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
|
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
traverse_obj,
unescapeHTML,
url_or_none,
)
class NineGagIE(InfoExtractor):
IE_NAME = '9gag'
IE_DESC = '9GAG'
_VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://9gag.com/gag/ae5Ag7B',
'info_dict': {
'id': 'ae5Ag7B',
'ext': 'webm',
'title': 'Capybara Agility Training',
'upload_date': '20191108',
'timestamp': 1573237208,
'thumbnail': 'https://img-9gag-fun.9cache.com/photo/ae5Ag7B_460s.jpg',
'categories': ['Awesome'],
'tags': ['Awesome'],
'duration': 44,
'like_count': int,
'dislike_count': int,
'comment_count': int,
}
}, {
# HTML escaped title
'url': 'https://9gag.com/gag/av5nvyb',
'only_matching': True,
}, {
# Non Anonymous Uploader
'url': 'https://9gag.com/gag/ajgp66G',
'info_dict': {
'id': 'ajgp66G',
'ext': 'webm',
'title': 'Master Shifu! Or Splinter! You decide:',
'upload_date': '20220806',
'timestamp': 1659803411,
'thumbnail': 'https://img-9gag-fun.9cache.com/photo/ajgp66G_460s.jpg',
'categories': ['Funny'],
'tags': ['Funny'],
'duration': 26,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'uploader': 'Peter Klaus',
'uploader_id': 'peterklaus12',
'uploader_url': 'https://9gag.com/u/peterklaus12',
}
}]
def _real_extract(self, url):
post_id = self._match_id(url)
post = self._download_json(
'https://9gag.com/v1/post', post_id, query={
'id': post_id
})['data']['post']
if post.get('type') != 'Animated':
raise ExtractorError(
'The given url does not contain a video',
expected=True)
duration = None
formats = []
thumbnails = []
for key, image in (post.get('images') or {}).items():
image_url = url_or_none(image.get('url'))
if not image_url:
continue
ext = determine_ext(image_url)
image_id = key.strip('image')
common = {
'url': image_url,
'width': int_or_none(image.get('width')),
'height': int_or_none(image.get('height')),
}
if ext in ('jpg', 'png'):
webp_url = image.get('webpUrl')
if webp_url:
t = common.copy()
t.update({
'id': image_id + '-webp',
'url': webp_url,
})
thumbnails.append(t)
common.update({
'id': image_id,
'ext': ext,
})
thumbnails.append(common)
elif ext in ('webm', 'mp4'):
if not duration:
duration = int_or_none(image.get('duration'))
common['acodec'] = 'none' if image.get('hasAudio') == 0 else None
for vcodec in ('vp8', 'vp9', 'h265'):
c_url = image.get(vcodec + 'Url')
if not c_url:
continue
c_f = common.copy()
c_f.update({
'format_id': image_id + '-' + vcodec,
'url': c_url,
'vcodec': vcodec,
})
formats.append(c_f)
common.update({
'ext': ext,
'format_id': image_id,
})
formats.append(common)
section = traverse_obj(post, ('postSection', 'name'))
tags = None
post_tags = post.get('tags')
if post_tags:
tags = []
for tag in post_tags:
tag_key = tag.get('key')
if not tag_key:
continue
tags.append(tag_key)
return {
'id': post_id,
'title': unescapeHTML(post.get('title')),
'timestamp': int_or_none(post.get('creationTs')),
'duration': duration,
'uploader': traverse_obj(post, ('creator', 'fullName')),
'uploader_id': traverse_obj(post, ('creator', 'username')),
'uploader_url': url_or_none(traverse_obj(post, ('creator', 'profileUrl'))),
'formats': formats,
'thumbnails': thumbnails,
'like_count': int_or_none(post.get('upVoteCount')),
'dislike_count': int_or_none(post.get('downVoteCount')),
'comment_count': int_or_none(post.get('commentsCount')),
'age_limit': 18 if post.get('nsfw') == 1 else None,
'categories': [section] if section else None,
'tags': tags,
}
|
