@@ -0,0 +1,73 @@
4+@website https://bandcamp.com/
7+@parse url, title, content, publishedDate, embedded, thumbnail
10+from urllib.parse import urlencode, urlparse, parse_qs
11+from dateutil.parser import parse as dateparse
13+from searx.utils import extract_text
15+categories = ['music']
18+base_url = "https://bandcamp.com/"
19+search_string = search_string = 'search?{query}&page={page}'
20+embedded_url = '''<iframe width="100%" height="166"
21+ scrolling="no" frameborder="no"
22+ data-src="https://bandcamp.com/EmbeddedPlayer/{type}={result_id}/size=large/bgcol=ffffff/linkcol=0687f5/tracklist=false/artwork=small/transparent=true/"
26+def request(query, params):
27+ '''pre-request callback
31+ data : {} # if method == POST
33+ category: 'search category'
34+ pageno : 1 # number of the requested page
37+ search_path = search_string.format(
38+ query=urlencode({'q': query}),
39+ page=params['pageno'])
41+ params['url'] = base_url + search_path
47+ '''post-response callback
48+ resp: requests response object
51+ tree = html.fromstring(resp.text)
52+ search_results = tree.xpath('//li[contains(@class, "searchresult")]')
53+ for result in search_results:
54+ link = result.xpath('.//div[@class="itemurl"]/a')[0]
55+ result_id = parse_qs(urlparse(link.get('href')).query)["search_item_id"][0]
56+ title = result.xpath('.//div[@class="heading"]/a/text()')
57+ date = dateparse(result.xpath('//div[@class="released"]/text()')[0].replace("released ", ""))
58+ content = result.xpath('.//div[@class="subhead"]/text()')
60+ "url": extract_text(link),
61+ "title": extract_text(title),
62+ "content": extract_text(content),
63+ "publishedDate": date,
65+ thumbnail = result.xpath('.//div[@class="art"]/img/@src')
67+ new_result['thumbnail'] = thumbnail[0]
68+ if "album" in result.classes:
69+ new_result["embedded"] = embedded_url.format(type='album', result_id=result_id)
70+ elif "track" in result.classes:
71+ new_result["embedded"] = embedded_url.format(type='track', result_id=result_id)
72+ results.append(new_result)