mirror of
https://github.com/searxng/searxng.git
synced 2024-11-22 04:01:40 +01:00
916739d6b4
The use of img_src AND thumbnail in the default results makes no sense (only a thumbnail is needed). In the current state this is rather confusing, because img_src is displayed like a thumbnail (small) and thumbnail is displayed like an image (large). Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
58 lines
1.5 KiB
Python
58 lines
1.5 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""Goodreads (books)
|
|
"""
|
|
|
|
from urllib.parse import urlencode
|
|
|
|
from lxml import html
|
|
from searx.utils import extract_text, eval_xpath, eval_xpath_list
|
|
|
|
about = {
|
|
'website': 'https://www.goodreads.com',
|
|
'wikidata_id': 'Q2359213',
|
|
'official_api_documentation': None,
|
|
'use_official_api': False,
|
|
'require_api_key': False,
|
|
'results': 'HTML',
|
|
}
|
|
categories = []
|
|
paging = True
|
|
|
|
base_url = "https://www.goodreads.com"
|
|
|
|
results_xpath = "//table//tr"
|
|
thumbnail_xpath = ".//img[contains(@class, 'bookCover')]/@src"
|
|
url_xpath = ".//a[contains(@class, 'bookTitle')]/@href"
|
|
title_xpath = ".//a[contains(@class, 'bookTitle')]"
|
|
author_xpath = ".//a[contains(@class, 'authorName')]"
|
|
info_text_xpath = ".//span[contains(@class, 'uitext')]"
|
|
|
|
|
|
def request(query, params):
|
|
args = {
|
|
'q': query,
|
|
'page': params['pageno'],
|
|
}
|
|
|
|
params['url'] = f"{base_url}/search?{urlencode(args)}"
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
|
|
dom = html.fromstring(resp.text)
|
|
|
|
for result in eval_xpath_list(dom, results_xpath):
|
|
results.append(
|
|
{
|
|
'url': base_url + extract_text(eval_xpath(result, url_xpath)),
|
|
'title': extract_text(eval_xpath(result, title_xpath)),
|
|
'thumbnail': extract_text(eval_xpath(result, thumbnail_xpath)),
|
|
'content': extract_text(eval_xpath(result, info_text_xpath)),
|
|
'metadata': extract_text(eval_xpath(result, author_xpath)),
|
|
}
|
|
)
|
|
|
|
return results
|