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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""`Open Library`_ is an open, editable library catalog, building towards a web
page for every book ever published.
.. _Open Library: https://openlibrary.org
Configuration
=============
The service sometimes takes a very long time to respond, the ``timeout`` may
need to be adjusted.
.. code:: yaml
- name: openlibrary
engine: openlibrary
shortcut: ol
timeout: 10
Implementations
===============
"""
from datetime import datetime
import typing as t
from urllib.parse import urlencode
from dateutil import parser
from searx.result_types import EngineResults
if t.TYPE_CHECKING:
from searx.extended_types import SXNG_Response
from searx.search.processors import OnlineParams
about = {
"website": "https://openlibrary.org",
"wikidata_id": "Q1201876",
"require_api_key": False,
"use_official_api": False,
"official_api_documentation": "https://openlibrary.org/developers/api",
}
paging = True
categories = ["general", "books"]
base_url = "https://openlibrary.org"
search_api = "https://openlibrary.org/search.json"
"""The engine uses the API at the endpoint search.json_.
.. _search.json: https://openlibrary.org/dev/docs/api/search
"""
results_per_page = 10
def request(query: str, params: "OnlineParams") -> None:
args = {
"q": query,
"page": params["pageno"],
"limit": results_per_page,
"fields": "*",
}
params["url"] = f"{search_api}?{urlencode(args)}"
logger.debug("REST API: %s", params["url"])
def response(resp: "SXNG_Response") -> EngineResults:
res = EngineResults()
json_data = resp.json()
for item in json_data.get("docs", []):
cover = ""
if "lending_identifier_s" in item:
cover = f"https://archive.org/services/img/{item['lending_identifier_s']}"
published = item.get("publish_date")
if published:
published_dates = [date for date in map(_parse_date, published) if date]
if published_dates:
published = min(published_dates)
if not published:
published = _parse_date(str(item.get("first_publish_year")))
content = " / ".join(item.get("first_sentence", []))
res.add(
res.types.Paper(
url=f"{base_url}/{item['key']}",
title=item["title"],
content=content,
isbn=item.get("isbn", [])[:5],
authors=item.get("author_name", []),
thumbnail=cover,
publishedDate=published,
tags=item.get("subject", [])[:10] + item.get("place", [])[:10],
)
)
return res
def _parse_date(date: str) -> datetime | None:
if not date:
return None
try:
return parser.parse(date)
except parser.ParserError:
return None
|
