summaryrefslogtreecommitdiff
path: root/searx/engines
diff options
context:
space:
mode:
Diffstat (limited to 'searx/engines')
-rw-r--r--searx/engines/apkmirror.py2
-rw-r--r--searx/engines/loc.py68
-rw-r--r--searx/engines/mediathekviewweb.py68
3 files changed, 137 insertions, 1 deletions
diff --git a/searx/engines/apkmirror.py b/searx/engines/apkmirror.py
index a4c66e891..a9ddd711a 100644
--- a/searx/engines/apkmirror.py
+++ b/searx/engines/apkmirror.py
@@ -45,7 +45,7 @@ def response(resp):
dom = html.fromstring(resp.text)
# parse results
- for result in eval_xpath_list(dom, './/div[@id="content"]/div[@class="listWidget"]/div[@class="appRow"]'):
+ for result in eval_xpath_list(dom, './/div[@id="content"]/div[@class="listWidget"]//div[@class="appRow"]'):
link = eval_xpath_getindex(result, './/h5/a', 0)
url = base_url + link.attrib.get('href') + '#downloads'
diff --git a/searx/engines/loc.py b/searx/engines/loc.py
new file mode 100644
index 000000000..5c09ceff2
--- /dev/null
+++ b/searx/engines/loc.py
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""
+
+ Library of Congress : images from Prints and Photographs Online Catalog
+
+"""
+
+from json import loads
+from urllib.parse import urlencode
+
+
+about = {
+ "website": 'https://www.loc.gov/pictures/',
+ "wikidata_id": 'Q131454',
+ "official_api_documentation": 'https://www.loc.gov/pictures/api',
+ "use_official_api": True,
+ "require_api_key": False,
+ "results": 'JSON',
+}
+
+categories = ['images']
+
+paging = True
+
+base_url = 'https://loc.gov/pictures/search/?'
+search_string = "&sp={page}&{query}&fo=json"
+
+IMG_SRC_FIXES = {
+ 'https://tile.loc.gov/storage-services/': 'https://tile.loc.gov/storage-services/',
+ 'https://loc.gov/pictures/static/images/': 'https://tile.loc.gov/storage-services/',
+ 'https://www.loc.gov/pictures/cdn/': 'https://tile.loc.gov/storage-services/',
+}
+
+
+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):
+ results = []
+
+ json_data = loads(resp.text)
+
+ for result in json_data['results']:
+ img_src = result['image']['full']
+ for url_prefix, url_replace in IMG_SRC_FIXES.items():
+ if img_src.startswith(url_prefix):
+ img_src = img_src.replace(url_prefix, url_replace)
+ break
+ else:
+ img_src = result['image']['thumb']
+ results.append({
+ 'url': result['links']['item'],
+ 'title': result['title'],
+ 'img_src': img_src,
+ 'thumbnail_src': result['image']['thumb'],
+ 'author': result['creator'],
+ 'template': 'images.html'
+ })
+
+ return results
diff --git a/searx/engines/mediathekviewweb.py b/searx/engines/mediathekviewweb.py
new file mode 100644
index 000000000..fa442c937
--- /dev/null
+++ b/searx/engines/mediathekviewweb.py
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""MediathekViewWeb (API)
+
+"""
+
+# pylint: disable=missing-function-docstring
+
+import datetime
+from json import loads, dumps
+
+about = {
+ "website": 'https://mediathekviewweb.de/',
+ "wikidata_id": 'Q27877380',
+ "official_api_documentation": 'https://gist.github.com/bagbag/a2888478d27de0e989cf777f81fb33de',
+ "use_official_api": True,
+ "require_api_key": False,
+ "results": 'JSON',
+}
+
+categories = ['videos']
+paging = True
+time_range_support = False
+safesearch = False
+
+def request(query, params):
+
+ params['url'] = 'https://mediathekviewweb.de/api/query'
+ params['method'] = 'POST'
+ params['headers']['Content-type'] = 'text/plain'
+ params['data'] = dumps({
+ 'queries' : [
+ {
+ 'fields' : [
+ 'title',
+ 'topic',
+ ],
+ 'query' : query
+ },
+ ],
+ 'sortBy' : 'timestamp',
+ 'sortOrder' : 'desc',
+ 'future' : True,
+ 'offset' : (params['pageno'] - 1 )* 10,
+ 'size' : 10
+ })
+ return params
+
+def response(resp):
+
+ resp = loads(resp.text)
+
+ mwv_result = resp['result']
+ mwv_result_list = mwv_result['results']
+
+ results = []
+
+ for item in mwv_result_list:
+
+ item['hms'] = str(datetime.timedelta(seconds=item['duration']))
+
+ results.append({
+ 'url' : item['url_video_hd'],
+ 'title' : "%(channel)s: %(title)s (%(hms)s)" % item,
+ 'length' : item['hms'],
+ 'content' : "%(description)s" % item,
+ })
+
+ return results