1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-14 08:40:11 +01:00
searxng/searx/engines/rottentomatoes.py
Markus Heiser 916739d6b4 [mod] simple theme: drop img_src from default results
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>
2024-05-16 07:30:38 +02:00

60 lines
1.7 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-or-later
"""RottenTomatoes (movies)
"""
from urllib.parse import quote_plus
from lxml import html
from searx.utils import eval_xpath, eval_xpath_list, extract_text
# about
about = {
"website": 'https://www.rottentomatoes.com/',
"wikidata_id": 'Q105584',
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
categories = ['movies']
base_url = "https://www.rottentomatoes.com"
results_xpath = "//search-page-media-row"
url_xpath = "./a[1]/@href"
title_xpath = "./a/img/@alt"
thumbnail_xpath = "./a/img/@src"
release_year_xpath = "concat('From ', string(./@releaseyear))"
score_xpath = "concat('Score: ', string(./@tomatometerscore))"
cast_xpath = "concat('Starring ', string(./@cast))"
def request(query, params):
params["url"] = f"{base_url}/search?search={quote_plus(query)}"
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in eval_xpath_list(dom, results_xpath):
content = []
for xpath in (release_year_xpath, score_xpath, cast_xpath):
info = extract_text(eval_xpath(result, xpath))
# a gap in the end means that no data was found
if info and info[-1] != " ":
content.append(info)
results.append(
{
'url': extract_text(eval_xpath(result, url_xpath)),
'title': extract_text(eval_xpath(result, title_xpath)),
'content': ', '.join(content),
'thumbnail': extract_text(eval_xpath(result, thumbnail_xpath)),
}
)
return results