]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/puhutv.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
22 class PuhuTVIE(InfoExtractor
):
23 _VALID_URL
= r
'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-izle'
27 'url': 'https://puhutv.com/sut-kardesler-izle',
28 'md5': 'fbd8f2d8e7681f8bcd51b592475a6ae7',
31 'display_id': 'sut-kardesler',
33 'title': 'Süt Kardeşler',
34 'description': 'md5:405fd024df916ca16731114eb18e511a',
35 'thumbnail': r
're:^https?://.*\.jpg$',
37 'creator': 'Arzu Film',
38 'timestamp': 1469778212,
39 'upload_date': '20160729',
42 'tags': ['Aile', 'Komedi', 'Klasikler'],
45 # episode, geo restricted, bypassable with --geo-verification-proxy
46 'url': 'https://puhutv.com/jet-sosyete-1-bolum-izle',
47 'only_matching': True,
50 'url': 'https://puhutv.com/dip-1-bolum-izle',
51 'only_matching': True,
59 def _real_extract(self
, url
):
60 display_id
= self
._match
_id
(url
)
62 info
= self
._download
_json
(
63 urljoin(url
, '/api/slug/%s-izle' % display_id
),
66 video_id
= compat_str(info
['id'])
67 title
= info
.get('name') or info
['title']['name']
68 if info
.get('display_name'):
69 title
= '%s %s' % (title
, info
.get('display_name'))
72 videos
= self
._download
_json
(
73 'https://puhutv.com/api/assets/%s/videos' % video_id
,
74 display_id
, 'Downloading video JSON',
75 headers
=self
.geo_verification_headers())
76 except ExtractorError
as e
:
77 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 403:
78 self
.raise_geo_restricted()
82 for video
in videos
['data']['videos']:
83 media_url
= url_or_none(video
.get('url'))
86 playlist
= video
.get('is_playlist')
87 if video
.get('stream_type') == 'hls' and playlist
is True:
88 formats
.extend(self
._extract
_m
3u8_formats
(
89 media_url
, video_id
, 'mp4', entry_protocol
='m3u8_native',
90 m3u8_id
='hls', fatal
=False))
92 quality
= int_or_none(video
.get('quality'))
98 video_format
= video
.get('video_format')
99 if video_format
== 'hls' and playlist
is False:
101 f
['protocol'] = 'm3u8_native'
102 elif video_format
== 'mp4':
108 format_id
+= '-%sp' % quality
109 f
['format_id'] = format_id
111 self
._sort
_formats
(formats
)
113 description
= try_get(
114 info
, lambda x
: x
['title']['description'],
115 compat_str
) or info
.get('description')
116 timestamp
= unified_timestamp(info
.get('created_at'))
118 info
, lambda x
: x
['title']['producer']['name'], compat_str
)
120 duration
= float_or_none(
121 try_get(info
, lambda x
: x
['content']['duration_in_ms'], int),
123 view_count
= try_get(info
, lambda x
: x
['content']['watch_count'], int)
126 info
, lambda x
: x
['content']['images']['wide'], dict) or {}
128 for image_id
, image_url
in images
.items():
129 if not isinstance(image_url
, compat_str
):
131 if not image_url
.startswith(('http', '//')):
132 image_url
= 'https://%s' % image_url
133 t
= parse_resolution(image_id
)
140 release_year
= try_get(info
, lambda x
: x
['title']['released_at'], int)
142 season_number
= int_or_none(info
.get('season_number'))
143 season_id
= str_or_none(info
.get('season_id'))
144 episode_number
= int_or_none(info
.get('episode_number'))
147 for genre
in try_get(info
, lambda x
: x
['title']['genres'], list) or []:
148 if not isinstance(genre
, dict):
150 genre_name
= genre
.get('name')
151 if genre_name
and isinstance(genre_name
, compat_str
):
152 tags
.append(genre_name
)
155 for subtitle
in try_get(
156 info
, lambda x
: x
['content']['subtitles'], list) or []:
157 if not isinstance(subtitle
, dict):
159 lang
= subtitle
.get('language')
160 sub_url
= url_or_none(subtitle
.get('url'))
161 if not lang
or not isinstance(lang
, compat_str
) or not sub_url
:
163 subtitles
[self
._SUBTITLE
_LANGS
.get(lang
, lang
)] = [{
169 'display_id': display_id
,
171 'description': description
,
172 'season_id': season_id
,
173 'season_number': season_number
,
174 'episode_number': episode_number
,
175 'release_year': release_year
,
176 'timestamp': timestamp
,
178 'view_count': view_count
,
179 'duration': duration
,
181 'subtitles': subtitles
,
182 'thumbnails': thumbnails
,
187 class PuhuTVSerieIE(InfoExtractor
):
188 _VALID_URL
= r
'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-detay'
189 IE_NAME
= 'puhutv:serie'
191 'url': 'https://puhutv.com/deniz-yildizi-detay',
193 'title': 'Deniz Yıldızı',
194 'id': 'deniz-yildizi',
196 'playlist_mincount': 205,
198 # a film detail page which is using same url with serie page
199 'url': 'https://puhutv.com/kaybedenler-kulubu-detay',
200 'only_matching': True,
203 def _extract_entries(self
, seasons
):
204 for season
in seasons
:
205 season_id
= season
.get('id')
210 while has_more
is True:
211 season
= self
._download
_json
(
212 'https://galadriel.puhutv.com/seasons/%s' % season_id
,
213 season_id
, 'Downloading page %s' % page
, query
={
217 episodes
= season
.get('episodes')
218 if isinstance(episodes
, list):
220 slug_path
= str_or_none(ep
.get('slugPath'))
223 video_id
= str_or_none(int_or_none(ep
.get('id')))
224 yield self
.url_result(
225 'https://puhutv.com/%s' % slug_path
,
226 ie
=PuhuTVIE
.ie_key(), video_id
=video_id
,
227 video_title
=ep
.get('name') or ep
.get('eventLabel'))
229 has_more
= season
.get('hasMore')
231 def _real_extract(self
, url
):
232 playlist_id
= self
._match
_id
(url
)
234 info
= self
._download
_json
(
235 urljoin(url
, '/api/slug/%s-detay' % playlist_id
),
238 seasons
= info
.get('seasons')
240 return self
.playlist_result(
241 self
._extract
_entries
(seasons
), playlist_id
, info
.get('name'))
243 # For films, these are using same url with series
244 video_id
= info
.get('slug') or info
['assets'][0]['slug']
245 return self
.url_result(
246 'https://puhutv.com/%s-izle' % video_id
,
247 PuhuTVIE
.ie_key(), video_id
)