]>
Commit | Line | Data |
---|---|---|
6624a2b0 | 1 | # encoding: utf-8 |
4c6d2ff8 | 2 | from __future__ import unicode_literals |
6624a2b0 | 3 | |
f143d86a | 4 | import re |
6624a2b0 | 5 | |
6 | from .common import InfoExtractor | |
5c7495a1 YCH |
7 | from ..compat import ( |
8 | compat_str, | |
15707c7e | 9 | compat_urllib_parse_urlencode, |
5c7495a1 | 10 | ) |
38cce791 | 11 | from ..utils import ExtractorError |
6624a2b0 | 12 | |
13 | ||
14 | class SohuIE(InfoExtractor): | |
6d2d21f7 | 15 | _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?' |
6624a2b0 | 16 | |
5ee6fc97 YCH |
17 | _TESTS = [{ |
18 | 'note': 'This video is available only in Mainland China', | |
4c6d2ff8 | 19 | 'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super', |
5ee6fc97 | 20 | 'md5': '29175c8cadd8b5cc4055001e85d6b372', |
4c6d2ff8 PH |
21 | 'info_dict': { |
22 | 'id': '382479172', | |
23 | 'ext': 'mp4', | |
24 | 'title': 'MV:Far East Movement《The Illest》', | |
6624a2b0 | 25 | }, |
051df9ad | 26 | 'skip': 'On available in China', |
5ee6fc97 YCH |
27 | }, { |
28 | 'url': 'http://tv.sohu.com/20150305/n409385080.shtml', | |
3f3308cd | 29 | 'md5': '699060e75cf58858dd47fb9c03c42cfb', |
5ee6fc97 YCH |
30 | 'info_dict': { |
31 | 'id': '409385080', | |
32 | 'ext': 'mp4', | |
33 | 'title': '《2015湖南卫视羊年元宵晚会》唐嫣《花好月圆》', | |
34 | } | |
35 | }, { | |
36 | 'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml', | |
3f3308cd | 37 | 'md5': '9bf34be48f2f4dadcb226c74127e203c', |
5ee6fc97 YCH |
38 | 'info_dict': { |
39 | 'id': '78693464', | |
40 | 'ext': 'mp4', | |
41 | 'title': '【爱范品】第31期:MWC见不到的奇葩手机', | |
42 | } | |
cd65491c YCH |
43 | }, { |
44 | 'note': 'Multipart video', | |
45 | 'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml', | |
46 | 'info_dict': { | |
47 | 'id': '78910339', | |
f158799b | 48 | 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', |
cd65491c YCH |
49 | }, |
50 | 'playlist': [{ | |
3f3308cd | 51 | 'md5': 'bdbfb8f39924725e6589c146bc1883ad', |
cd65491c YCH |
52 | 'info_dict': { |
53 | 'id': '78910339_part1', | |
54 | 'ext': 'mp4', | |
55 | 'duration': 294, | |
56 | 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', | |
57 | } | |
58 | }, { | |
3f3308cd | 59 | 'md5': '3e1f46aaeb95354fd10e7fca9fc1804e', |
cd65491c YCH |
60 | 'info_dict': { |
61 | 'id': '78910339_part2', | |
62 | 'ext': 'mp4', | |
63 | 'duration': 300, | |
64 | 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', | |
65 | } | |
66 | }, { | |
3f3308cd | 67 | 'md5': '8407e634175fdac706766481b9443450', |
cd65491c YCH |
68 | 'info_dict': { |
69 | 'id': '78910339_part3', | |
70 | 'ext': 'mp4', | |
71 | 'duration': 150, | |
72 | 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', | |
73 | } | |
74 | }] | |
2cb434e5 | 75 | }, { |
cd459b1d | 76 | 'note': 'Video with title containing dash', |
2cb434e5 YCH |
77 | 'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml', |
78 | 'info_dict': { | |
79 | 'id': '78932792', | |
80 | 'ext': 'mp4', | |
81 | 'title': 'youtube-dl testing video', | |
82 | }, | |
83 | 'params': { | |
84 | 'skip_download': True | |
85 | } | |
5ee6fc97 | 86 | }] |
6624a2b0 | 87 | |
6624a2b0 | 88 | def _real_extract(self, url): |
f143d86a | 89 | |
6d2d21f7 JMF |
90 | def _fetch_data(vid_id, mytv=False): |
91 | if mytv: | |
92 | base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid=' | |
93 | else: | |
4c6d2ff8 | 94 | base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' |
5ac71f0b | 95 | |
cd459b1d | 96 | return self._download_json( |
38cce791 YCH |
97 | base_data_url + vid_id, video_id, |
98 | 'Downloading JSON data for %s' % vid_id, | |
99 | headers=self.geo_verification_headers()) | |
f143d86a | 100 | |
6624a2b0 | 101 | mobj = re.match(self._VALID_URL, url) |
102 | video_id = mobj.group('id') | |
6d2d21f7 | 103 | mytv = mobj.group('mytv') is not None |
f143d86a | 104 | |
6624a2b0 | 105 | webpage = self._download_webpage(url, video_id) |
2cb434e5 | 106 | |
f158799b | 107 | title = re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage)) |
6624a2b0 | 108 | |
5ac71f0b S |
109 | vid = self._html_search_regex( |
110 | r'var vid ?= ?["\'](\d+)["\']', | |
111 | webpage, 'video path') | |
112 | vid_data = _fetch_data(vid, mytv) | |
3dbec410 YCH |
113 | if vid_data['play'] != 1: |
114 | if vid_data.get('status') == 12: | |
115 | raise ExtractorError( | |
116 | 'Sohu said: There\'s something wrong in the video.', | |
117 | expected=True) | |
118 | else: | |
119 | raise ExtractorError( | |
120 | 'Sohu said: The video is only licensed to users in Mainland China.', | |
121 | expected=True) | |
f143d86a | 122 | |
5ac71f0b S |
123 | formats_json = {} |
124 | for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'): | |
125 | vid_id = vid_data['data'].get('%sVid' % format_id) | |
126 | if not vid_id: | |
127 | continue | |
128 | vid_id = compat_str(vid_id) | |
129 | formats_json[format_id] = vid_data if vid == vid_id else _fetch_data(vid_id, mytv) | |
f143d86a | 130 | |
5ac71f0b | 131 | part_count = vid_data['data']['totalBlocks'] |
f143d86a PH |
132 | |
133 | playlist = [] | |
134 | for i in range(part_count): | |
5ac71f0b S |
135 | formats = [] |
136 | for format_id, format_data in formats_json.items(): | |
3f3308cd | 137 | allot = format_data['allot'] |
3f3308cd | 138 | |
5ac71f0b | 139 | data = format_data['data'] |
3f3308cd YCH |
140 | clips_url = data['clipsURL'] |
141 | su = data['su'] | |
142 | ||
98ca1024 YCH |
143 | video_url = 'newflv.sohu.ccgslb.net' |
144 | cdnId = None | |
145 | retries = 0 | |
3f3308cd | 146 | |
98ca1024 YCH |
147 | while 'newflv.sohu.ccgslb.net' in video_url: |
148 | params = { | |
149 | 'prot': 9, | |
150 | 'file': clips_url[i], | |
151 | 'new': su[i], | |
152 | 'prod': 'flash', | |
5fd6cd64 | 153 | 'rb': 1, |
98ca1024 | 154 | } |
5ee6fc97 | 155 | |
98ca1024 YCH |
156 | if cdnId is not None: |
157 | params['idc'] = cdnId | |
158 | ||
159 | download_note = 'Downloading %s video URL part %d of %d' % ( | |
160 | format_id, i + 1, part_count) | |
161 | ||
162 | if retries > 0: | |
163 | download_note += ' (retry #%d)' % retries | |
164 | part_info = self._parse_json(self._download_webpage( | |
15707c7e | 165 | 'http://%s/?%s' % (allot, compat_urllib_parse_urlencode(params)), |
98ca1024 YCH |
166 | video_id, download_note), video_id) |
167 | ||
168 | video_url = part_info['url'] | |
169 | cdnId = part_info.get('nid') | |
170 | ||
171 | retries += 1 | |
172 | if retries > 5: | |
173 | raise ExtractorError('Failed to get video URL') | |
5ac71f0b S |
174 | |
175 | formats.append({ | |
176 | 'url': video_url, | |
177 | 'format_id': format_id, | |
178 | 'filesize': data['clipsBytes'][i], | |
179 | 'width': data['width'], | |
180 | 'height': data['height'], | |
181 | 'fps': data['fps'], | |
182 | }) | |
183 | self._sort_formats(formats) | |
184 | ||
185 | playlist.append({ | |
186 | 'id': '%s_part%d' % (video_id, i + 1), | |
6624a2b0 | 187 | 'title': title, |
5ac71f0b S |
188 | 'duration': vid_data['data']['clipsDuration'][i], |
189 | 'formats': formats, | |
190 | }) | |
f143d86a PH |
191 | |
192 | if len(playlist) == 1: | |
193 | info = playlist[0] | |
4ec929dc | 194 | info['id'] = video_id |
f143d86a PH |
195 | else: |
196 | info = { | |
f158799b | 197 | '_type': 'multi_video', |
f143d86a PH |
198 | 'entries': playlist, |
199 | 'id': video_id, | |
f158799b | 200 | 'title': title, |
f143d86a PH |
201 | } |
202 | ||
203 | return info |