]>
Commit | Line | Data |
---|---|---|
ecfef3e5 PH |
1 | from __future__ import unicode_literals |
2 | ||
d8d61486 | 3 | import re |
d8d61486 JMF |
4 | |
5 | from .common import InfoExtractor | |
dd67702a | 6 | from ..utils import ( |
96c2e3e9 | 7 | mimetype2ext, |
dd67702a | 8 | qualities, |
5b9d187c | 9 | remove_end, |
d8d61486 JMF |
10 | ) |
11 | ||
12 | ||
13 | class ImdbIE(InfoExtractor): | |
ecfef3e5 PH |
14 | IE_NAME = 'imdb' |
15 | IE_DESC = 'Internet Movie Database trailers' | |
4c93ee8d | 16 | _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-)vi(?P<id>\d+)' |
d8d61486 | 17 | |
f196508f | 18 | _TESTS = [{ |
ecfef3e5 | 19 | 'url': 'http://www.imdb.com/video/imdb/vi2524815897', |
ecfef3e5 PH |
20 | 'info_dict': { |
21 | 'id': '2524815897', | |
22 | 'ext': 'mp4', | |
5b9d187c | 23 | 'title': 'Ice Age: Continental Drift Trailer (No. 2)', |
ecfef3e5 | 24 | 'description': 'md5:9061c2219254e5d14e03c25c98e96a81', |
d8d61486 | 25 | } |
f196508f S |
26 | }, { |
27 | 'url': 'http://www.imdb.com/video/_/vi2524815897', | |
28 | 'only_matching': True, | |
4c93ee8d S |
29 | }, { |
30 | 'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897', | |
31 | 'only_matching': True, | |
32 | }, { | |
33 | 'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897', | |
34 | 'only_matching': True, | |
f196508f | 35 | }] |
d8d61486 JMF |
36 | |
37 | def _real_extract(self, url): | |
11fba175 | 38 | video_id = self._match_id(url) |
97e302a4 | 39 | webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id) |
11fba175 PH |
40 | descr = self._html_search_regex( |
41 | r'(?s)<span itemprop="description">(.*?)</span>', | |
42 | webpage, 'description', fatal=False) | |
dd67702a JMF |
43 | player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id |
44 | player_page = self._download_webpage( | |
45 | player_url, video_id, 'Downloading player page') | |
46 | # the player page contains the info for the default format, we have to | |
47 | # fetch other pages for the rest of the formats | |
48 | extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page) | |
49 | format_pages = [ | |
50 | self._download_webpage( | |
51 | f_url, video_id, 'Downloading info for %s format' % f_name) | |
52 | for f_url, f_name in extra_formats] | |
53 | format_pages.append(player_page) | |
54 | ||
f7f2e53a | 55 | quality = qualities(('SD', '480p', '720p', '1080p')) |
d8d61486 | 56 | formats = [] |
dd67702a | 57 | for format_page in format_pages: |
b03d0d06 JMF |
58 | json_data = self._search_regex( |
59 | r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>', | |
ecfef3e5 | 60 | format_page, 'json data', flags=re.DOTALL) |
96c2e3e9 S |
61 | info = self._parse_json(json_data, video_id, fatal=False) |
62 | if not info: | |
63 | continue | |
64 | format_info = info.get('videoPlayerObject', {}).get('video', {}) | |
65 | if not format_info: | |
66 | continue | |
67 | video_info_list = format_info.get('videoInfoList') | |
68 | if not video_info_list or not isinstance(video_info_list, list): | |
69 | continue | |
70 | video_info = video_info_list[0] | |
71 | if not video_info or not isinstance(video_info, dict): | |
72 | continue | |
73 | video_url = video_info.get('videoUrl') | |
74 | if not video_url: | |
75 | continue | |
76 | format_id = format_info.get('ffname') | |
d8d61486 | 77 | formats.append({ |
96c2e3e9 S |
78 | 'format_id': format_id, |
79 | 'url': video_url, | |
80 | 'ext': mimetype2ext(video_info.get('videoMimeType')), | |
81 | 'quality': quality(format_id), | |
d8d61486 | 82 | }) |
dd67702a | 83 | self._sort_formats(formats) |
d8d61486 JMF |
84 | |
85 | return { | |
86 | 'id': video_id, | |
5b9d187c | 87 | 'title': remove_end(self._og_search_title(webpage), ' - IMDb'), |
d8d61486 JMF |
88 | 'formats': formats, |
89 | 'description': descr, | |
5b9d187c | 90 | 'thumbnail': format_info.get('slate'), |
d8d61486 | 91 | } |
c645c765 | 92 | |
ecfef3e5 | 93 | |
c645c765 | 94 | class ImdbListIE(InfoExtractor): |
ecfef3e5 PH |
95 | IE_NAME = 'imdb:list' |
96 | IE_DESC = 'Internet Movie Database lists' | |
5886b38d | 97 | _VALID_URL = r'https?://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})' |
22a6f150 PH |
98 | _TEST = { |
99 | 'url': 'http://www.imdb.com/list/JFs9NWw6XI0', | |
100 | 'info_dict': { | |
101 | 'id': 'JFs9NWw6XI0', | |
102 | 'title': 'March 23, 2012 Releases', | |
103 | }, | |
104 | 'playlist_count': 7, | |
105 | } | |
5f6a1245 | 106 | |
c645c765 | 107 | def _real_extract(self, url): |
11fba175 | 108 | list_id = self._match_id(url) |
d7b51547 | 109 | webpage = self._download_webpage(url, list_id) |
d7b51547 PH |
110 | entries = [ |
111 | self.url_result('http://www.imdb.com' + m, 'Imdb') | |
a3978a61 | 112 | for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)] |
d7b51547 PH |
113 | |
114 | list_title = self._html_search_regex( | |
115 | r'<h1 class="header">(.*?)</h1>', webpage, 'list title') | |
116 | ||
ecfef3e5 | 117 | return self.playlist_result(entries, list_id, list_title) |