From 4d3c399ee985385e888ba068d973e4653d9f50b9 Mon Sep 17 00:00:00 2001 From: Kyle Anthony Williams Date: Sun, 27 Dec 2020 23:46:11 -0500 Subject: [PATCH] [feat] add bandcamp engine --- searx/engines/bandcamp.py | 72 +++++++++++++++++++++++++++++++++++++++ searx/settings.yml | 5 +++ 2 files changed, 77 insertions(+) create mode 100644 searx/engines/bandcamp.py diff --git a/searx/engines/bandcamp.py b/searx/engines/bandcamp.py new file mode 100644 index 000000000..b1b5214fe --- /dev/null +++ b/searx/engines/bandcamp.py @@ -0,0 +1,72 @@ +""" +Bandcamp (Music) + +@website https://bandcamp.com/ +@provide-api no +@results HTML +@parse url, title, content, publishedDate, embedded, 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 + +categories = ['music'] +paging = True + +base_url = "https://bandcamp.com/" +search_string = search_string = 'search?{query}&page={page}' +embedded_url = '''''' + + +def request(query, params): + '''pre-request callback + params: + method : POST/GET + headers : {} + data : {} # if method == POST + url : '' + category: 'search category' + pageno : 1 # number of the requested page + ''' + + 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] + title = result.xpath('//div[@class="heading"]/a/text()')[0] + date = dateparse(result.xpath('//div[@class="released"]/text()')[0].replace("released ", "")) + content = result.xpath('//div[@class="subhead"]/text()')[0] + thumbnail = result.xpath('//div[@class="art"]/img/@src')[0] + new_result = { + "url": extract_text(link), + "title": title, + "content": content, + "publishedDate": date, + "thumbnail": thumbnail, + } + if "album" in result.classes: + new_result["embedded"] = embedded_url.format(type='album', result_id=result_id) + elif "track" in result.classes: + new_result["embedded"] = embedded_url.format(type='track', result_id=result_id) + results.append(new_result) + return results diff --git a/searx/settings.yml b/searx/settings.yml index c289cde5c..058867092 100644 --- a/searx/settings.yml +++ b/searx/settings.yml @@ -197,6 +197,11 @@ engines: # engine : base # shortcut : bs + - name: bandcamp + engine: bandcamp + shortcut: bc + categories: music + - name : wikipedia engine : wikipedia shortcut : wp