[mod] engines - add IMDB / Internet Movie Database

Merged from @Guilvareux's commit [1] and slightly modfied / see [2].

[1] https://github.com/searx/searx/pull/2980/commits/f2f90071
[2] https://github.com/searx/searx/pull/2980

2 files changed, 101 insertions, 0 deletions

diff --git a/searx/engines/imdb.py b/searx/engines/imdb.py
new file mode 100644
index 000000000..88913ddc6
--- /dev/null
+++ b/searx/engines/imdb.py
@@ -0,0 +1,95 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+# lint: pylint
+
+"""IMDB - Internet Movie Database
+
+Retrieves results from a basic search.  Advanced search options are not
+supported.  IMDB's API is undocumented, here are some posts about:
+
+- https://stackoverflow.com/questions/1966503/does-imdb-provide-an-api
+- https://rapidapi.com/blog/how-to-use-imdb-api/
+
+An alternative that needs IMDPro_ is `IMDb and Box Office Mojo
+<https://developer.imdb.com/documentation>`_
+
+.. __IMDPro: https://pro.imdb.com/login
+
+"""
+
+import json
+
+about = {
+    "website": 'https://imdb.com/',
+    "wikidata_id": 'Q37312',
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": 'HTML',
+}
+
+categories = ['general', ]
+paging = False
+
+# suggestion_url = "https://sg.media-imdb.com/suggestion/{letter}/{query}.json"
+suggestion_url = "https://v2.sg.media-imdb.com/suggestion/{letter}/{query}.json"
+
+href_base = 'https://imdb.com/{category}/{entry_id}'
+
+search_categories = {
+    "nm": "name",
+    "tt": "title",
+    "kw": "keyword",
+    "co": "company",
+    "ep": "episode"
+}
+
+
+def request(query, params):
+
+    query = query.replace(" ", "_").lower()
+    params['url'] = suggestion_url.format(letter=query[0], query=query)
+
+    return params
+
+
+def response(resp):
+
+    suggestions = json.loads(resp.text)
+    results = []
+
+    for entry in suggestions['d']:
+
+        # https://developer.imdb.com/documentation/key-concepts#imdb-ids
+        entry_id = entry['id']
+        categ = search_categories.get(entry_id[:2])
+        if categ is None:
+            logger.error(
+                'skip unknown category tag %s in %s', entry_id[:2], entry_id
+            )
+            continue
+
+        title = entry['l']
+        if 'q' in entry:
+            title += " (%s)" % entry['q']
+
+        content = ''
+        if 'rank' in entry:
+            content += "(%s) " % entry['rank']
+        if 'y' in entry:
+            content += str(entry['y']) + " - "
+        if 's' in entry:
+            content += entry['s']
+
+        # imageUrl is the image itself, it is not a thumb!
+        # image_url = entry['i']['imageUrl']
+
+        results.append({
+            "title":  title,
+            "url": href_base.format(category=categ, entry_id=entry_id),
+            "content": content,
+            # "thumbnail" : image_url,
+            # "template": "videos.html",
+
+        })
+
+    return results
diff --git a/searx/settings.yml b/searx/settings.yml
index 207024192..cce70ac53 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -744,6 +744,12 @@ engines:
       require_api_key: false
       results: JSON
 
+  - name: imdb
+    engine: imdb
+    shortcut: imdb
+    timeout: 6.0
+    disabled: true
+
   - name: ina
     engine: ina
     shortcut: in