]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/wat.py
2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
15 class WatIE(InfoExtractor
):
16 _VALID_URL
= r
'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html'
19 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
20 'md5': 'ce70e9223945ed26a8056d413ca55dc9',
23 'display_id': 'soupe-figues-l-orange-aux-epices',
25 'title': 'Soupe de figues à l\'orange et aux épices',
26 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
27 'upload_date': '20140819',
32 def download_video_info(self
, real_id
):
33 # 'contentv4' is used in the website, but it also returns the related
34 # videos, we don't need them
35 info
= self
._download
_json
('http://www.wat.tv/interface/contentv3/' + real_id
, real_id
)
38 def _real_extract(self
, url
):
39 def real_id_for_chapter(chapter
):
40 return chapter
['tc_start'].split('-')[0]
41 mobj
= re
.match(self
._VALID
_URL
, url
)
42 short_id
= mobj
.group('short_id')
43 display_id
= mobj
.group('display_id')
44 webpage
= self
._download
_webpage
(url
, display_id
or short_id
)
45 real_id
= self
._search
_regex
(r
'xtpage = ".*-(.*?)";', webpage
, 'real id')
47 video_info
= self
.download_video_info(real_id
)
49 if video_info
.get('geolock'):
50 raise ExtractorError('This content is not available in your area', expected
=True)
52 chapters
= video_info
['chapters']
53 first_chapter
= chapters
[0]
54 files
= video_info
['files']
57 if real_id_for_chapter(first_chapter
) != real_id
:
58 self
.to_screen('Multipart video detected')
60 for chapter
in chapters
:
61 chapter_id
= real_id_for_chapter(chapter
)
62 # Yes, when we this chapter is processed by WatIE,
63 # it will download the info again
64 chapter_info
= self
.download_video_info(chapter_id
)
65 chapter_urls
.append(chapter_info
['url'])
66 entries
= [self
.url_result(chapter_url
) for chapter_url
in chapter_urls
]
67 return self
.playlist_result(entries
, real_id
, video_info
['title'])
70 if 'date_diffusion' in first_chapter
:
71 upload_date
= unified_strdate(first_chapter
['date_diffusion'])
72 # Otherwise we can continue and extract just one part, we have to use
73 # the short id for getting the video url
76 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id
,
77 'format_id': 'Mobile',
80 fmts
= [('SD', 'web')]
81 if first_file
.get('hasHD'):
82 fmts
.append(('HD', 'webhd'))
84 def compute_token(param
):
85 timestamp
= '%08x' % int(time
.time())
86 magic
= '9b673b13fa4682ed14c3cfa5af5310274b514c4133e9b3a81e6e3aba009l2564'
87 return '%s/%s' % (hashlib
.md5((magic
+ param
+ timestamp
).encode('ascii')).hexdigest(), timestamp
)
90 webid
= '/%s/%s' % (fmt
[1], real_id
)
91 video_url
= self
._download
_webpage
(
92 'http://www.wat.tv/get%s?token=%s&getURL=1' % (webid
, compute_token(webid
)),
94 'Downloding %s video URL' % fmt
[0],
95 'Failed to download %s video URL' % fmt
[0],
107 'display_id': display_id
,
108 'title': first_chapter
['title'],
109 'thumbnail': first_chapter
['preview'],
110 'description': first_chapter
['description'],
111 'view_count': video_info
['views'],
112 'upload_date': upload_date
,
113 'duration': first_file
['duration'],