|
|
|
@ -17,41 +17,93 @@
|
|
|
|
|
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
|
|
|
|
|
|
# Google Books api document: https://developers.google.com/books/docs/v1/using
|
|
|
|
|
from typing import Dict, List, Optional
|
|
|
|
|
from urllib.parse import quote
|
|
|
|
|
|
|
|
|
|
import requests
|
|
|
|
|
|
|
|
|
|
from cps.services.Metadata import Metadata
|
|
|
|
|
from cps.isoLanguages import get_lang3, get_language_name
|
|
|
|
|
from cps.services.Metadata import MetaRecord, Metadata
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class Google(Metadata):
|
|
|
|
|
__name__ = "Google"
|
|
|
|
|
__id__ = "google"
|
|
|
|
|
BASE_URL = "https://www.googleapis.com/books/v1/volumes?q="
|
|
|
|
|
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"
|
|
|
|
|
|
|
|
|
|
def search(self, query, generic_cover=""):
|
|
|
|
|
def search(
|
|
|
|
|
self, query: str, generic_cover: str = "", locale: str = "en"
|
|
|
|
|
) -> Optional[List[MetaRecord]]:
|
|
|
|
|
if self.active:
|
|
|
|
|
val = list()
|
|
|
|
|
result = requests.get(Google.BASE_URL + query.replace(" ","+"))
|
|
|
|
|
for r in result.json()['items']:
|
|
|
|
|
v = dict()
|
|
|
|
|
v['id'] = r['id']
|
|
|
|
|
v['title'] = r['volumeInfo']['title']
|
|
|
|
|
v['authors'] = r['volumeInfo'].get('authors', [])
|
|
|
|
|
v['description'] = r['volumeInfo'].get('description', "")
|
|
|
|
|
v['publisher'] = r['volumeInfo'].get('publisher', "")
|
|
|
|
|
v['publishedDate'] = r['volumeInfo'].get('publishedDate', "")
|
|
|
|
|
v['tags'] = r['volumeInfo'].get('categories', [])
|
|
|
|
|
v['rating'] = r['volumeInfo'].get('averageRating', 0)
|
|
|
|
|
if r['volumeInfo'].get('imageLinks'):
|
|
|
|
|
v['cover'] = r['volumeInfo']['imageLinks']['thumbnail'].replace("http://", "https://")
|
|
|
|
|
else:
|
|
|
|
|
# v['cover'] = "/../../../static/generic_cover.jpg"
|
|
|
|
|
v['cover'] = generic_cover
|
|
|
|
|
v['source'] = {
|
|
|
|
|
"id": self.__id__,
|
|
|
|
|
"description": "Google Books",
|
|
|
|
|
"link": "https://books.google.com/"}
|
|
|
|
|
v['url'] = "https://books.google.com/books?id=" + r['id']
|
|
|
|
|
val.append(v)
|
|
|
|
|
return val
|
|
|
|
|
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)
|
|
|
|
|
results = requests.get(Google.SEARCH_URL + query)
|
|
|
|
|
for result in results.json()["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:
|
|
|
|
|
match = dict()
|
|
|
|
|
match["id"] = result["id"]
|
|
|
|
|
match["title"] = result["volumeInfo"]["title"]
|
|
|
|
|
match["authors"] = result["volumeInfo"].get("authors", [])
|
|
|
|
|
match["url"] = Google.BOOK_URL + result["id"]
|
|
|
|
|
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", "")
|
|
|
|
|
match["publishedDate"] = result["volumeInfo"].get("publishedDate", "")
|
|
|
|
|
match["rating"] = result["volumeInfo"].get("averageRating", 0)
|
|
|
|
|
match["series"], match["series_index"] = "", 1
|
|
|
|
|
match["tags"] = result["volumeInfo"].get("categories", [])
|
|
|
|
|
|
|
|
|
|
match["source"] = {
|
|
|
|
|
"id": self.__id__,
|
|
|
|
|
"description": Google.DESCRIPTION,
|
|
|
|
|
"link": Google.META_URL,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
match["identifiers"] = {
|
|
|
|
|
"google": match.get("id"),
|
|
|
|
|
}
|
|
|
|
|
match = self._parse_isbn(result=result, match=match)
|
|
|
|
|
return match
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _parse_isbn(result: Dict, match: Dict) -> Dict:
|
|
|
|
|
identifiers = result["volumeInfo"].get("industryIdentifiers", [])
|
|
|
|
|
for identifier in identifiers:
|
|
|
|
|
if identifier.get("type") == Google.ISBN_TYPE:
|
|
|
|
|
match["identifiers"]["isbn"] = identifier.get("identifier")
|
|
|
|
|
break
|
|
|
|
|
return match
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _parse_cover(result: Dict, generic_cover: str) -> str:
|
|
|
|
|
if result["volumeInfo"].get("imageLinks"):
|
|
|
|
|
cover_url = result["volumeInfo"]["imageLinks"]["thumbnail"]
|
|
|
|
|
return cover_url.replace("http://", "https://")
|
|
|
|
|
return generic_cover
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _parse_languages(result: Dict, locale: str) -> List[str]:
|
|
|
|
|
language_iso2 = result.get("language", "")
|
|
|
|
|
languages = (
|
|
|
|
|
[get_language_name(locale, get_lang3(language_iso2))]
|
|
|
|
|
if language_iso2
|
|
|
|
|
else []
|
|
|
|
|
)
|
|
|
|
|
return languages
|
|
|
|
|