]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/appletrailers.py
ef5644aa54fe28002dc4d8c76308941c264252e3
4 from .common
import InfoExtractor
11 class AppleTrailersIE(InfoExtractor
):
12 _VALID_URL
= r
'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
14 u
"url": u
"http://trailers.apple.com/trailers/wb/manofsteel/",
17 u
"file": u
"manofsteel-trailer4.mov",
18 u
"md5": u
"d97a8e575432dbcb81b7c3acb741f8a8",
21 u
"title": u
"Trailer 4",
22 u
"upload_date": u
"20130523",
23 u
"uploader_id": u
"wb",
27 u
"file": u
"manofsteel-trailer3.mov",
28 u
"md5": u
"b8017b7131b721fb4e8d6f49e1df908c",
31 u
"title": u
"Trailer 3",
32 u
"upload_date": u
"20130417",
33 u
"uploader_id": u
"wb",
37 u
"file": u
"manofsteel-trailer.mov",
38 u
"md5": u
"d0f1e1150989b9924679b441f3404d48",
42 u
"upload_date": u
"20121212",
43 u
"uploader_id": u
"wb",
47 u
"file": u
"manofsteel-teaser.mov",
48 u
"md5": u
"5fe08795b943eb2e757fa95cb6def1cb",
52 u
"upload_date": u
"20120721",
53 u
"uploader_id": u
"wb",
59 _JSON_RE
= r
'iTunes.playURL\((.*?)\);'
61 def _real_extract(self
, url
):
62 mobj
= re
.match(self
._VALID
_URL
, url
)
63 movie
= mobj
.group('movie')
64 uploader_id
= mobj
.group('company')
66 playlist_url
= compat_urlparse
.urljoin(url
, u
'includes/playlists/itunes.inc')
68 s
= re
.sub(r
'(?s)<script[^<]*?>.*?</script>', u
'', s
)
69 s
= re
.sub(r
'<img ([^<]*?)>', r
'<img \1/>', s
)
70 # The ' in the onClick attributes are not escaped, it couldn't be parsed
71 # like: http://trailers.apple.com/trailers/wb/gravity/
73 return u
'iTunes.playURL(%s);' % m
.group(1).replace('\'', ''')
74 s
= re
.sub(self
._JSON
_RE
, _clean_json
, s
)
75 s
= u
'<html>' + s
+ u
'</html>'
77 doc
= self
._download
_xml
(playlist_url
, movie
, transform_source
=fix_html
)
80 for li
in doc
.findall('./div/ul/li'):
81 on_click
= li
.find('.//a').attrib
['onClick']
82 trailer_info_json
= self
._search
_regex
(self
._JSON
_RE
,
83 on_click
, u
'trailer info')
84 trailer_info
= json
.loads(trailer_info_json
)
85 title
= trailer_info
['title']
86 video_id
= movie
+ '-' + re
.sub(r
'[^a-zA-Z0-9]', '', title
).lower()
87 thumbnail
= li
.find('.//img').attrib
['src']
88 upload_date
= trailer_info
['posted'].replace('-', '')
90 runtime
= trailer_info
['runtime']
91 m
= re
.search(r
'(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime
)
94 duration
= 60 * int(m
.group('minutes')) + int(m
.group('seconds'))
96 first_url
= trailer_info
['url']
97 trailer_id
= first_url
.split('/')[-1].rpartition('_')[0].lower()
98 settings_json_url
= compat_urlparse
.urljoin(url
, 'includes/settings/%s.json' % trailer_id
)
99 settings_json
= self
._download
_webpage
(settings_json_url
, trailer_id
, u
'Downloading settings json')
100 settings
= json
.loads(settings_json
)
103 for format
in settings
['metadata']['sizes']:
104 # The src is a file pointing to the real video file
105 format_url
= re
.sub(r
'_(\d*p.mov)', r
'_h\1', format
['src'])
108 'ext': determine_ext(format_url
),
109 'format': format
['type'],
110 'width': format
['width'],
111 'height': int(format
['height']),
113 formats
= sorted(formats
, key
=lambda f
: (f
['height'], f
['width']))
121 'duration': duration
,
122 'thumbnail': thumbnail
,
123 'upload_date': upload_date
,
124 'uploader_id': uploader_id
,
125 'user_agent': 'QuickTime compatible (youtube-dl)',