[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
This commit is contained in:
Paul Alcock 2021-09-22 01:55:09 +01:00 committed by Markus Heiser
parent e39a03cc61
commit 823d44ed0a
3 changed files with 102 additions and 0 deletions

View file

@ -162,3 +162,4 @@ features or generally made searx better:
- @jhigginbotham
- @xenrox
- @OliveiraHermogenes
- Paul Alcock @Guilvareux

95
searx/engines/imdb.py Normal file
View file

@ -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

View file

@ -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