1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-13 16:20:13 +01:00

[fix] bandcamp: fix itemtype (album|track) and exceptions

BTW: polish implementation and show tracklist for albums

Closes: https://github.com/searxng/searxng/issues/883
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser 2022-02-17 22:10:34 +01:00
parent bf2a2ed48f
commit 05c105b837
2 changed files with 42 additions and 16 deletions

View File

@ -1,16 +1,23 @@
"""
Bandcamp (Music)
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""Bandcamp (Music)
@website https://bandcamp.com/
@provide-api no
@results HTML
@parse url, title, content, publishedDate, iframe_src, thumbnail
"""
from urllib.parse import urlencode, urlparse, parse_qs
from dateutil.parser import parse as dateparse
from lxml import html
from searx.utils import extract_text
from searx.utils import (
eval_xpath_getindex,
eval_xpath_list,
extract_text,
)
# about
about = {
@ -26,12 +33,13 @@ categories = ['music']
paging = True
base_url = "https://bandcamp.com/"
search_string = search_string = 'search?{query}&page={page}'
iframe_src = "https://bandcamp.com/EmbeddedPlayer/{type}={result_id}/size=large/bgcol=ffffff/linkcol=0687f5/tracklist=false/artwork=small/transparent=true/"
search_string = 'search?{query}&page={page}'
iframe_src = "https://bandcamp.com/EmbeddedPlayer/{type}={result_id}/size=large/bgcol=000/linkcol=fff/artwork=small"
def request(query, params):
'''pre-request callback
params<dict>:
method : POST/GET
headers : {}
@ -42,37 +50,45 @@ def request(query, params):
'''
search_path = search_string.format(query=urlencode({'q': query}), page=params['pageno'])
params['url'] = base_url + search_path
return params
def response(resp):
'''post-response callback
resp: requests response object
'''
results = []
tree = html.fromstring(resp.text)
search_results = tree.xpath('//li[contains(@class, "searchresult")]')
for result in search_results:
link = result.xpath('.//div[@class="itemurl"]/a')[0]
result_id = parse_qs(urlparse(link.get('href')).query)["search_item_id"][0]
dom = html.fromstring(resp.text)
for result in eval_xpath_list(dom, '//li[contains(@class, "searchresult")]'):
link = eval_xpath_getindex(result, './/div[@class="itemurl"]/a', 0, default=None)
if link is None:
continue
title = result.xpath('.//div[@class="heading"]/a/text()')
date = dateparse(result.xpath('//div[@class="released"]/text()')[0].replace("released ", ""))
content = result.xpath('.//div[@class="subhead"]/text()')
new_result = {
"url": extract_text(link),
"title": extract_text(title),
"content": extract_text(content),
"publishedDate": date,
}
date = eval_xpath_getindex(result, '//div[@class="released"]/text()', 0, default=None)
if date:
new_result["publishedDate"] = dateparse(date.replace("released ", ""))
thumbnail = result.xpath('.//div[@class="art"]/img/@src')
if thumbnail:
new_result['thumbnail'] = thumbnail[0]
if "album" in result.classes:
result_id = parse_qs(urlparse(link.get('href')).query)["search_item_id"][0]
itemtype = extract_text(result.xpath('.//div[@class="itemtype"]')).lower()
if "album" == itemtype:
new_result["iframe_src"] = iframe_src.format(type='album', result_id=result_id)
elif "track" in result.classes:
elif "track" == itemtype:
new_result["iframe_src"] = iframe_src.format(type='track', result_id=result_id)
results.append(new_result)

View File

@ -17,3 +17,13 @@ iframe[src^="https://www.mixcloud.com"] {
// 200px, somtimes 250px.
height: 250px;
}
iframe[src^="https://bandcamp.com/EmbeddedPlayer"] {
// show playlist
height: 350px;
}
iframe[src^="https://bandcamp.com/EmbeddedPlayer/track"] {
// hide playlist
height: 120px;
}