]>
Commit | Line | Data |
---|---|---|
6de82b44 | 1 | from .common import InfoExtractor |
3d2623a8 | 2 | from ..networking.exceptions import HTTPError |
6de82b44 | 3 | from ..utils import ( |
8fd2a7be | 4 | ExtractorError, |
6de82b44 | 5 | float_or_none, |
e897bd82 | 6 | int_or_none, |
8fd2a7be | 7 | parse_resolution, |
6de82b44 | 8 | str_or_none, |
6de82b44 | 9 | try_get, |
8fd2a7be S |
10 | unified_timestamp, |
11 | url_or_none, | |
12 | urljoin, | |
6de82b44 E |
13 | ) |
14 | ||
15 | ||
16 | class PuhuTVIE(InfoExtractor): | |
8fd2a7be | 17 | _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-izle' |
6de82b44 | 18 | IE_NAME = 'puhutv' |
8fd2a7be S |
19 | _TESTS = [{ |
20 | # film | |
21 | 'url': 'https://puhutv.com/sut-kardesler-izle', | |
162bcc68 | 22 | 'md5': 'a347470371d56e1585d1b2c8dab01c96', |
8fd2a7be S |
23 | 'info_dict': { |
24 | 'id': '5085', | |
25 | 'display_id': 'sut-kardesler', | |
26 | 'ext': 'mp4', | |
27 | 'title': 'Süt Kardeşler', | |
162bcc68 | 28 | 'description': 'md5:ca09da25b7e57cbb5a9280d6e48d17aa', |
8fd2a7be S |
29 | 'thumbnail': r're:^https?://.*\.jpg$', |
30 | 'duration': 4832.44, | |
31 | 'creator': 'Arzu Film', | |
162bcc68 RA |
32 | 'timestamp': 1561062602, |
33 | 'upload_date': '20190620', | |
8fd2a7be S |
34 | 'release_year': 1976, |
35 | 'view_count': int, | |
162bcc68 | 36 | 'tags': list, |
6de82b44 | 37 | }, |
8fd2a7be S |
38 | }, { |
39 | # episode, geo restricted, bypassable with --geo-verification-proxy | |
40 | 'url': 'https://puhutv.com/jet-sosyete-1-bolum-izle', | |
41 | 'only_matching': True, | |
42 | }, { | |
43 | # 4k, with subtitles | |
44 | 'url': 'https://puhutv.com/dip-1-bolum-izle', | |
45 | 'only_matching': True, | |
46 | }] | |
6de82b44 E |
47 | _SUBTITLE_LANGS = { |
48 | 'English': 'en', | |
49 | 'Deutsch': 'de', | |
add96eb9 | 50 | 'عربى': 'ar', |
6de82b44 E |
51 | } |
52 | ||
53 | def _real_extract(self, url): | |
8fd2a7be S |
54 | display_id = self._match_id(url) |
55 | ||
6de82b44 | 56 | info = self._download_json( |
add96eb9 | 57 | urljoin(url, f'/api/slug/{display_id}-izle'), |
8fd2a7be | 58 | display_id)['data'] |
6de82b44 | 59 | |
add96eb9 | 60 | video_id = str(info['id']) |
162bcc68 RA |
61 | show = info.get('title') or {} |
62 | title = info.get('name') or show['name'] | |
6de82b44 | 63 | if info.get('display_name'): |
add96eb9 | 64 | title = '{} {}'.format(title, info['display_name']) |
6de82b44 | 65 | |
8fd2a7be S |
66 | try: |
67 | videos = self._download_json( | |
add96eb9 | 68 | f'https://puhutv.com/api/assets/{video_id}/videos', |
8fd2a7be S |
69 | display_id, 'Downloading video JSON', |
70 | headers=self.geo_verification_headers()) | |
71 | except ExtractorError as e: | |
3d2623a8 | 72 | if isinstance(e.cause, HTTPError) and e.cause.status == 403: |
8fd2a7be S |
73 | self.raise_geo_restricted() |
74 | raise | |
75 | ||
162bcc68 | 76 | urls = [] |
8fd2a7be | 77 | formats = [] |
162bcc68 | 78 | |
8fd2a7be S |
79 | for video in videos['data']['videos']: |
80 | media_url = url_or_none(video.get('url')) | |
162bcc68 | 81 | if not media_url or media_url in urls: |
8fd2a7be | 82 | continue |
162bcc68 RA |
83 | urls.append(media_url) |
84 | ||
8fd2a7be | 85 | playlist = video.get('is_playlist') |
162bcc68 | 86 | if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url: |
f7f30491 | 87 | formats.extend(self._extract_m3u8_formats( |
8fd2a7be | 88 | media_url, video_id, 'mp4', entry_protocol='m3u8_native', |
f7f30491 | 89 | m3u8_id='hls', fatal=False)) |
8fd2a7be | 90 | continue |
162bcc68 | 91 | |
8fd2a7be S |
92 | quality = int_or_none(video.get('quality')) |
93 | f = { | |
94 | 'url': media_url, | |
95 | 'ext': 'mp4', | |
add96eb9 | 96 | 'height': quality, |
8fd2a7be S |
97 | } |
98 | video_format = video.get('video_format') | |
162bcc68 RA |
99 | is_hls = (video_format == 'hls' or '/hls/' in media_url or '/chunklist.m3u8' in media_url) and playlist is False |
100 | if is_hls: | |
8fd2a7be S |
101 | format_id = 'hls' |
102 | f['protocol'] = 'm3u8_native' | |
103 | elif video_format == 'mp4': | |
104 | format_id = 'http' | |
8fd2a7be S |
105 | else: |
106 | continue | |
107 | if quality: | |
add96eb9 | 108 | format_id += f'-{quality}p' |
8fd2a7be S |
109 | f['format_id'] = format_id |
110 | formats.append(f) | |
8fd2a7be | 111 | |
8fd2a7be | 112 | creator = try_get( |
add96eb9 | 113 | show, lambda x: x['producer']['name'], str) |
8fd2a7be | 114 | |
162bcc68 | 115 | content = info.get('content') or {} |
8fd2a7be S |
116 | |
117 | images = try_get( | |
162bcc68 | 118 | content, lambda x: x['images']['wide'], dict) or {} |
8fd2a7be S |
119 | thumbnails = [] |
120 | for image_id, image_url in images.items(): | |
add96eb9 | 121 | if not isinstance(image_url, str): |
8fd2a7be S |
122 | continue |
123 | if not image_url.startswith(('http', '//')): | |
add96eb9 | 124 | image_url = f'https://{image_url}' |
8fd2a7be S |
125 | t = parse_resolution(image_id) |
126 | t.update({ | |
127 | 'id': image_id, | |
add96eb9 | 128 | 'url': image_url, |
8fd2a7be S |
129 | }) |
130 | thumbnails.append(t) | |
131 | ||
6de82b44 | 132 | tags = [] |
162bcc68 | 133 | for genre in show.get('genres') or []: |
8fd2a7be | 134 | if not isinstance(genre, dict): |
6de82b44 | 135 | continue |
8fd2a7be | 136 | genre_name = genre.get('name') |
add96eb9 | 137 | if genre_name and isinstance(genre_name, str): |
8fd2a7be | 138 | tags.append(genre_name) |
6de82b44 E |
139 | |
140 | subtitles = {} | |
162bcc68 | 141 | for subtitle in content.get('subtitles') or []: |
6de82b44 E |
142 | if not isinstance(subtitle, dict): |
143 | continue | |
144 | lang = subtitle.get('language') | |
162bcc68 | 145 | sub_url = url_or_none(subtitle.get('url') or subtitle.get('file')) |
add96eb9 | 146 | if not lang or not isinstance(lang, str) or not sub_url: |
6de82b44 E |
147 | continue |
148 | subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{ | |
add96eb9 | 149 | 'url': sub_url, |
6de82b44 E |
150 | }] |
151 | ||
6de82b44 E |
152 | return { |
153 | 'id': video_id, | |
154 | 'display_id': display_id, | |
155 | 'title': title, | |
162bcc68 RA |
156 | 'description': info.get('description') or show.get('description'), |
157 | 'season_id': str_or_none(info.get('season_id')), | |
158 | 'season_number': int_or_none(info.get('season_number')), | |
159 | 'episode_number': int_or_none(info.get('episode_number')), | |
160 | 'release_year': int_or_none(show.get('released_at')), | |
161 | 'timestamp': unified_timestamp(info.get('created_at')), | |
8fd2a7be | 162 | 'creator': creator, |
162bcc68 RA |
163 | 'view_count': int_or_none(content.get('watch_count')), |
164 | 'duration': float_or_none(content.get('duration_in_ms'), 1000), | |
6de82b44 E |
165 | 'tags': tags, |
166 | 'subtitles': subtitles, | |
6de82b44 | 167 | 'thumbnails': thumbnails, |
add96eb9 | 168 | 'formats': formats, |
6de82b44 E |
169 | } |
170 | ||
171 | ||
172 | class PuhuTVSerieIE(InfoExtractor): | |
8fd2a7be | 173 | _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-detay' |
6de82b44 | 174 | IE_NAME = 'puhutv:serie' |
8fd2a7be S |
175 | _TESTS = [{ |
176 | 'url': 'https://puhutv.com/deniz-yildizi-detay', | |
177 | 'info_dict': { | |
178 | 'title': 'Deniz Yıldızı', | |
179 | 'id': 'deniz-yildizi', | |
6de82b44 | 180 | }, |
8fd2a7be S |
181 | 'playlist_mincount': 205, |
182 | }, { | |
183 | # a film detail page which is using same url with serie page | |
184 | 'url': 'https://puhutv.com/kaybedenler-kulubu-detay', | |
185 | 'only_matching': True, | |
186 | }] | |
187 | ||
188 | def _extract_entries(self, seasons): | |
6de82b44 | 189 | for season in seasons: |
8fd2a7be S |
190 | season_id = season.get('id') |
191 | if not season_id: | |
192 | continue | |
193 | page = 1 | |
6de82b44 E |
194 | has_more = True |
195 | while has_more is True: | |
8fd2a7be | 196 | season = self._download_json( |
add96eb9 | 197 | f'https://galadriel.puhutv.com/seasons/{season_id}', |
198 | season_id, f'Downloading page {page}', query={ | |
8fd2a7be | 199 | 'page': page, |
6de82b44 E |
200 | 'per': 40, |
201 | }) | |
8fd2a7be S |
202 | episodes = season.get('episodes') |
203 | if isinstance(episodes, list): | |
204 | for ep in episodes: | |
205 | slug_path = str_or_none(ep.get('slugPath')) | |
206 | if not slug_path: | |
207 | continue | |
208 | video_id = str_or_none(int_or_none(ep.get('id'))) | |
209 | yield self.url_result( | |
add96eb9 | 210 | f'https://puhutv.com/{slug_path}', |
8fd2a7be S |
211 | ie=PuhuTVIE.ie_key(), video_id=video_id, |
212 | video_title=ep.get('name') or ep.get('eventLabel')) | |
213 | page += 1 | |
214 | has_more = season.get('hasMore') | |
6de82b44 E |
215 | |
216 | def _real_extract(self, url): | |
217 | playlist_id = self._match_id(url) | |
218 | ||
219 | info = self._download_json( | |
add96eb9 | 220 | urljoin(url, f'/api/slug/{playlist_id}-detay'), |
8fd2a7be | 221 | playlist_id)['data'] |
6de82b44 | 222 | |
6de82b44 E |
223 | seasons = info.get('seasons') |
224 | if seasons: | |
8fd2a7be S |
225 | return self.playlist_result( |
226 | self._extract_entries(seasons), playlist_id, info.get('name')) | |
227 | ||
228 | # For films, these are using same url with series | |
229 | video_id = info.get('slug') or info['assets'][0]['slug'] | |
230 | return self.url_result( | |
add96eb9 | 231 | f'https://puhutv.com/{video_id}-izle', |
8fd2a7be | 232 | PuhuTVIE.ie_key(), video_id) |