2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
5 from ..compat
import compat_str
14 class WatIE(InfoExtractor
):
15 _VALID_URL
= r
'(?:wat:|https?://(?:www\.)?wat\.tv/video/.*-)(?P<id>[0-9a-z]+)'
19 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
23 'title': 'Soupe de figues à l\'orange et aux épices',
24 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
25 'upload_date': '20140819',
30 'skip_download': True,
32 'expected_warnings': ['HTTP Error 404'],
33 'skip': 'This content is no longer available',
36 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
37 'md5': 'b16574df2c3cd1a36ca0098f2a791925',
41 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
42 'upload_date': '20140816',
44 'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."],
45 'skip': 'This content is no longer available',
50 def _real_extract(self
, url
):
51 video_id
= self
._match
_id
(url
)
52 video_id
= video_id
if video_id
.isdigit() and len(video_id
) > 6 else compat_str(int(video_id
, 36))
54 # 'contentv4' is used in the website, but it also returns the related
55 # videos, we don't need them
56 # video_data = self._download_json(
57 # 'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
58 video_data
= self
._download
_json
(
59 'https://mediainfo.tf1.fr/mediainfocombo/' + video_id
,
60 video_id
, query
={'context': 'MYTF1'}
)
61 video_info
= video_data
['media']
63 error_desc
= video_info
.get('error_desc')
65 if video_info
.get('error_code') == 'GEOBLOCKED':
66 self
.raise_geo_restricted(error_desc
, video_info
.get('geoList'))
67 raise ExtractorError(error_desc
, expected
=True)
69 title
= video_info
['title']
74 def extract_formats(manifest_urls
):
75 for f
, f_url
in manifest_urls
.items():
78 if f
in ('dash', 'mpd'):
79 fmts
, subs
= self
._extract
_mpd
_formats
_and
_subtitles
(
80 f_url
.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
81 video_id
, mpd_id
='dash', fatal
=False)
83 fmts
, subs
= self
._extract
_m
3u8_formats
_and
_subtitles
(
84 f_url
, video_id
, 'mp4',
85 'm3u8_native', m3u8_id
='hls', fatal
=False)
89 self
._merge
_subtitles
(subs
, target
=subtitles
)
91 delivery
= video_data
.get('delivery') or {}
92 extract_formats({delivery.get('format'): delivery.get('url')}
)
94 if delivery
.get('drm'):
95 self
.raise_no_formats('This video is DRM protected.', expected
=True)
96 manifest_urls
= self
._download
_json
(
97 'http://www.wat.tv/get/webhtml/' + video_id
, video_id
, fatal
=False)
99 extract_formats(manifest_urls
)
101 self
._sort
_formats
(formats
)
106 'thumbnail': video_info
.get('preview'),
107 'upload_date': unified_strdate(try_get(
108 video_data
, lambda x
: x
['mediametrie']['chapters'][0]['estatS4'])),
109 'duration': int_or_none(video_info
.get('duration')),
111 'subtitles': subtitles
,