]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/zapiks.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
16 class ZapiksIE(InfoExtractor
):
17 _VALID_URL
= r
'https?://(?:www\.)?zapiks\.(?:fr|com)/(?:(?:[a-z]{2}/)?(?P<display_id>.+?)\.html|index\.php\?.*\bmedia_id=(?P<id>\d+))'
20 'url': 'http://www.zapiks.fr/ep2s3-bon-appetit-eh-be-viva.html',
21 'md5': 'aeb3c473b2d564b2d46d664d28d5f050',
25 'title': 'EP2S3 - Bon Appétit - Eh bé viva les pyrénées con!',
26 'description': 'md5:7054d6f6f620c6519be1fe710d4da847',
27 'thumbnail': r
're:^https?://.*\.jpg$',
29 'timestamp': 1359044972,
30 'upload_date': '20130124',
36 'url': 'http://www.zapiks.com/ep3s5-bon-appetit-baqueira-m-1.html',
37 'only_matching': True,
40 'url': 'http://www.zapiks.com/nl/ep3s5-bon-appetit-baqueira-m-1.html',
41 'only_matching': True,
44 'url': 'http://www.zapiks.fr/index.php?action=playerIframe&media_id=118046&width=640&height=360&autoStart=false&language=fr',
45 'only_matching': True,
49 def _real_extract(self
, url
):
50 mobj
= re
.match(self
._VALID
_URL
, url
)
51 video_id
= mobj
.group('id')
52 display_id
= mobj
.group('display_id') or video_id
54 webpage
= self
._download
_webpage
(url
, display_id
)
57 video_id
= self
._search
_regex
(
58 r
'data-media-id="(\d+)"', webpage
, 'video id')
60 playlist
= self
._download
_xml
(
61 'http://www.zapiks.fr/view/index.php?action=playlist&media_id=%s&lang=en' % video_id
,
65 'jwplayer': 'http://rss.jwpcdn.com/'
69 return xpath_with_ns(path
, NS_MAP
)
71 item
= playlist
.find('./channel/item')
73 title
= xpath_text(item
, 'title', 'title') or self
._og
_search
_title
(webpage
)
74 description
= self
._og
_search
_description
(webpage
, default
=None)
75 thumbnail
= xpath_text(
76 item
, ns('./jwplayer:image'), 'thumbnail') or self
._og
_search
_thumbnail
(webpage
, default
=None)
77 duration
= parse_duration(self
._html
_search
_meta
(
78 'duration', webpage
, 'duration', default
=None))
79 timestamp
= parse_iso8601(self
._html
_search
_meta
(
80 'uploadDate', webpage
, 'upload date', default
=None), ' ')
82 view_count
= int_or_none(self
._search
_regex
(
83 r
'UserPlays:(\d+)', webpage
, 'view count', default
=None))
84 comment_count
= int_or_none(self
._search
_regex
(
85 r
'UserComments:(\d+)', webpage
, 'comment count', default
=None))
88 for source
in item
.findall(ns('./jwplayer:source')):
89 format_id
= source
.attrib
['label']
91 'url': source
.attrib
['file'],
92 'format_id': format_id
,
94 m
= re
.search(r
'^(?P<height>\d+)[pP]', format_id
)
96 f
['height'] = int(m
.group('height'))
98 self
._sort
_formats
(formats
)
103 'description': description
,
104 'thumbnail': thumbnail
,
105 'duration': duration
,
106 'timestamp': timestamp
,
107 'view_count': view_count
,
108 'comment_count': comment_count
,