Itmens/lib.itmens
Itmens/lib.itmens
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add support for books.com.tw

Browse source
This commit is contained in:
Your Name 2023-04-25 19:04:57 -04:00 • committed by Henri Dickson
parent a6787b186d
commit 8e3b96ef70
9 changed files with 1385 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

48
catalog/book/tests.py
View file

@ -169,6 +169,54 @@ class GoogleBooksTestCase(TestCase):
self.assertEqual(site.resource.item.title, "1984 Nineteen Eighty-Four")
class BooksTWTestCase(TestCase):
def test_parse(self):
t_type = IdType.BooksTW
t_id = "0010947886"
t_url = "https://www.books.com.tw/products/0010947886?loc=P_br_60nq68yhb_D_2aabdc_B_1"
t_url2 = "https://www.books.com.tw/products/0010947886"
p1 = SiteManager.get_site_by_url(t_url)
p2 = SiteManager.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://www.books.com.tw/products/0010947886"
site = SiteManager.get_site_by_url(t_url)
self.assertIsNotNone(site)
self.assertEqual(site.ready, False)
site.get_resource_ready()
self.assertEqual(site.ready, True)
self.assertEqual(
site.resource.metadata.get("title"),
"阿拉伯人三千年：從民族、部落、語言、文化、宗教到帝國，綜覽阿拉伯世界的崛起、衰落與再興",
)
self.assertEqual(
site.resource.metadata.get("orig_title"),
"Arabs: A 3000-Year History of Peoples, Tribes and Empires",
)
self.assertEqual(site.resource.metadata.get("isbn"), "9786263152236")
self.assertEqual(site.resource.metadata.get("author"), ["Tim Mackintosh-Smith"])
self.assertEqual(site.resource.metadata.get("translator"), ["吳莉君"])
self.assertEqual(site.resource.metadata.get("language"), "繁體中文")
self.assertEqual(site.resource.metadata.get("pub_house"), "臉譜")
self.assertEqual(site.resource.metadata.get("pub_year"), 2023)
self.assertEqual(site.resource.metadata.get("pub_month"), 2)
self.assertEqual(site.resource.metadata.get("binding"), "平裝")
self.assertEqual(site.resource.metadata.get("pages"), 792)
self.assertEqual(site.resource.metadata.get("price"), "1050 NTD")
self.assertEqual(site.resource.id_type, IdType.BooksTW)
self.assertEqual(site.resource.id_value, "0010947886")
self.assertEqual(site.resource.item.isbn, "9786263152236")
self.assertEqual(
site.resource.item.title, "阿拉伯人三千年：從民族、部落、語言、文化、宗教到帝國，綜覽阿拉伯世界的崛起、衰落與再興"
)
class DoubanBookTestCase(TestCase):
def setUp(self):
pass

2
catalog/common/models.py
View file

@ -25,6 +25,7 @@ class SiteName(models.TextChoices):
Douban = "douban", _("豆瓣")
Goodreads = "goodreads", _("Goodreads")
GoogleBooks = "googlebooks", _("谷歌图书")
BooksTW = "bookstw", _("博客来")
IMDB = "imdb", _("IMDB")
TMDB = "tmdb", _("The Movie Database")
Bandcamp = "bandcamp", _("Bandcamp")
@ -61,6 +62,7 @@ class IdType(models.TextChoices):
DoubanMusic = "doubanmusic", _("豆瓣音乐")
DoubanGame = "doubangame", _("豆瓣游戏")
DoubanDrama = "doubandrama", _("豆瓣舞台剧")
BooksTW = "bookstw", _("博客来图书")
Bandcamp = "bandcamp", _("Bandcamp")
Spotify_Album = "spotify_album", _("Spotify专辑")
Spotify_Show = "spotify_show", _("Spotify播客")

111
catalog/migrations/0005_bookstw.py Normal file
View file

@ -0,0 +1,111 @@
# Generated by Django 3.2.18 on 2023-04-25 23:02
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
("catalog", "0004_podcast_no_real_change"),
]
operations = [
migrations.AlterField(
model_name="externalresource",
name="id_type",
field=models.CharField(
choices=[
("wikidata", "维基数据"),
("isbn10", "ISBN10"),
("isbn", "ISBN"),
("asin", "ASIN"),
("issn", "ISSN"),
("cubn", "统一书号"),
("isrc", "ISRC"),
("gtin", "GTIN UPC EAN码"),
("rss", "RSS Feed URL"),
("imdb", "IMDb"),
("tmdb_tv", "TMDB剧集"),
("tmdb_tvseason", "TMDB剧集"),
("tmdb_tvepisode", "TMDB剧集"),
("tmdb_movie", "TMDB电影"),
("goodreads", "Goodreads"),
("goodreads_work", "Goodreads著作"),
("googlebooks", "谷歌图书"),
("doubanbook", "豆瓣读书"),
("doubanbook_work", "豆瓣读书著作"),
("doubanmovie", "豆瓣电影"),
("doubanmusic", "豆瓣音乐"),
("doubangame", "豆瓣游戏"),
("doubandrama", "豆瓣舞台剧"),
("bookstw", "博客来图书"),
("bandcamp", "Bandcamp"),
("spotify_album", "Spotify专辑"),
("spotify_show", "Spotify播客"),
("discogs_release", "Discogs Release"),
("discogs_master", "Discogs Master"),
("musicbrainz", "MusicBrainz ID"),
("doubanbook_author", "豆瓣读书作者"),
("doubanmovie_celebrity", "豆瓣电影影人"),
("goodreads_author", "Goodreads作者"),
("spotify_artist", "Spotify艺术家"),
("tmdb_person", "TMDB影人"),
("igdb", "IGDB游戏"),
("steam", "Steam游戏"),
("bangumi", "Bangumi"),
("apple_podcast", "苹果播客"),
],
max_length=50,
verbose_name="IdType of the source site",
),
),
migrations.AlterField(
model_name="itemlookupid",
name="id_type",
field=models.CharField(
blank=True,
choices=[
("wikidata", "维基数据"),
("isbn10", "ISBN10"),
("isbn", "ISBN"),
("asin", "ASIN"),
("issn", "ISSN"),
("cubn", "统一书号"),
("isrc", "ISRC"),
("gtin", "GTIN UPC EAN码"),
("rss", "RSS Feed URL"),
("imdb", "IMDb"),
("tmdb_tv", "TMDB剧集"),
("tmdb_tvseason", "TMDB剧集"),
("tmdb_tvepisode", "TMDB剧集"),
("tmdb_movie", "TMDB电影"),
("goodreads", "Goodreads"),
("goodreads_work", "Goodreads著作"),
("googlebooks", "谷歌图书"),
("doubanbook", "豆瓣读书"),
("doubanbook_work", "豆瓣读书著作"),
("doubanmovie", "豆瓣电影"),
("doubanmusic", "豆瓣音乐"),
("doubangame", "豆瓣游戏"),
("doubandrama", "豆瓣舞台剧"),
("bookstw", "博客来图书"),
("bandcamp", "Bandcamp"),
("spotify_album", "Spotify专辑"),
("spotify_show", "Spotify播客"),
("discogs_release", "Discogs Release"),
("discogs_master", "Discogs Master"),
("musicbrainz", "MusicBrainz ID"),
("doubanbook_author", "豆瓣读书作者"),
("doubanmovie_celebrity", "豆瓣电影影人"),
("goodreads_author", "Goodreads作者"),
("spotify_artist", "Spotify艺术家"),
("tmdb_person", "TMDB影人"),
("igdb", "IGDB游戏"),
("steam", "Steam游戏"),
("bangumi", "Bangumi"),
("apple_podcast", "苹果播客"),
],
max_length=50,
verbose_name="源网站",
),
),
]

1
catalog/sites/__init__.py
View file

@ -18,3 +18,4 @@ from .bandcamp import Bandcamp
from .bangumi import Bangumi
from .discogs import DiscogsRelease
from .discogs import DiscogsMaster
from .bookstw import BooksTW

137
catalog/sites/bookstw.py Normal file
View file

@ -0,0 +1,137 @@
from catalog.common import *
from catalog.book.models import *
from catalog.book.utils import *
from .douban import *
import logging
_logger = logging.getLogger(__name__)
@SiteManager.register
class BooksTW(AbstractSite):
SITE_NAME = SiteName.BooksTW
ID_TYPE = IdType.BooksTW
URL_PATTERNS = [
r"\w+://www\.books\.com\.tw/products/(\w+)",
]
WIKI_PROPERTY_ID = "?"
DEFAULT_MODEL = Edition
@classmethod
def id_to_url(cls, id_value):
return "https://www.books.com.tw/products/" + id_value
def scrape(self):
content = BasicDownloader(self.url).download().html()
isbn_elem = content.xpath(
"//div[@class='bd']/ul/li[starts-with(text(),'ISBN：')]/text()"
)
isbn = isbn_elem[0].strip().split("：", 1)[1].strip() if isbn_elem else None
# isbn_elem = content.xpath(
# "//div[@class='bd']/ul/li[starts-with(text(),'EISBN')]/text()"
# )
# eisbn = isbn_elem[0].strip().split("：", 1)[1].strip() if isbn_elem else None
title = content.xpath("string(//h1)") or f"Unknown Title {self.id_value}"
subtitle = None
orig_title = content.xpath("string(//h1/following-sibling::h2)")
authors = content.xpath("string(//div/ul/li[contains(text(),'作者：')])")
authors = authors.strip().split("：", 1)[1].split(",") if authors else []
authors = [s.strip() for s in authors]
# author_orig = content.xpath("string(//div/ul/li[contains(text(),'原文作者：')])")
translators = content.xpath("string(//div/ul/li[contains(text(),'譯者：')])")
translators = (
translators.strip().split("：", 1)[1].split(",") if translators else []
)
translators = [s.strip() for s in translators]
language_elem = content.xpath("//div/ul/li[starts-with(text(),'語言：')]/text()")
language = (
language_elem[0].strip().split("：")[1].strip() if language_elem else None
)
pub_house = content.xpath("string(//div/ul/li[contains(text(),'出版社：')])")
pub_house = (
pub_house.strip().split("：", 1)[1].strip().split(" ", 1)[0]
if pub_house
else None
)
pub_date = content.xpath("string(//div/ul/li[contains(text(),'出版日期：')])")
pub_date = re.match(
r"(\d+)/(\d+)/(\d+)\s*$",
pub_date.strip().split("：", 1)[1].strip().split(" ", 1)[0]
if pub_date
else "",
)
if pub_date:
pub_year = int(pub_date[1])
pub_month = int(pub_date[2])
else:
pub_year = None
pub_month = None
spec = content.xpath("string(//div/ul/li[contains(text(),'規格：')])")
spec = spec.strip().split("：", 1)[1].strip().split("/") if spec else []
if len(spec) > 1:
binding = spec[0].strip()
pages = spec[1].strip().split("頁")
pages = int(pages[0]) if len(pages) > 1 else None
if pages and (pages > 999999 or pages < 1):
pages = None
else:
binding = None
pages = None
price = content.xpath("string(//div/ul/li[contains(text(),'定價：')])")
price = (
price.strip().split("：", 1)[1].split("元")[0].strip() + " NTD"
if price
else None
)
brief = content.xpath("string(//h3[text()='內容簡介']/following-sibling::div)")
contents = content.xpath("string(//h3[text()='目錄']/following-sibling::div)")
series = None
imprint = None
img_url = content.xpath(
"string(//div[contains(@class,'cover_img')]//img[contains(@class,'cover')]/@src)"
)
img_url = re.sub(r"&[wh]=\d+", "", img_url) if img_url else None
data = {
"title": title,
"subtitle": subtitle,
"orig_title": orig_title,
"author": authors,
"translator": translators,
"language": language,
"pub_house": pub_house,
"pub_year": pub_year,
"pub_month": pub_month,
"binding": binding,
"price": price,
"pages": pages,
"isbn": isbn,
"brief": brief,
"contents": contents,
"series": series,
"imprint": imprint,
"cover_image_url": img_url,
}
pd = ResourceContent(metadata=data)
t, n = detect_isbn_asin(isbn)
if t:
pd.lookup_ids[t] = n
pd.cover_image, pd.cover_image_extention = BasicImageDownloader.download_image(
img_url, self.url
)
return pd

2
catalog/sites/rss.py
View file

@ -47,7 +47,7 @@ class RSS(AbstractSite):
@classmethod
def validate_url_fallback(cls, url):
val = URLValidator(verify_exists=False)
val = URLValidator()
try:
val(url)
return cls.parse_feed_from_url(url) is not None

6
common/static/sass/_Label.sass
View file

@ -15,6 +15,8 @@ $bangumi-color-primary: #F09199
$bangumi-color-secondary: #FCFCFC
$goodreads-color-primary: #372213
$goodreads-color-secondary: #F4F1EA
$bookstw-color-primary: white
$bookstw-color-secondary: #7FBA19
$tmdb-color-primary: #91CCA3
$tmdb-color-secondary: #1FB4E2
$bandcamp-color-primary: #28A0C1
@ -78,6 +80,10 @@ $bandcamp-color-secondary: white
background: $goodreads-color-secondary
color: $goodreads-color-primary
font-weight: lighter
&.source-label__bookstw
background: $bookstw-color-secondary
color: $bookstw-color-primary
font-weight: lighter
&.source-label__tmdb
background: linear-gradient(90deg, $tmdb-color-primary, $tmdb-color-secondary)
color: white

4
doc/catalog.md
View file

@ -88,14 +88,14 @@ classDiagram
Add a new site
--------------
- add a new item to `IdType` enum in `catalog/common/models.py`
- add a new value to `IdType` and `SiteName` in `catalog/common/models.py`
- add a new file in `catalog/sites/`, a new class inherits `AbstractSite`, with:
* `SITE_NAME`
* `ID_TYPE`
* `URL_PATTERNS`
* `WIKI_PROPERTY_ID` (not used now)
* `DEFAULT_MODEL` (unless specified in `scrape()` return val)
* a `classmethod` `id_to_url()`
* a classmethod `id_to_url()`
* a method `scrape()` returns a `ResourceContent` object
* ...

1077
test_data/https___www_books_com_tw_products_0010947886 Normal file
View file

File diff suppressed because it is too large Load diff