searxng/searx/engines/ebay.py
2020-10-08 13:20:55 +02:00

69 lines
2.1 KiB
Python

# Ebay (Videos, Music, Files)
#
# @website https://www.ebay.com
# @provide-api no (nothing found)
#
# @using-api no
# @results HTML (using search portal)
# @stable yes (HTML can change)
# @parse url, title, content, price, shipping, source
from lxml import html
from searx.engines.xpath import extract_text
from urllib.parse import quote
categories = ['shopping']
paging = True
url = 'https://www.ebay.com'
search_url = url + '/sch/i.html?_nkw={query}&_sacat={pageno}'
results_xpath = '//li[contains(@class, "s-item")]'
url_xpath = './/a[@class="s-item__link"]/@href'
title_xpath = './/h3[@class="s-item__title"]'
content_xpath = './/div[@span="SECONDARY_INFO"]'
price_xpath = './/div[contains(@class, "s-item__detail")]/span[@class="s-item__price"][1]/text()'
shipping_xpath = './/span[contains(@class, "s-item__shipping")]/text()'
source_country_xpath = './/span[contains(@class, "s-item__location")]/text()'
thumbnail_xpath = './/img[@class="s-item__image-img"]/@src'
def request(query, params):
params['url'] = search_url.format(query=quote(query), pageno=params['pageno'])
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
results_dom = dom.xpath(results_xpath)
if not results_dom:
return []
for result_dom in results_dom:
url = extract_text(result_dom.xpath(url_xpath))
title = extract_text(result_dom.xpath(title_xpath))
content = extract_text(result_dom.xpath(content_xpath))
price = extract_text(result_dom.xpath(price_xpath))
shipping = extract_text(result_dom.xpath(shipping_xpath))
source_country = extract_text(result_dom.xpath(source_country_xpath))
thumbnail = extract_text(result_dom.xpath(thumbnail_xpath))
if title == "":
continue
results.append({
'url': url,
'title': title,
'content': content,
'price': price,
'shipping': shipping,
'source_country': source_country,
'thumbnail': thumbnail,
'template': 'products.html',
})
return results