1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
10 compat_urllib_parse_unquote
,
16 get_element_by_attribute
,
21 class MetacafeIE(InfoExtractor
):
22 _VALID_URL
= r
'https?://(?:www\.)?metacafe\.com/watch/(?P<video_id>[^/]+)/(?P<display_id>[^/?#]+)'
23 _DISCLAIMER
= 'http://www.metacafe.com/family_filter/'
24 _FILTER_POST
= 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
29 'add_ie': ['Youtube'],
30 'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',
34 'upload_date': '20090102',
35 'title': 'The Electric Company | "Short I" | PBS KIDS GO!',
36 'description': 'md5:2439a8ef6d5a70e380c22f5ad323e5a8',
41 # Normal metacafe video
43 'url': 'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
44 'md5': '6e0bca200eaad2552e6915ed6fd4d9ad',
48 'title': 'News: Stuff You Won\'t Do with Your PlayStation 4',
50 'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
52 'skip': 'Page is temporarily unavailable.',
54 # metacafe video with family filter
56 'url': 'http://www.metacafe.com/watch/2155630/adult_art_by_david_hart_156/',
57 'md5': 'b06082c5079bbdcde677a6291fbdf376',
61 'title': 'Adult Art By David Hart 156',
63 'description': 'md5:9afac8fc885252201ad14563694040fc',
66 'skip_download': True,
71 'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/',
73 'id': 'an-dVVXnuY7Jh77J',
75 'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',
76 'uploader': 'AnyClip',
77 'description': 'md5:cbef0460d31e3807f6feb4e7a5952e5b',
80 # age-restricted video
82 'url': 'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
83 'md5': '98dde7c1a35d02178e8ab7560fe8bd09',
87 'title': 'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
88 'uploader': 'Dwayne Pipe',
89 'description': 'md5:950bf4c581e2c059911fa3ffbe377e4b',
95 'url': 'http://www.metacafe.com/watch/cb-8VD4r_Zws8VP/open_this_is_face_the_nation_february_9/',
99 'title': 'Open: This is Face the Nation, February 9',
100 'description': 'md5:8a9ceec26d1f7ed6eab610834cc1a476',
102 'uploader': 'CBSI-NEW',
103 'upload_date': '20140209',
104 'timestamp': 1391959800,
108 'skip_download': True,
111 # Movieclips.com video
113 'url': 'http://www.metacafe.com/watch/mv-Wy7ZU/my_week_with_marilyn_do_you_love_me/',
117 'title': 'My Week with Marilyn - Do You Love Me?',
118 'description': 'From the movie My Week with Marilyn - Colin (Eddie Redmayne) professes his love to Marilyn (Michelle Williams) and gets her to promise to return to set and finish the movie.',
119 'uploader': 'movie_trailers',
123 'skip_download': 'requires rtmpdump',
128 def report_disclaimer(self
):
129 self
.to_screen('Retrieving disclaimer')
131 def _real_extract(self
, url
):
132 # Extract id and simplified title from URL
133 video_id
, display_id
= re
.match(self
._VALID
_URL
, url
).groups()
135 # the video may come from an external site
136 m_external
= re
.match(r
'^(\w{2})-(.*)$', video_id
)
137 if m_external
is not None:
138 prefix
, ext_id
= m_external
.groups()
139 # Check if video comes from YouTube
141 return self
.url_result('http://www.youtube.com/watch?v=%s' % ext_id
, 'Youtube')
142 # CBS videos use theplatform.com
144 return self
.url_result('theplatform:%s' % ext_id
, 'ThePlatform')
147 # Disable family filter
148 'Cookie': 'user=%s; ' % compat_urllib_parse
.quote(json
.dumps({'ffilter': False}))
151 # AnyClip videos require the flashversion cookie so that we get the link
153 if video_id
.startswith('an-'):
154 headers
['Cookie'] += 'flashVersion=0; '
156 # Retrieve video webpage to extract further information
157 webpage
= self
._download
_webpage
(url
, video_id
, headers
=headers
)
159 error
= get_element_by_attribute(
160 'class', 'notfound-page-title', webpage
)
162 raise ExtractorError(error
, expected
=True)
164 video_title
= self
._html
_search
_meta
(
165 ['og:title', 'twitter:title'], webpage
, 'title', default
=None) or self
._search
_regex
(r
'<h1>(.*?)</h1>', webpage
, 'title')
167 # Extract URL, uploader and title from webpage
168 self
.report_extraction(video_id
)
170 mobj
= re
.search(r
'(?m)&(?:media|video)URL=([^&]+)', webpage
)
172 mediaURL
= compat_urllib_parse_unquote(mobj
.group(1))
173 video_ext
= determine_ext(mediaURL
)
175 # Extract gdaKey if available
176 mobj
= re
.search(r
'(?m)&gdaKey=(.*?)&', webpage
)
180 gdaKey
= mobj
.group(1)
181 video_url
= '%s?__gda__=%s' % (mediaURL
, gdaKey
)
182 if video_url
is None:
183 mobj
= re
.search(r
'<video src="([^"]+)"', webpage
)
185 video_url
= mobj
.group(1)
187 if video_url
is None:
188 flashvars
= self
._search
_regex
(
189 r
' name="flashvars" value="(.*?)"', webpage
, 'flashvars',
192 vardict
= compat_parse_qs(flashvars
)
193 if 'mediaData' not in vardict
:
194 raise ExtractorError('Unable to extract media URL')
196 r
'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict
['mediaData'][0])
198 raise ExtractorError('Unable to extract media URL')
199 mediaURL
= mobj
.group('mediaURL').replace('\\/', '/')
200 video_url
= '%s?__gda__=%s' % (mediaURL
, mobj
.group('key'))
201 video_ext
= determine_ext(video_url
)
202 if video_url
is None:
203 player_url
= self
._search
_regex
(
204 r
"swfobject\.embedSWF\('([^']+)'",
205 webpage
, 'config URL', default
=None)
207 config_url
= self
._search
_regex
(
208 r
'config=(.+)$', player_url
, 'config URL')
209 config_doc
= self
._download
_xml
(
210 config_url
, video_id
,
211 note
='Downloading video config')
212 smil_url
= config_doc
.find('.//properties').attrib
['smil_file']
213 smil_doc
= self
._download
_xml
(
215 note
='Downloading SMIL document')
216 base_url
= smil_doc
.find('./head/meta').attrib
['base']
218 for vn
in smil_doc
.findall('.//video'):
219 br
= int(vn
.attrib
['system-bitrate'])
220 play_path
= vn
.attrib
['src']
222 'format_id': 'smil-%d' % br
,
224 'play_path': play_path
,
226 'player_url': player_url
,
227 'ext': play_path
.partition(':')[0],
229 if video_url
is None:
230 flashvars
= self
._parse
_json
(self
._search
_regex
(
231 r
'flashvars\s*=\s*({.*});', webpage
, 'flashvars',
232 default
=None), video_id
, fatal
=False)
235 for source
in flashvars
.get('sources'):
236 source_url
= source
.get('src')
239 ext
= mimetype2ext(source
.get('type')) or determine_ext(source_url
)
241 video_url
.extend(self
._extract
_m
3u8_formats
(
242 source_url
, video_id
, 'mp4',
243 'm3u8_native', m3u8_id
='hls', fatal
=False))
250 if video_url
is None:
251 raise ExtractorError('Unsupported video type')
253 description
= self
._html
_search
_meta
(
254 ['og:description', 'twitter:description', 'description'],
255 webpage
, 'title', fatal
=False)
256 thumbnail
= self
._html
_search
_meta
(
257 ['og:image', 'twitter:image'], webpage
, 'title', fatal
=False)
258 video_uploader
= self
._html
_search
_regex
(
259 r
'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
260 webpage
, 'uploader nickname', fatal
=False)
261 duration
= int_or_none(
262 self
._html
_search
_meta
('video:duration', webpage
, default
=None))
265 if re
.search(r
'(?:"contentRating":|"rating",)"restricted"', webpage
)
268 if isinstance(video_url
, list):
275 self
._sort
_formats
(formats
)
279 'display_id': display_id
,
280 'description': description
,
281 'uploader': video_uploader
,
282 'title': video_title
,
283 'thumbnail': thumbnail
,
284 'age_limit': age_limit
,
286 'duration': duration
,