Merge pull request #2763 from return42/add-bandcamp

Add Bandcamp search engine

searx/engines/bandcamp.py

@@ -0,0 +1,73 @@
+"""
+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 = '''<iframe width="100%" height="166"
+    scrolling="no" frameborder="no"
+    data-src="https://bandcamp.com/EmbeddedPlayer/{type}={result_id}/size=large/bgcol=ffffff/linkcol=0687f5/tracklist=false/artwork=small/transparent=true/"
+></iframe>'''
+
+
+def request(query, params):
+    '''pre-request callback
+    params<dict>:
+      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()')
+        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,
+        }
+        thumbnail = result.xpath('.//div[@class="art"]/img/@src')
+        if thumbnail:
+            new_result['thumbnail'] = thumbnail[0]
+        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

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

searx/templates/oscar/result_templates/default.html

@@ -13,10 +13,10 @@
 </div>
 {%- endif -%}
 
-{%- if result.img_src -%}
+{%- if result.img_src or result.thumbnail -%}
 <div class="container-fluid">{{- "" -}}
     <div class="row">{{- "" -}}
-        <img src="{{ image_proxify(result.img_src) }}" title="{{ result.title|striptags }}" style="width: auto; max-height: 60px; min-height: 60px;" class="col-xs-2 col-sm-4 col-md-4 result-content">
+        <img src="{{ image_proxify(result.img_src or result.thumbnail) }}" title="{{ result.title|striptags }}" style="width: auto; max-height: 60px; min-height: 60px;" class="col-xs-2 col-sm-4 col-md-4 result-content">
         {%- if result.content %}<p class="result-content col-xs-8 col-sm-8 col-md-8">{{ result.content|safe }}</p>{% endif -%}
     </div>{{- "" -}}
 </div>