1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
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
|
