
        }
        url
      }
    }
  }
}

fragment sourceFileFields on SourceFile {
  __typename
  sourceFileId
  projectId
  userId
  title
  assetId
  renditionUrl
  mimeType
  size
  category
  licenseType
  unitAmount
  currency
  tier
  hidden
  extension
  hasUserPurchased
}

fragment sourceLinkFields on LinkedAsset {
  __typename
  name
  premium
  url
  category
  licenseType
}

fragment OwnerFields on User {
  displayName
  hasPremiumAccess
  id
  isFollowing
  isProfileOwner
  location
  locationUrl
  url
  username
  availabilityInfo {
    availabilityTimeline
    isAvailableFullTime
    isAvailableFreelance
  }
}
""",

    "GetMoodboardItemsAndRecommendations": """\
query GetMoodboardItemsAndRecommendations(
  $id: Int!
  $firstItem: Int!
  $afterItem: String
  $shouldGetRecommendations: Boolean!
  $shouldGetItems: Boolean!
  $shouldGetMoodboardFields: Boolean!
) {
  viewer @include(if: $shouldGetMoodboardFields) {
    isOptedOutOfRecommendations
    isAdmin
  }
  moodboard(id: $id) {
    ...moodboardFields @include(if: $shouldGetMoodboardFields)

    items(first: $firstItem, after: $afterItem) @include(if: $shouldGetItems) {
      pageInfo {
        endCursor
        hasNextPage
      }
      nodes {
        ...nodesFields
      }
    }

    recommendedItems(first: 80) @include(if: $shouldGetRecommendations) {
      nodes {
        ...nodesFields
        fetchSource
      }
    }
  }
}

fragment moodboardFields on Moodboard {
  id
  label
  privacy
  followerCount
  isFollowing
  projectCount
  url
  isOwner
  owners {
    ...OwnerFields
    images {
      size_50 {
        url
      }
      size_100 {
        url
      }
      size_115 {
        url
      }
      size_230 {
        url
      }
      size_138 {
        url
      }
      size_276 {
        url
      }
    }
  }
}

fragment projectFields on Project {
  __typename
  id
  isOwner
  publishedOn
  matureAccess
  hasMatureContent
  modifiedOn
  name
  url
  isPrivate
  slug
  license {
    license
    description
    id
    label
    url
    text
    images
  }
  fields {
    label
  }
  colors {
    r
    g
    b
  }
  owners {
    ...OwnerFields
    images {
      size_50 {
        url
      }
      size_100 {
        url
      }
      size_115 {
        url
      }
      size_230 {
        url
      }
      size_138 {
        url
      }
      size_276 {
        url
      }
    }
  }
  covers {
    size_original {
      url
    }
    size_max_808 {
      url
    }
    size_808 {
      url
    }
    size_404 {
      url
    }
    size_202 {
      url
    }
    size_230 {
      url
    }
    size_115 {
      url
    }
  }
  stats {
    views {
      all
    }
    appreciations {
      all
    }
    comments {
      all
    }
  }
}

fragment exifDataValueFields on exifDataValue {
  id
  label
  value
  searchValue
}

fragment nodesFields on MoodboardItem {
  id
  entityType
  width
  height
  flexWidth
  flexHeight
  images {
    size
    url
  }

  entity {
    ... on Project {
      ...projectFields
    }

    ... on ImageModule {
      project {
        ...projectFields
      }

      colors {
        r
        g
        b
      }

      exifData {
        lens {
          ...exifDataValueFields
        }
        software {
          ...exifDataValueFields
        }
        makeAndModel {
          ...exifDataValueFields
        }
        focalLength {
          ...exifDataValueFields
        }
        iso {
          ...exifDataValueFields
        }
        location {
          ...exifDataValueFields
        }
        flash {
          ...exifDataValueFields
        }
        exposureMode {
          ...exifDataValueFields
        }
        shutterSpeed {
          ...exifDataValueFields
        }
        aperture {
          ...exifDataValueFields
        }
      }
    }

    ... on MediaCollectionComponent {
      project {
        ...projectFields
      }
    }
  }
}

fragment OwnerFields on User {
  displayName
  hasPremiumAccess
  id
  isFollowing
  isProfileOwner
  location
  locationUrl
  url
  username
  availabilityInfo {
    availabilityTimeline
    isAvailableFullTime
    isAvailableFreelance
  }
}
""",

}