]>
Commit | Line | Data |
---|---|---|
a206ef62 RA |
1 | import re |
2 | ||
f096ec26 | 3 | from .common import InfoExtractor |
14f25df2 | 4 | from ..compat import compat_str |
5 | from ..utils import ExtractorError, int_or_none, urlencode_postdata | |
f096ec26 RA |
6 | |
7 | ||
8 | class CuriosityStreamBaseIE(InfoExtractor): | |
9 | _NETRC_MACHINE = 'curiositystream' | |
10 | _auth_token = None | |
f096ec26 RA |
11 | |
12 | def _handle_errors(self, result): | |
13 | error = result.get('error', {}).get('message') | |
14 | if error: | |
15 | if isinstance(error, dict): | |
16 | error = ', '.join(error.values()) | |
17 | raise ExtractorError( | |
18 | '%s said: %s' % (self.IE_NAME, error), expected=True) | |
19 | ||
f7ad7160 | 20 | def _call_api(self, path, video_id, query=None): |
f096ec26 | 21 | headers = {} |
d2ff2c91 | 22 | if not self._auth_token: |
23 | auth_cookie = self._get_cookies('https://curiositystream.com').get('auth_token') | |
24 | if auth_cookie: | |
25 | self.write_debug('Obtained auth_token cookie') | |
8a82af35 | 26 | self._auth_token = auth_cookie.value |
f096ec26 RA |
27 | if self._auth_token: |
28 | headers['X-Auth-Token'] = self._auth_token | |
29 | result = self._download_json( | |
f7ad7160 | 30 | self._API_BASE_URL + path, video_id, headers=headers, query=query) |
f096ec26 RA |
31 | self._handle_errors(result) |
32 | return result['data'] | |
33 | ||
52efa4b3 | 34 | def _perform_login(self, username, password): |
b207d5eb | 35 | result = self._download_json( |
d0e6121a | 36 | 'https://api.curiositystream.com/v1/login', None, |
37 | note='Logging in', data=urlencode_postdata({ | |
52efa4b3 | 38 | 'email': username, |
b207d5eb RA |
39 | 'password': password, |
40 | })) | |
41 | self._handle_errors(result) | |
92775d8a | 42 | CuriosityStreamBaseIE._auth_token = result['message']['auth_token'] |
f096ec26 | 43 | |
3b983ee4 RA |
44 | |
45 | class CuriosityStreamIE(CuriosityStreamBaseIE): | |
46 | IE_NAME = 'curiositystream' | |
47 | _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)' | |
9ac24e23 | 48 | _TESTS = [{ |
14f25df2 | 49 | 'url': 'http://app.curiositystream.com/video/2', |
3b983ee4 RA |
50 | 'info_dict': { |
51 | 'id': '2', | |
52 | 'ext': 'mp4', | |
53 | 'title': 'How Did You Develop The Internet?', | |
54 | 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', | |
9ac24e23 | 55 | 'channel': 'Curiosity Stream', |
56 | 'categories': ['Technology', 'Interview'], | |
57 | 'average_rating': 96.79, | |
58 | 'series_id': '2', | |
f7ad7160 | 59 | }, |
60 | 'params': { | |
f7ad7160 | 61 | # m3u8 download |
62 | 'skip_download': True, | |
63 | }, | |
9ac24e23 | 64 | }] |
3b983ee4 | 65 | |
d0e6121a | 66 | _API_BASE_URL = 'https://api.curiositystream.com/v1/media/' |
67 | ||
3b983ee4 RA |
68 | def _real_extract(self, url): |
69 | video_id = self._match_id(url) | |
f096ec26 | 70 | |
a206ef62 | 71 | formats = [] |
f7ad7160 | 72 | for encoding_format in ('m3u8', 'mpd'): |
d0e6121a | 73 | media = self._call_api(video_id, video_id, query={ |
f7ad7160 | 74 | 'encodingsNew': 'true', |
75 | 'encodingsFormat': encoding_format, | |
76 | }) | |
77 | for encoding in media.get('encodings', []): | |
78 | playlist_url = encoding.get('master_playlist_url') | |
79 | if encoding_format == 'm3u8': | |
80 | # use `m3u8` entry_protocol until EXT-X-MAP is properly supported by `m3u8_native` entry_protocol | |
81 | formats.extend(self._extract_m3u8_formats( | |
82 | playlist_url, video_id, 'mp4', | |
83 | m3u8_id='hls', fatal=False)) | |
84 | elif encoding_format == 'mpd': | |
85 | formats.extend(self._extract_mpd_formats( | |
86 | playlist_url, video_id, mpd_id='dash', fatal=False)) | |
87 | encoding_url = encoding.get('url') | |
88 | file_url = encoding.get('file_url') | |
89 | if not encoding_url and not file_url: | |
a206ef62 | 90 | continue |
f7ad7160 | 91 | f = { |
92 | 'width': int_or_none(encoding.get('width')), | |
93 | 'height': int_or_none(encoding.get('height')), | |
94 | 'vbr': int_or_none(encoding.get('video_bitrate')), | |
95 | 'abr': int_or_none(encoding.get('audio_bitrate')), | |
96 | 'filesize': int_or_none(encoding.get('size_in_bytes')), | |
97 | 'vcodec': encoding.get('video_codec'), | |
98 | 'acodec': encoding.get('audio_codec'), | |
99 | 'container': encoding.get('container_type'), | |
100 | } | |
101 | for f_url in (encoding_url, file_url): | |
102 | if not f_url: | |
103 | continue | |
104 | fmt = f.copy() | |
105 | rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url) | |
106 | if rtmp: | |
107 | fmt.update({ | |
108 | 'url': rtmp.group('url'), | |
109 | 'play_path': rtmp.group('playpath'), | |
110 | 'app': rtmp.group('app'), | |
111 | 'ext': 'flv', | |
112 | 'format_id': 'rtmp', | |
113 | }) | |
114 | else: | |
115 | fmt.update({ | |
116 | 'url': f_url, | |
117 | 'format_id': 'http', | |
118 | }) | |
119 | formats.append(fmt) | |
a206ef62 | 120 | |
f7ad7160 | 121 | title = media['title'] |
122 | ||
f096ec26 RA |
123 | subtitles = {} |
124 | for closed_caption in media.get('closed_captions', []): | |
125 | sub_url = closed_caption.get('file') | |
126 | if not sub_url: | |
127 | continue | |
128 | lang = closed_caption.get('code') or closed_caption.get('language') or 'en' | |
129 | subtitles.setdefault(lang, []).append({ | |
130 | 'url': sub_url, | |
131 | }) | |
132 | ||
133 | return { | |
f096ec26 | 134 | 'id': video_id, |
a206ef62 | 135 | 'formats': formats, |
f096ec26 RA |
136 | 'title': title, |
137 | 'description': media.get('description'), | |
138 | 'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'), | |
139 | 'duration': int_or_none(media.get('duration')), | |
140 | 'tags': media.get('tags'), | |
141 | 'subtitles': subtitles, | |
9ac24e23 | 142 | 'channel': media.get('producer'), |
143 | 'categories': [media.get('primary_category'), media.get('type')], | |
144 | 'average_rating': media.get('rating_percentage'), | |
145 | 'series_id': str(media.get('collection_id') or '') or None, | |
f096ec26 RA |
146 | } |
147 | ||
148 | ||
92775d8a | 149 | class CuriosityStreamCollectionBaseIE(CuriosityStreamBaseIE): |
150 | ||
151 | def _real_extract(self, url): | |
152 | collection_id = self._match_id(url) | |
153 | collection = self._call_api(collection_id, collection_id) | |
154 | entries = [] | |
155 | for media in collection.get('media', []): | |
156 | media_id = compat_str(media.get('id')) | |
157 | media_type, ie = ('series', CuriosityStreamSeriesIE) if media.get('is_collection') else ('video', CuriosityStreamIE) | |
158 | entries.append(self.url_result( | |
159 | 'https://curiositystream.com/%s/%s' % (media_type, media_id), | |
160 | ie=ie.ie_key(), video_id=media_id)) | |
161 | return self.playlist_result( | |
162 | entries, collection_id, | |
163 | collection.get('title'), collection.get('description')) | |
164 | ||
165 | ||
166 | class CuriosityStreamCollectionsIE(CuriosityStreamCollectionBaseIE): | |
167 | IE_NAME = 'curiositystream:collections' | |
168 | _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/collections/(?P<id>\d+)' | |
ef39f860 | 169 | _API_BASE_URL = 'https://api.curiositystream.com/v2/collections/' |
3b983ee4 | 170 | _TESTS = [{ |
ef39f860 | 171 | 'url': 'https://curiositystream.com/collections/86', |
f096ec26 | 172 | 'info_dict': { |
ef39f860 | 173 | 'id': '86', |
174 | 'title': 'Staff Picks', | |
175 | 'description': 'Wondering where to start? Here are a few of our favorite series and films... from our couch to yours.', | |
f096ec26 | 176 | }, |
ef39f860 | 177 | 'playlist_mincount': 7, |
ed807c18 | 178 | }, { |
92775d8a | 179 | 'url': 'https://curiositystream.com/collections/36', |
180 | 'only_matching': True, | |
181 | }] | |
182 | ||
183 | ||
184 | class CuriosityStreamSeriesIE(CuriosityStreamCollectionBaseIE): | |
185 | IE_NAME = 'curiositystream:series' | |
186 | _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:series|collection)/(?P<id>\d+)' | |
187 | _API_BASE_URL = 'https://api.curiositystream.com/v2/series/' | |
188 | _TESTS = [{ | |
189 | 'url': 'https://curiositystream.com/series/2', | |
ed807c18 | 190 | 'info_dict': { |
191 | 'id': '2', | |
192 | 'title': 'Curious Minds: The Internet', | |
193 | 'description': 'How is the internet shaping our lives in the 21st Century?', | |
194 | }, | |
195 | 'playlist_mincount': 16, | |
196 | }, { | |
92775d8a | 197 | 'url': 'https://curiositystream.com/collection/2', |
ed807c18 | 198 | 'only_matching': True, |
3b983ee4 | 199 | }] |