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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
|
# -*- coding: utf-8 -*-
# Copyright 2020-2022 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://redgifs.com/"""
from .common import Extractor, Message
from .. import text
class RedgifsExtractor(Extractor):
"""Base class for redgifs extractors"""
category = "redgifs"
filename_fmt = "{category}_{id}.{extension}"
archive_fmt = "{id}"
root = "https://www.redgifs.com"
def __init__(self, match):
Extractor.__init__(self, match)
self.key = match.group(1)
formats = self.config("format")
if formats is None:
formats = ("hd", "sd", "gif")
elif isinstance(formats, str):
formats = (formats, "hd", "sd", "gif")
self.formats = formats
def items(self):
metadata = self.metadata()
for gif in self.gifs():
url = self._process(gif)
if not url:
self.log.warning("Skipping '%s' (format not available)",
gif["id"])
continue
gif.update(metadata)
yield Message.Directory, gif
yield Message.Url, url, gif
def _process(self, gif):
gif["_fallback"] = formats = self._formats(gif)
gif["date"] = text.parse_timestamp(gif.get("createDate"))
return next(formats, None)
def _formats(self, gif):
urls = gif["urls"]
for fmt in self.formats:
url = urls.get(fmt)
if url:
url = url.replace("//thumbs2.", "//thumbs3.", 1)
text.nameext_from_url(url, gif)
yield url
def metadata(self):
return {}
def gifs(self):
return ()
class RedgifsUserExtractor(RedgifsExtractor):
"""Extractor for redgifs user profiles"""
subcategory = "user"
directory_fmt = ("{category}", "{userName}")
pattern = r"(?:https?://)?(?:www\.)?redgifs\.com/users/([^/?#]+)"
test = ("https://www.redgifs.com/users/Natalifiction", {
"pattern": r"https://\w+\.redgifs\.com/[A-Za-z]+\.mp4",
"count": ">= 120",
})
def metadata(self):
return {"userName": self.key}
def gifs(self):
return RedgifsAPI(self).user(self.key)
class RedgifsSearchExtractor(RedgifsExtractor):
"""Extractor for redgifs search results"""
subcategory = "search"
directory_fmt = ("{category}", "Search", "{search}")
pattern = r"(?:https?://)?(?:www\.)?redgifs\.com/browse/?\?([^#]+)"
test = (
("https://www.redgifs.com/browse?tags=JAV", {
"pattern": r"https://\w+\.redgifs\.com/[A-Za-z]+\.mp4",
"range": "1-10",
"count": 10,
}),
("https://www.redgifs.com/browse?type=i&verified=y&order=top7"),
)
def metadata(self):
self.params = params = text.parse_query(self.key)
search = params.get("tags") or params.get("order") or "trending"
return {"search": search}
def gifs(self):
return RedgifsAPI(self).search(self.params)
class RedgifsImageExtractor(RedgifsExtractor):
"""Extractor for individual gifs from redgifs.com"""
subcategory = "image"
pattern = (r"(?:https?://)?(?:"
r"(?:www\.)?redgifs\.com/(?:watch|ifr)|"
r"(?:www\.)?gifdeliverynetwork\.com|"
r"i\.redgifs\.com/i)/([A-Za-z]+)")
test = (
("https://redgifs.com/watch/foolishforkedabyssiniancat", {
"pattern": r"https://\w+\.redgifs\.com"
r"/FoolishForkedAbyssiniancat\.mp4",
"content": "f6e03f1df9a2ff2a74092f53ee7580d2fb943533",
}),
("https://redgifs.com/ifr/FoolishForkedAbyssiniancat"),
("https://i.redgifs.com/i/FoolishForkedAbyssiniancat"),
("https://www.gifdeliverynetwork.com/foolishforkedabyssiniancat"),
)
def gifs(self):
return (RedgifsAPI(self).gif(self.key),)
class RedgifsAPI():
API_ROOT = "https://api.redgifs.com"
def __init__(self, extractor):
self.extractor = extractor
def gif(self, gif_id):
endpoint = "/v2/gifs/" + gif_id.lower()
return self._call(endpoint)["gif"]
def user(self, user, order="best"):
endpoint = "/v2/users/{}/search".format(user.lower())
params = {"order": order}
return self._pagination(endpoint, params)
def search(self, params):
endpoint = "/v2/gifs/search"
params["search_text"] = params.pop("tags", None)
params.pop("needSendGtm", None)
return self._pagination(endpoint, params)
def _call(self, endpoint, params=None):
url = self.API_ROOT + endpoint
return self.extractor.request(url, params=params).json()
def _pagination(self, endpoint, params):
params["page"] = 1
while True:
data = self._call(endpoint, params)
yield from data["gifs"]
if params["page"] >= data["pages"]:
return
params["page"] += 1
|
