[afreecatv] Fix extraction (closes #15556)
[youtube-dl] / youtube_dl / extractor / afreecatv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_xpath
8 from ..utils import (
9     determine_ext,
10     ExtractorError,
11     int_or_none,
12     xpath_text,
13 )
14
15
16 class AfreecaTVIE(InfoExtractor):
17     IE_NAME = 'afreecatv'
18     IE_DESC = 'afreecatv.com'
19     _VALID_URL = r'''(?x)
20                     https?://
21                         (?:
22                             (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
23                             (?:
24                                 /app/(?:index|read_ucc_bbs)\.cgi|
25                                 /player/[Pp]layer\.(?:swf|html)
26                             )\?.*?\bnTitleNo=|
27                             vod\.afreecatv\.com/PLAYER/STATION/
28                         )
29                         (?P<id>\d+)
30                     '''
31     _TESTS = [{
32         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
33         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
34         'info_dict': {
35             'id': '36164052',
36             'ext': 'mp4',
37             'title': '데일리 에이프릴 요정들의 시상식!',
38             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
39             'uploader': 'dailyapril',
40             'uploader_id': 'dailyapril',
41             'upload_date': '20160503',
42         },
43         'skip': 'Video is gone',
44     }, {
45         'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
46         'info_dict': {
47             'id': '36153164',
48             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
49             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
50             'uploader': 'dailyapril',
51             'uploader_id': 'dailyapril',
52         },
53         'playlist_count': 2,
54         'playlist': [{
55             'md5': 'd8b7c174568da61d774ef0203159bf97',
56             'info_dict': {
57                 'id': '36153164_1',
58                 'ext': 'mp4',
59                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
60                 'upload_date': '20160502',
61             },
62         }, {
63             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
64             'info_dict': {
65                 'id': '36153164_2',
66                 'ext': 'mp4',
67                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
68                 'upload_date': '20160502',
69             },
70         }],
71         'skip': 'Video is gone',
72     }, {
73         'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
74         'info_dict': {
75             'id': '18650793',
76             'ext': 'mp4',
77             'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
78             'thumbnail': r're:^https?://.*\.jpg$',
79             'uploader': '윈아디',
80             'uploader_id': 'badkids',
81             'duration': 107,
82         },
83         'params': {
84             'skip_download': True,
85         },
86     }, {
87         'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
88         'info_dict': {
89             'id': '10481652',
90             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
91             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
92             'uploader': 'dailyapril',
93             'uploader_id': 'dailyapril',
94             'duration': 6492,
95         },
96         'playlist_count': 2,
97         'playlist': [{
98             'md5': 'd8b7c174568da61d774ef0203159bf97',
99             'info_dict': {
100                 'id': '20160502_c4c62b9d_174361386_1',
101                 'ext': 'mp4',
102                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
103                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
104                 'uploader': 'dailyapril',
105                 'uploader_id': 'dailyapril',
106                 'upload_date': '20160502',
107                 'duration': 3601,
108             },
109         }, {
110             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
111             'info_dict': {
112                 'id': '20160502_39e739bb_174361386_2',
113                 'ext': 'mp4',
114                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
115                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
116                 'uploader': 'dailyapril',
117                 'uploader_id': 'dailyapril',
118                 'upload_date': '20160502',
119                 'duration': 2891,
120             },
121         }],
122         'params': {
123             'skip_download': True,
124         },
125     }, {
126         # non standard key
127         'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
128         'info_dict': {
129             'id': '20170411_BE689A0E_190960999_1_2_h',
130             'ext': 'mp4',
131             'title': '혼자사는여자집',
132             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
133             'uploader': '♥이슬이',
134             'uploader_id': 'dasl8121',
135             'upload_date': '20170411',
136             'duration': 213,
137         },
138         'params': {
139             'skip_download': True,
140         },
141     }, {
142         # adult video
143         'url': 'http://vod.afreecatv.com/PLAYER/STATION/26542731',
144         'info_dict': {
145             'id': '20171001_F1AE1711_196617479_1',
146             'ext': 'mp4',
147             'title': '[생]서아 초심 찾기 방송 (part 1)',
148             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
149             'uploader': 'BJ서아',
150             'uploader_id': 'bjdyrksu',
151             'upload_date': '20171001',
152             'duration': 3600,
153             'age_limit': 18,
154         },
155         'params': {
156             'skip_download': True,
157         },
158     }, {
159         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
160         'only_matching': True,
161     }, {
162         'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
163         'only_matching': True,
164     }]
165
166     @staticmethod
167     def parse_video_key(key):
168         video_key = {}
169         m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
170         if m:
171             video_key['upload_date'] = m.group('upload_date')
172             video_key['part'] = int(m.group('part'))
173         return video_key
174
175     def _real_extract(self, url):
176         video_id = self._match_id(url)
177
178         webpage = self._download_webpage(url, video_id)
179
180         station_id = self._search_regex(
181             r'nStationNo\s*=\s*(\d+)', webpage, 'station')
182         bbs_id = self._search_regex(
183             r'nBbsNo\s*=\s*(\d+)', webpage, 'bbs')
184         video_id = self._search_regex(
185             r'nTitleNo\s*=\s*(\d+)', webpage, 'title', default=video_id)
186
187         video_xml = self._download_xml(
188             'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
189             video_id, headers={
190                 'Referer': 'http://vod.afreecatv.com/embed.php',
191             }, query={
192                 'nTitleNo': video_id,
193                 'nStationNo': station_id,
194                 'nBbsNo': bbs_id,
195                 'partialView': 'SKIP_ADULT',
196             })
197
198         flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
199         if flag and flag != 'SUCCEED':
200             raise ExtractorError(
201                 '%s said: %s' % (self.IE_NAME, flag), expected=True)
202
203         video_element = video_xml.findall(compat_xpath('./track/video'))[1]
204         if video_element is None or video_element.text is None:
205             raise ExtractorError('Specified AfreecaTV video does not exist',
206                                  expected=True)
207
208         video_url = video_element.text.strip()
209
210         title = xpath_text(video_xml, './track/title', 'title', fatal=True)
211
212         uploader = xpath_text(video_xml, './track/nickname', 'uploader')
213         uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
214         duration = int_or_none(xpath_text(
215             video_xml, './track/duration', 'duration'))
216         thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
217
218         common_entry = {
219             'uploader': uploader,
220             'uploader_id': uploader_id,
221             'thumbnail': thumbnail,
222         }
223
224         info = common_entry.copy()
225         info.update({
226             'id': video_id,
227             'title': title,
228             'duration': duration,
229         })
230
231         if not video_url:
232             entries = []
233             file_elements = video_element.findall(compat_xpath('./file'))
234             one = len(file_elements) == 1
235             for file_num, file_element in enumerate(file_elements, start=1):
236                 file_url = file_element.text
237                 if not file_url:
238                     continue
239                 key = file_element.get('key', '')
240                 upload_date = self._search_regex(
241                     r'^(\d{8})_', key, 'upload date', default=None)
242                 file_duration = int_or_none(file_element.get('duration'))
243                 format_id = key if key else '%s_%s' % (video_id, file_num)
244                 if determine_ext(file_url) == 'm3u8':
245                     formats = self._extract_m3u8_formats(
246                         file_url, video_id, 'mp4', entry_protocol='m3u8_native',
247                         m3u8_id='hls',
248                         note='Downloading part %d m3u8 information' % file_num)
249                 else:
250                     formats = [{
251                         'url': file_url,
252                         'format_id': 'http',
253                     }]
254                 if not formats:
255                     continue
256                 self._sort_formats(formats)
257                 file_info = common_entry.copy()
258                 file_info.update({
259                     'id': format_id,
260                     'title': title if one else '%s (part %d)' % (title, file_num),
261                     'upload_date': upload_date,
262                     'duration': file_duration,
263                     'formats': formats,
264                 })
265                 entries.append(file_info)
266             entries_info = info.copy()
267             entries_info.update({
268                 '_type': 'multi_video',
269                 'entries': entries,
270             })
271             return entries_info
272
273         info = {
274             'id': video_id,
275             'title': title,
276             'uploader': uploader,
277             'uploader_id': uploader_id,
278             'duration': duration,
279             'thumbnail': thumbnail,
280         }
281
282         if determine_ext(video_url) == 'm3u8':
283             info['formats'] = self._extract_m3u8_formats(
284                 video_url, video_id, 'mp4', entry_protocol='m3u8_native',
285                 m3u8_id='hls')
286         else:
287             app, playpath = video_url.split('mp4:')
288             info.update({
289                 'url': app,
290                 'ext': 'flv',
291                 'play_path': 'mp4:' + playpath,
292                 'rtmp_live': True,  # downloading won't end without this
293             })
294
295         return info