]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tv5mondeplus.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
16 class TV5MondePlusIE(InfoExtractor
):
18 _VALID_URL
= r
'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
20 'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
21 'md5': '12130fc199f020673138a83466542ec6',
23 'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
25 'title': 'Tdah, mon amour - Enfants',
26 'description': 'md5:230e3aca23115afcf8006d1bece6df74',
27 'upload_date': '20170401',
28 'timestamp': 1491022860,
33 def _real_extract(self
, url
):
34 display_id
= self
._match
_id
(url
)
35 webpage
= self
._download
_webpage
(url
, display_id
)
37 if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage
:
38 self
.raise_geo_restricted(countries
=['FR'])
40 series
= get_element_by_class('video-detail__title', webpage
)
41 title
= episode
= get_element_by_class(
42 'video-detail__subtitle', webpage
) or series
43 if series
and series
!= title
:
44 title
= '%s - %s' % (series
, title
)
45 vpl_data
= extract_attributes(self
._search
_regex
(
46 r
'(<[^>]+class="video_player_loader"[^>]+>)',
47 webpage
, 'video player loader'))
49 video_files
= self
._parse
_json
(
50 vpl_data
['data-broadcast'], display_id
).get('files', [])
52 for video_file
in video_files
:
53 v_url
= video_file
.get('url')
56 video_format
= video_file
.get('format') or determine_ext(v_url
)
57 if video_format
== 'm3u8':
58 formats
.extend(self
._extract
_m
3u8_formats
(
59 v_url
, display_id
, 'mp4', 'm3u8_native',
60 m3u8_id
='hls', fatal
=False))
64 'format_id': video_format
,
66 self
._sort
_formats
(formats
)
70 'display_id': display_id
,
72 'description': clean_html(get_element_by_class('video-detail__description', webpage
)),
73 'thumbnail': vpl_data
.get('data-image'),
74 'duration': int_or_none(vpl_data
.get('data-duration')) or parse_duration(self
._html
_search
_meta
('duration', webpage
)),
75 'timestamp': parse_iso8601(self
._html
_search
_meta
('uploadDate', webpage
)),