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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
|
# -*- coding: utf-8 -*-
# Copyright 2025 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://tenor.com/"""
from .common import Extractor, Message
from .. import text, util
BASE_PATTERN = r"(?:https?://)?tenor\.com/(?:\w\w(?:-\w\w)?/)?"
class TenorExtractor(Extractor):
"""Base class for tenor extractors"""
category = "tenor"
root = "https://tenor.com"
filename_fmt = "{id}{title:? //}.{extension}"
archive_fmt = "{id}"
request_interval = (0.5, 1.5)
def _init(self):
formats = self.config("format")
if formats is None:
self.formats = ("gif", "mp4", "webm", "webp")
else:
if isinstance(formats, str):
formats = formats.split(",")
self.formats = formats
def items(self):
for gif in self.gifs():
if not (fmt := self._extract_format(gif)):
self.log.warning("%s: Selected format(s) not available",
gif.get("id"))
continue
url = fmt["url"]
title = gif.pop("h1_title", "")
gif["title"] = title[:-4] if title.endswith(" GIF") else title
gif["width"], gif["height"] = fmt.pop("dims") or (0, 0)
gif["description"] = gif.pop("content_description", "")
gif["id_format"] = url.rsplit("/", 2)[1]
gif["format"] = fmt["name"]
gif["duration"] = fmt["duration"]
gif["size"] = fmt["size"]
gif["date"] = self.parse_timestamp(gif["created"])
yield Message.Directory, "", gif
yield Message.Url, url, text.nameext_from_url(url, gif)
def _extract_format(self, gif):
media_formats = gif["media_formats"]
for fmt in self.formats:
if fmt in media_formats:
media = media_formats[fmt]
media["name"] = fmt
return media
def _search_results(self, query):
url = "https://tenor.googleapis.com/v2/search"
params = {
"appversion": "browser-r20250225-1",
"prettyPrint": "false",
"key": "AIzaSyC-P6_qz3FzCoXGLk6tgitZo4jEJ5mLzD8",
"client_key": "tenor_web",
"locale": "en",
"anon_id": "",
"q": query,
"limit": "50",
"contentfilter": "low",
"media_filter": "gif,gif_transparent,mediumgif,tinygif,"
"tinygif_transparent,webp,webp_transparent,"
"tinywebp,tinywebp_transparent,tinymp4,mp4,webm,"
"originalgif,gifpreview",
"fields": "next,results.id,results.media_formats,results.title,"
"results.h1_title,results.long_title,results.itemurl,"
"results.url,results.created,results.user,"
"results.shares,results.embed,results.hasaudio,"
"results.policy_status,results.source_id,results.flags,"
"results.tags,results.content_rating,results.bg_color,"
"results.legacy_info,results.geographic_restriction,"
"results.content_description",
"pos": None,
"component": "web_desktop",
}
headers = {
"Referer": self.root + "/",
"Origin" : self.root,
}
while True:
data = self.request_json(url, params=params, headers=headers)
yield from data["results"]
params["pos"] = data.get("next")
if not params["pos"]:
return
def metadata(self):
return False
def gifs(self):
return ()
class TenorImageExtractor(TenorExtractor):
subcategory = "image"
pattern = BASE_PATTERN + r"view/(?:[^/?#]*-)?(\d+)"
example = "https://tenor.com/view/SLUG-1234567890"
def gifs(self):
url = f"{self.root}/view/{self.groups[0]}"
page = self.request(url).text
pos = page.index('id="store-cache"')
data = util.json_loads(text.extract(page, ">", "</script>", pos)[0])
return (data["gifs"]["byId"].popitem()[1]["results"][0],)
class TenorSearchExtractor(TenorExtractor):
subcategory = "search"
directory_fmt = ("{category}", "{search_tags}")
pattern = BASE_PATTERN + r"search/([^/?#]+)"
example = "https://tenor.com/search/QUERY"
def gifs(self):
query = text.unquote(self.groups[0])
rest, _, last = query.rpartition("-")
if last == "gifs":
query = rest
self.kwdict["search_tags"] = search_tags = query.replace("-", " ")
return self._search_results(search_tags)
class TenorUserExtractor(TenorExtractor):
subcategory = "user"
directory_fmt = ("{category}", "@{user[username]}")
pattern = BASE_PATTERN + r"(?:users|official)/([^/?#]+)"
example = "https://tenor.com/users/USER"
def gifs(self):
return self._search_results("@" + self.groups[0])
|
