]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/franceculture.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
11 class FranceCultureIE(InfoExtractor
):
12 _VALID_URL
= r
'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
14 'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
16 'id': 'rendez-vous-au-pays-des-geeks',
17 'display_id': 'rendez-vous-au-pays-des-geeks',
19 'title': 'Rendez-vous au pays des geeks',
20 'thumbnail': 're:^https?://.*\\.jpg$',
21 'upload_date': '20140301',
26 def _real_extract(self
, url
):
27 display_id
= self
._match
_id
(url
)
29 webpage
= self
._download
_webpage
(url
, display_id
)
31 video_url
= self
._search
_regex
(
32 r
'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<button[^>]+data-asset-source="([^"]+)"',
33 webpage
, 'video path')
35 title
= self
._og
_search
_title
(webpage
)
37 upload_date
= unified_strdate(self
._search
_regex
(
38 '(?s)<div[^>]+class="date"[^>]*>.*?<span[^>]+class="inner"[^>]*>([^<]+)<',
39 webpage
, 'upload date', fatal
=False))
40 thumbnail
= self
._search
_regex
(
41 r
'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-dejavu-src="([^"]+)"',
42 webpage
, 'thumbnail', fatal
=False)
43 uploader
= self
._html
_search
_regex
(
44 r
'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
45 webpage
, 'uploader', default
=None)
46 vcodec
= 'none' if determine_ext(video_url
.lower()) == 'mp3' else None
50 'display_id': display_id
,
53 'thumbnail': thumbnail
,
56 'upload_date': upload_date
,