]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/imdb.py
debian/patches: Refresh patches to apply cleanly.
[youtubedl] / youtube_dl / extractor / imdb.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 determine_ext,
8 mimetype2ext,
9 parse_duration,
10 qualities,
11 url_or_none,
12 )
13
14
15 class ImdbIE(InfoExtractor):
16 IE_NAME = 'imdb'
17 IE_DESC = 'Internet Movie Database trailers'
18 _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).+?[/-]vi(?P<id>\d+)'
19
20 _TESTS = [{
21 'url': 'http://www.imdb.com/video/imdb/vi2524815897',
22 'info_dict': {
23 'id': '2524815897',
24 'ext': 'mp4',
25 'title': 'No. 2 from Ice Age: Continental Drift (2012)',
26 'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
27 }
28 }, {
29 'url': 'http://www.imdb.com/video/_/vi2524815897',
30 'only_matching': True,
31 }, {
32 'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
33 'only_matching': True,
34 }, {
35 'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
36 'only_matching': True,
37 }, {
38 'url': 'http://www.imdb.com/videoplayer/vi1562949145',
39 'only_matching': True,
40 }, {
41 'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
42 'only_matching': True,
43 }, {
44 'url': 'https://www.imdb.com/list/ls009921623/videoplayer/vi260482329',
45 'only_matching': True,
46 }]
47
48 def _real_extract(self, url):
49 video_id = self._match_id(url)
50 webpage = self._download_webpage(
51 'https://www.imdb.com/videoplayer/vi' + video_id, video_id)
52 video_metadata = self._parse_json(self._search_regex(
53 r'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage,
54 'video metadata'), video_id)['videos']['videoMetadata']['vi' + video_id]
55 title = self._html_search_meta(
56 ['og:title', 'twitter:title'], webpage) or self._html_search_regex(
57 r'<title>(.+?)</title>', webpage, 'title', fatal=False) or video_metadata['title']
58
59 quality = qualities(('SD', '480p', '720p', '1080p'))
60 formats = []
61 for encoding in video_metadata.get('encodings', []):
62 if not encoding or not isinstance(encoding, dict):
63 continue
64 video_url = url_or_none(encoding.get('videoUrl'))
65 if not video_url:
66 continue
67 ext = mimetype2ext(encoding.get(
68 'mimeType')) or determine_ext(video_url)
69 if ext == 'm3u8':
70 formats.extend(self._extract_m3u8_formats(
71 video_url, video_id, 'mp4', entry_protocol='m3u8_native',
72 m3u8_id='hls', fatal=False))
73 continue
74 format_id = encoding.get('definition')
75 formats.append({
76 'format_id': format_id,
77 'url': video_url,
78 'ext': ext,
79 'quality': quality(format_id),
80 })
81 self._sort_formats(formats)
82
83 return {
84 'id': video_id,
85 'title': title,
86 'formats': formats,
87 'description': video_metadata.get('description'),
88 'thumbnail': video_metadata.get('slate', {}).get('url'),
89 'duration': parse_duration(video_metadata.get('duration')),
90 }
91
92
93 class ImdbListIE(InfoExtractor):
94 IE_NAME = 'imdb:list'
95 IE_DESC = 'Internet Movie Database lists'
96 _VALID_URL = r'https?://(?:www\.)?imdb\.com/list/ls(?P<id>\d{9})(?!/videoplayer/vi\d+)'
97 _TEST = {
98 'url': 'https://www.imdb.com/list/ls009921623/',
99 'info_dict': {
100 'id': '009921623',
101 'title': 'The Bourne Legacy',
102 'description': 'A list of trailers, clips, and more from The Bourne Legacy, starring Jeremy Renner and Rachel Weisz.',
103 },
104 'playlist_count': 8,
105 }
106
107 def _real_extract(self, url):
108 list_id = self._match_id(url)
109 webpage = self._download_webpage(url, list_id)
110 entries = [
111 self.url_result('http://www.imdb.com' + m, 'Imdb')
112 for m in re.findall(r'href="(/list/ls%s/videoplayer/vi[^"]+)"' % list_id, webpage)]
113
114 list_title = self._html_search_regex(
115 r'<h1[^>]+class="[^"]*header[^"]*"[^>]*>(.*?)</h1>',
116 webpage, 'list title')
117 list_description = self._html_search_regex(
118 r'<div[^>]+class="[^"]*list-description[^"]*"[^>]*><p>(.*?)</p>',
119 webpage, 'list description')
120
121 return self.playlist_result(entries, list_id, list_title, list_description)