1
0
mirror of https://github.com/janeczku/calibre-web synced 2024-12-18 14:10:30 +00:00
calibre-web/cps/metadata_provider/google.py

130 lines
4.8 KiB
Python
Raw Normal View History

2021-07-05 16:55:54 +00:00
# -*- coding: utf-8 -*-
# This file is part of the Calibre-Web (https://github.com/janeczku/calibre-web)
# Copyright (C) 2021 OzzieIsaacs
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
2021-07-07 19:24:29 +00:00
# Google Books api document: https://developers.google.com/books/docs/v1/using
from typing import Dict, List, Optional
from urllib.parse import quote
from datetime import datetime
2021-07-05 16:55:54 +00:00
import requests
2021-12-13 00:23:03 +00:00
from cps import logger
from cps.isoLanguages import get_lang3, get_language_name
2021-12-13 16:21:41 +00:00
from cps.services.Metadata import MetaRecord, MetaSourceInfo, Metadata
2021-07-05 16:55:54 +00:00
log = logger.create()
2021-07-05 16:55:54 +00:00
2021-07-06 18:24:27 +00:00
class Google(Metadata):
2021-07-05 16:55:54 +00:00
__name__ = "Google"
2021-07-08 17:14:38 +00:00
__id__ = "google"
DESCRIPTION = "Google Books"
META_URL = "https://books.google.com/"
BOOK_URL = "https://books.google.com/books?id="
SEARCH_URL = "https://www.googleapis.com/books/v1/volumes?q="
ISBN_TYPE = "ISBN_13"
2021-07-05 16:55:54 +00:00
def search(
self, query: str, generic_cover: str = "", locale: str = "en"
) -> Optional[List[MetaRecord]]:
val = list()
2021-07-05 16:55:54 +00:00
if self.active:
title_tokens = list(self.get_title_tokens(query, strip_joiners=False))
if title_tokens:
tokens = [quote(t.encode("utf-8")) for t in title_tokens]
query = "+".join(tokens)
try:
results = requests.get(Google.SEARCH_URL + query)
results.raise_for_status()
except Exception as e:
log.warning(e)
2024-08-12 16:29:31 +00:00
return []
for result in results.json().get("items", []):
val.append(
self._parse_search_result(
result=result, generic_cover=generic_cover, locale=locale
)
)
return val
def _parse_search_result(
self, result: Dict, generic_cover: str, locale: str
) -> MetaRecord:
2021-12-13 16:21:41 +00:00
match = MetaRecord(
id=result["id"],
title=result["volumeInfo"]["title"],
authors=result["volumeInfo"].get("authors", []),
url=Google.BOOK_URL + result["id"],
source=MetaSourceInfo(
id=self.__id__,
description=Google.DESCRIPTION,
link=Google.META_URL,
),
)
2021-12-13 16:21:41 +00:00
match.cover = self._parse_cover(result=result, generic_cover=generic_cover)
match.description = result["volumeInfo"].get("description", "")
match.languages = self._parse_languages(result=result, locale=locale)
match.publisher = result["volumeInfo"].get("publisher", "")
try:
datetime.strptime(result["volumeInfo"].get("publishedDate", ""), "%Y-%m-%d")
match.publishedDate = result["volumeInfo"].get("publishedDate", "")
except ValueError:
match.publishedDate = ""
2021-12-13 16:21:41 +00:00
match.rating = result["volumeInfo"].get("averageRating", 0)
match.series, match.series_index = "", 1
match.tags = result["volumeInfo"].get("categories", [])
2021-12-13 16:21:41 +00:00
match.identifiers = {"google": match.id}
match = self._parse_isbn(result=result, match=match)
return match
@staticmethod
2021-12-13 16:21:41 +00:00
def _parse_isbn(result: Dict, match: MetaRecord) -> MetaRecord:
identifiers = result["volumeInfo"].get("industryIdentifiers", [])
for identifier in identifiers:
if identifier.get("type") == Google.ISBN_TYPE:
2021-12-13 16:21:41 +00:00
match.identifiers["isbn"] = identifier.get("identifier")
break
return match
2021-07-05 16:55:54 +00:00
@staticmethod
def _parse_cover(result: Dict, generic_cover: str) -> str:
if result["volumeInfo"].get("imageLinks"):
cover_url = result["volumeInfo"]["imageLinks"]["thumbnail"]
# strip curl in cover
cover_url = cover_url.replace("&edge=curl", "")
# request 800x900 cover image (higher resolution)
cover_url += "&fife=w800-h900"
return cover_url.replace("http://", "https://")
return generic_cover
2021-07-05 16:55:54 +00:00
@staticmethod
def _parse_languages(result: Dict, locale: str) -> List[str]:
2021-12-13 16:21:41 +00:00
language_iso2 = result["volumeInfo"].get("language", "")
languages = (
[get_language_name(locale, get_lang3(language_iso2))]
if language_iso2
else []
)
return languages