From bfd68e6a3fc1527589bcb33159daf14a9440c21b Mon Sep 17 00:00:00 2001
From: Your Name <you@example.com>
Date: Fri, 9 Dec 2022 02:35:21 +0000
Subject: [PATCH] new data model: googlebooks

---
 catalog/book/tests.py                         | 32 ++++++++
 catalog/common/models.py                      |  2 +-
 catalog/common/sites.py                       |  2 +-
 catalog/sites/__init__.py                     |  1 +
 catalog/sites/google_books.py                 | 79 +++++++++++++++++++
 ...ogleapis_com_books_v1_volumes_hV__zQEACAAJ | 75 ++++++++++++++++++
 6 files changed, 189 insertions(+), 2 deletions(-)
 create mode 100644 catalog/sites/google_books.py
 create mode 100644 test_data/https___www_googleapis_com_books_v1_volumes_hV__zQEACAAJ

diff --git a/catalog/book/tests.py b/catalog/book/tests.py
index 279956e6..51e55353 100644
--- a/catalog/book/tests.py
+++ b/catalog/book/tests.py
@@ -116,6 +116,35 @@ class GoodreadsTestCase(TestCase):
         self.assertEqual(w1, w2)
 
 
+class GoogleBooksTestCase(TestCase):
+    def test_parse(self):
+        t_type = IdType.GoogleBooks
+        t_id = 'hV--zQEACAAJ'
+        t_url = 'https://books.google.com.bn/books?id=hV--zQEACAAJ&hl=ms'
+        t_url2 = 'https://books.google.com/books?id=hV--zQEACAAJ'
+        p1 = SiteList.get_site_by_url(t_url)
+        p2 = SiteList.get_site_by_url(t_url2)
+        self.assertIsNotNone(p1)
+        self.assertEqual(p1.url, t_url2)
+        self.assertEqual(p1.ID_TYPE, t_type)
+        self.assertEqual(p1.id_value, t_id)
+        self.assertEqual(p2.url, t_url2)
+
+    @use_local_response
+    def test_scrape(self):
+        t_url = 'https://books.google.com.bn/books?id=hV--zQEACAAJ'
+        site = SiteList.get_site_by_url(t_url)
+        self.assertEqual(site.ready, False)
+        site.get_resource_ready()
+        self.assertEqual(site.ready, True)
+        self.assertEqual(site.resource.metadata.get('title'), '1984 Nineteen Eighty-Four')
+        self.assertEqual(site.resource.metadata.get('isbn'), '9781847498571')
+        self.assertEqual(site.resource.id_type, IdType.GoogleBooks)
+        self.assertEqual(site.resource.id_value, 'hV--zQEACAAJ')
+        self.assertEqual(site.resource.item.isbn, '9781847498571')
+        self.assertEqual(site.resource.item.title, '1984 Nineteen Eighty-Four')
+
+
 class DoubanBookTestCase(TestCase):
     def setUp(self):
         pass
@@ -170,9 +199,12 @@ class MultiBookSitesTestCase(TestCase):
         # isbn = '9781847498571'
         url1 = 'https://www.goodreads.com/book/show/56821625-1984'
         url2 = 'https://book.douban.com/subject/35902899/'
+        url3 = 'https://books.google.com/books?id=hV--zQEACAAJ'
         p1 = SiteList.get_site_by_url(url1).get_resource_ready()
         p2 = SiteList.get_site_by_url(url2).get_resource_ready()
+        p3 = SiteList.get_site_by_url(url3).get_resource_ready()
         self.assertEqual(p1.item.id, p2.item.id)
+        self.assertEqual(p2.item.id, p3.item.id)
 
     @use_local_response
     def test_works(self):
diff --git a/catalog/common/models.py b/catalog/common/models.py
index 691d317a..7537ee41 100644
--- a/catalog/common/models.py
+++ b/catalog/common/models.py
@@ -27,7 +27,7 @@ class IdType(models.TextChoices):
     TMDB_Movie = 'tmdb_movie', _('TMDB电影')
     Goodreads = 'goodreads', _('Goodreads')
     Goodreads_Work = 'goodreads_work', _('Goodreads著作')
-    GoogleBook = 'googlebook', _('谷歌图书')
+    GoogleBooks = 'googlebooks', _('谷歌图书')
     DoubanBook = 'doubanbook', _('豆瓣读书')
     DoubanBook_Work = 'doubanbook_work', _('豆瓣读书著作')
     DoubanMovie = 'doubanmovie', _('豆瓣电影')
diff --git a/catalog/common/sites.py b/catalog/common/sites.py
index 8c959158..d23db01e 100644
--- a/catalog/common/sites.py
+++ b/catalog/common/sites.py
@@ -20,7 +20,7 @@ _logger = logging.getLogger(__name__)
 class ResourceContent:
     lookup_ids: dict = field(default_factory=dict)
     metadata: dict = field(default_factory=dict)
-    cover_image = None
+    cover_image: bytes = None
     cover_image_extention: str = None
 
 
diff --git a/catalog/sites/__init__.py b/catalog/sites/__init__.py
index 01717bde..6f6dc2f7 100644
--- a/catalog/sites/__init__.py
+++ b/catalog/sites/__init__.py
@@ -6,6 +6,7 @@ from .douban_music import DoubanMusic
 from .douban_game import DoubanGame
 from .douban_drama import DoubanDrama
 from .goodreads import Goodreads
+from .google_books import GoogleBooks
 from .tmdb import TMDB_Movie
 from .imdb import IMDB
 from .spotify import Spotify
diff --git a/catalog/sites/google_books.py b/catalog/sites/google_books.py
new file mode 100644
index 00000000..0554d3d8
--- /dev/null
+++ b/catalog/sites/google_books.py
@@ -0,0 +1,79 @@
+from catalog.common import *
+from catalog.models import *
+import re
+import logging
+
+
+_logger = logging.getLogger(__name__)
+
+
+@SiteList.register
+class GoogleBooks(AbstractSite):
+    ID_TYPE = IdType.GoogleBooks
+    URL_PATTERNS = [   
+        r"https://books\.google\.co[^/]+/books\?id=([^&#]+)",
+        r"https://www\.google\.co[^/]+/books/edition/[^/]+/([^&#?]+)",
+        r"https://books\.google\.co[^/]+/books/about/[^?]+?id=([^&#?]+)",
+    ]
+    WIKI_PROPERTY_ID = ''
+    DEFAULT_MODEL = Edition
+
+    @classmethod
+    def id_to_url(self, id_value):
+        return "https://books.google.com/books?id=" + id_value
+
+    def scrape(self):
+        api_url = f'https://www.googleapis.com/books/v1/volumes/{self.id_value}'
+        b = BasicDownloader(api_url).download().json()
+        other = {}
+        title = b['volumeInfo']['title']
+        subtitle = b['volumeInfo']['subtitle'] if 'subtitle' in b['volumeInfo'] else None
+        pub_year = None
+        pub_month = None
+        if 'publishedDate' in b['volumeInfo']:
+            pub_date = b['volumeInfo']['publishedDate'].split('-')
+            pub_year = pub_date[0]
+            pub_month = pub_date[1] if len(pub_date) > 1 else None
+        pub_house = b['volumeInfo']['publisher'] if 'publisher' in b['volumeInfo'] else None
+        language = b['volumeInfo']['language'] if 'language' in b['volumeInfo'] else None
+        pages = b['volumeInfo']['pageCount'] if 'pageCount' in b['volumeInfo'] else None
+        if 'mainCategory' in b['volumeInfo']:
+            other['分类'] = b['volumeInfo']['mainCategory']
+        authors = b['volumeInfo']['authors'] if 'authors' in b['volumeInfo'] else None
+        if 'description' in b['volumeInfo']:
+            brief = b['volumeInfo']['description']
+        elif 'textSnippet' in b['volumeInfo']:
+            brief = b["volumeInfo"]["textSnippet"]["searchInfo"]
+        else:
+            brief = ''
+        brief = re.sub(r'<.*?>', '', brief.replace('<br', '\n<br'))
+        img_url = b['volumeInfo']['imageLinks']['thumbnail'] if 'imageLinks' in b['volumeInfo'] else None
+        isbn10 = None
+        isbn13 = None
+        for iid in b['volumeInfo']['industryIdentifiers'] if 'industryIdentifiers' in b['volumeInfo'] else []:
+            if iid['type'] == 'ISBN_10':
+                isbn10 = iid['identifier']
+            if iid['type'] == 'ISBN_13':
+                isbn13 = iid['identifier']
+        isbn = isbn13  # if isbn13 is not None else isbn10
+
+        raw_img, ext = BasicImageDownloader.download_image(img_url, self.url)
+        data = {
+            'title': title,
+            'subtitle': subtitle,
+            'orig_title': None,
+            'author': authors,
+            'translator': None,
+            'language': language,
+            'pub_house': pub_house,
+            'pub_year': pub_year,
+            'pub_month': pub_month,
+            'binding': None,
+            'pages': pages,
+            'isbn': isbn,
+            'brief': brief,
+            'contents': None,
+            'other_info': other,
+            'cover_image_url': img_url,
+        }
+        return ResourceContent(metadata=data, cover_image=raw_img, cover_image_extention=ext, lookup_ids={IdType.ISBN: isbn13})
diff --git a/test_data/https___www_googleapis_com_books_v1_volumes_hV__zQEACAAJ b/test_data/https___www_googleapis_com_books_v1_volumes_hV__zQEACAAJ
new file mode 100644
index 00000000..ed286c6a
--- /dev/null
+++ b/test_data/https___www_googleapis_com_books_v1_volumes_hV__zQEACAAJ
@@ -0,0 +1,75 @@
+{
+  "kind": "books#volume",
+  "id": "hV--zQEACAAJ",
+  "etag": "lwbqGlV/h5s",
+  "selfLink": "https://www.googleapis.com/books/v1/volumes/hV--zQEACAAJ",
+  "volumeInfo": {
+    "title": "1984 Nineteen Eighty-Four",
+    "authors": [
+      "George Orwell"
+    ],
+    "publisher": "Alma Classics",
+    "publishedDate": "2021-01-07",
+    "description": "In 1984, London is a grim city in the totalitarian state of Oceania where Big Brother is always watching you and the Thought Police can practically read your mind. Winston Smith is a man in grave danger for the simple reason that his memory still functions. Drawn into a forbidden love affair, Winston finds the courage to join a secret revolutionary organization called The Brotherhood, dedicated to the destruction of the Party. Together with his beloved Julia, he hazards his life in a deadly match against the powers that be.Lionel Trilling said of Orwell's masterpiece \" 1984 is a profound, terrifying, and wholly fascinating book. It is a fantasy of the political future, and like any such fantasy, serves its author as a magnifying device for an examination of the present.\" Though the year 1984 now exists in the past, Orwell's novel remains an urgent call for the individual willing to speak truth to power.\"",
+    "industryIdentifiers": [
+      {
+        "type": "ISBN_10",
+        "identifier": "1847498574"
+      },
+      {
+        "type": "ISBN_13",
+        "identifier": "9781847498571"
+      }
+    ],
+    "readingModes": {
+      "text": false,
+      "image": false
+    },
+    "pageCount": 400,
+    "printedPageCount": 400,
+    "dimensions": {
+      "height": "19.90 cm",
+      "width": "13.10 cm",
+      "thickness": "2.20 cm"
+    },
+    "printType": "BOOK",
+    "averageRating": 4,
+    "ratingsCount": 564,
+    "maturityRating": "NOT_MATURE",
+    "allowAnonLogging": false,
+    "contentVersion": "preview-1.0.0",
+    "panelizationSummary": {
+      "containsEpubBubbles": false,
+      "containsImageBubbles": false
+    },
+    "imageLinks": {
+      "smallThumbnail": "http://books.google.com/books/content?id=hV--zQEACAAJ&printsec=frontcover&img=1&zoom=5&imgtk=AFLRE72QQ6bzD4LfhArQGJHoUdX5wex-wfg5FVAKOo2MbmCbFSF_HbDUwhZ-gAvmSKiEBTyoRkC3Kvbo9k1jB0uiOyOXcvgAc2643MV091Ny8TySRaV2HSVXtch-MYK2qfzNvUKwGEhx&source=gbs_api",
+      "thumbnail": "http://books.google.com/books/content?id=hV--zQEACAAJ&printsec=frontcover&img=1&zoom=1&imgtk=AFLRE70UTuB9rf2_mqyGrJGsI2XbzpjV2vGQP9Oyjc441rCvvRiGMhMGYXsgTMbAUZ3rHtxarPvPIqaT-RGH9JzzFEbrXs3cp7f2jaHVh3M-fyPcEkg0eao_AuYUePhckBN-PtHZNyy-&source=gbs_api"
+    },
+    "language": "en",
+    "previewLink": "http://books.google.com/books?id=hV--zQEACAAJ&hl=&source=gbs_api",
+    "infoLink": "https://play.google.com/store/books/details?id=hV--zQEACAAJ&source=gbs_api",
+    "canonicalVolumeLink": "https://play.google.com/store/books/details?id=hV--zQEACAAJ"
+  },
+  "saleInfo": {
+    "country": "US",
+    "saleability": "NOT_FOR_SALE",
+    "isEbook": false
+  },
+  "accessInfo": {
+    "country": "US",
+    "viewability": "NO_PAGES",
+    "embeddable": false,
+    "publicDomain": false,
+    "textToSpeechPermission": "ALLOWED",
+    "epub": {
+      "isAvailable": false
+    },
+    "pdf": {
+      "isAvailable": false
+    },
+    "webReaderLink": "http://play.google.com/books/reader?id=hV--zQEACAAJ&hl=&source=gbs_api",
+    "accessViewStatus": "NONE",
+    "quoteSharingAllowed": false
+  }
+}