1 from __future__ import unicode_literals
6 from .common import InfoExtractor
12 class ImdbIE(InfoExtractor):
14 IE_DESC = 'Internet Movie Database trailers'
15 _VALID_URL = r'https?://(?:www|m)\.imdb\.com/video/[^/]+/vi(?P<id>\d+)'
18 'url': 'http://www.imdb.com/video/imdb/vi2524815897',
22 'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
23 'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
26 'url': 'http://www.imdb.com/video/_/vi2524815897',
27 'only_matching': True,
30 def _real_extract(self, url):
31 video_id = self._match_id(url)
32 webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
33 descr = self._html_search_regex(
34 r'(?s)<span itemprop="description">(.*?)</span>',
35 webpage, 'description', fatal=False)
36 player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
37 player_page = self._download_webpage(
38 player_url, video_id, 'Downloading player page')
39 # the player page contains the info for the default format, we have to
40 # fetch other pages for the rest of the formats
41 extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
43 self._download_webpage(
44 f_url, video_id, 'Downloading info for %s format' % f_name)
45 for f_url, f_name in extra_formats]
46 format_pages.append(player_page)
48 quality = qualities(('SD', '480p', '720p', '1080p'))
50 for format_page in format_pages:
51 json_data = self._search_regex(
52 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
53 format_page, 'json data', flags=re.DOTALL)
54 info = json.loads(json_data)
55 format_info = info['videoPlayerObject']['video']
56 f_id = format_info['ffname']
59 'url': format_info['videoInfoList'][0]['videoUrl'],
60 'quality': quality(f_id),
62 self._sort_formats(formats)
66 'title': self._og_search_title(webpage),
69 'thumbnail': format_info['slate'],
73 class ImdbListIE(InfoExtractor):
75 IE_DESC = 'Internet Movie Database lists'
76 _VALID_URL = r'https?://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
78 'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
81 'title': 'March 23, 2012 Releases',
86 def _real_extract(self, url):
87 list_id = self._match_id(url)
88 webpage = self._download_webpage(url, list_id)
90 self.url_result('http://www.imdb.com' + m, 'Imdb')
91 for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
93 list_title = self._html_search_regex(
94 r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
96 return self.playlist_result(entries, list_id, list_title)