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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
|
# encoding: utf-8
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_parse_unquote,
)
from ..utils import (
int_or_none,
str_to_int,
xpath_text,
unescapeHTML,
)
class DaumIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
IE_NAME = 'daum.net'
_TESTS = [{
'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
'info_dict': {
'id': 'vab4dyeDBysyBssyukBUjBz',
'ext': 'mp4',
'title': '마크 헌트 vs 안토니오 실바',
'description': 'Mark Hunt vs Antonio Silva',
'upload_date': '20131217',
'thumbnail': 're:^https?://.*\.(?:jpg|png)',
'duration': 2117,
'view_count': int,
'comment_count': int,
},
}, {
'url': 'http://m.tvpot.daum.net/v/65139429',
'info_dict': {
'id': '65139429',
'ext': 'mp4',
'title': 'md5:a100d65d09cec246d8aa9bde7de45aed',
'description': 'md5:79794514261164ff27e36a21ad229fc5',
'upload_date': '20150604',
'thumbnail': 're:^https?://.*\.(?:jpg|png)',
'duration': 154,
'view_count': int,
'comment_count': int,
},
}, {
'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
'only_matching': True,
}, {
'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
'info_dict': {
'id': 'vwIpVpCQsT8$',
'ext': 'flv',
'title': '01-Korean War ( Trouble on the horizon )',
'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
'upload_date': '20080223',
'thumbnail': 're:^https?://.*\.(?:jpg|png)',
'duration': 249,
'view_count': int,
'comment_count': int,
},
}]
def _real_extract(self, url):
video_id = compat_urllib_parse_unquote(self._match_id(url))
query = compat_urllib_parse.urlencode({'vid': video_id})
movie_data = self._download_json(
'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query,
video_id, 'Downloading video formats info')
# For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
info = self._download_xml(
'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
'Downloading video info')
formats = []
for format_el in movie_data['output_list']['output_list']:
profile = format_el['profile']
format_query = compat_urllib_parse.urlencode({
'vid': video_id,
'profile': profile,
})
url_doc = self._download_xml(
'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
video_id, note='Downloading video data for %s format' % profile)
format_url = url_doc.find('result/url').text
formats.append({
'url': format_url,
'format_id': profile,
'width': int_or_none(format_el.get('width')),
'height': int_or_none(format_el.get('height')),
'filesize': int_or_none(format_el.get('filesize')),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': info.find('TITLE').text,
'formats': formats,
'thumbnail': xpath_text(info, 'THUMB_URL'),
'description': xpath_text(info, 'CONTENTS'),
'duration': int_or_none(xpath_text(info, 'DURATION')),
'upload_date': info.find('REGDTTM').text[:8],
'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
}
class DaumClipIE(InfoExtractor):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
IE_NAME = 'daum.net:clip'
_TESTS = [{
'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
'info_dict': {
'id': '52554690',
'ext': 'mp4',
'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
'upload_date': '20130831',
'thumbnail': 're:^https?://.*\.(?:jpg|png)',
'duration': 3868,
'view_count': int,
},
}, {
'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
clip_info = self._download_json(
'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
video_id, 'Downloading clip info')['clip_bean']
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
'title': unescapeHTML(clip_info['title']),
'thumbnail': clip_info.get('thumb_url'),
'description': clip_info.get('contents'),
'duration': int_or_none(clip_info.get('duration')),
'upload_date': clip_info.get('up_date')[:8],
'view_count': int_or_none(clip_info.get('play_count')),
'ie_key': 'Daum',
}
class DaumListIE(InfoExtractor):
def _get_entries(self, list_id, list_id_type):
name = None
entries = []
for pagenum in itertools.count(1):
list_info = self._download_json(
'http://tvpot.daum.net/mypot/json/GetClipInfo.do?size=48&init=true&order=date&page=%d&%s=%s' % (
pagenum, list_id_type, list_id), list_id,'Downloading list info - %s' % pagenum)
entries.extend([
self.url_result(
'http://tvpot.daum.net/v/%s' % clip['vid'])
for clip in list_info['clip_list']
])
if not name:
name = list_info.get('playlist_bean', {}).get('name') or \
list_info.get('potInfo', {}).get('name')
if not list_info.get('has_more'):
break
return name, entries
class DaumPlaylistIE(DaumListIE):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View\.do|Top\.tv)\?.*?playlistid=(?P<id>[0-9]+)'
IE_NAME = 'daum.net:playlist'
_TESTS = [{
'note': 'Playlist url with clipid',
'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
'info_dict': {
'id': '6213966',
'title': 'Woorissica Official',
},
'playlist_mincount': 181
}, {
'note': 'Playlist url with clipid - noplaylist',
'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
'info_dict': {
'id': '73806844',
'ext': 'mp4',
'title': '151017 Airport',
'upload_date': '20160117',
},
'params': {
'noplaylist': True,
'skip_download': True,
}
}]
def _real_extract(self, url):
if DaumClipIE.suitable(url) and self._downloader.params.get('noplaylist'):
return self.url_result(url, 'DaumClip')
list_id = self._match_id(url)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
name, entries = self._get_entries(list_id, 'playlistid')
return self.playlist_result(entries, list_id, name)
class DaumUserIE(DaumListIE):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View|Top)\.do\?.*?ownerid=(?P<id>[0-9a-zA-Z]+)'
IE_NAME = 'daum.net:user'
_TESTS = [{
'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0',
'info_dict': {
'id': 'o2scDLIVbHc0',
'title': '마이 리틀 텔레비전',
},
'playlist_mincount': 213
}, {
'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156',
'info_dict': {
'id': '73801156',
'ext': 'mp4',
'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116',
'upload_date': '20160117',
'description': 'md5:5e91d2d6747f53575badd24bd62b9f36'
},
'params': {
'noplaylist': True,
'skip_download': True,
}
}, {
'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence',
'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631',
'info_dict': {
'id': '6196631',
'title': '마이 리틀 텔레비전 - 20160109',
},
'playlist_count': 11
}, {
'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0',
'only_matching': True,
}]
def _real_extract(self, url):
if DaumClipIE.suitable(url) and self._downloader.params.get('noplaylist'):
return self.url_result(url, 'DaumClip')
if DaumPlaylistIE.suitable(url):
return self.url_result(url, 'DaumPlaylist')
list_id = self._match_id(url)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
name, entries = self._get_entries(list_id, 'ownerid')
return self.playlist_result(entries, list_id, name)
|
