]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/imdb.py
d/p/remove-autoupdate-mechanism.patch: Update patch with metadata at the top.
[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 mimetype2ext,
8 qualities,
9 remove_end,
10 )
11
12
13 class ImdbIE(InfoExtractor):
14 IE_NAME = 'imdb'
15 IE_DESC = 'Internet Movie Database trailers'
16 _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title).+?[/-]vi(?P<id>\d+)'
17
18 _TESTS = [{
19 'url': 'http://www.imdb.com/video/imdb/vi2524815897',
20 'info_dict': {
21 'id': '2524815897',
22 'ext': 'mp4',
23 'title': 'Ice Age: Continental Drift Trailer (No. 2)',
24 'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
25 }
26 }, {
27 'url': 'http://www.imdb.com/video/_/vi2524815897',
28 'only_matching': True,
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,
35 }, {
36 'url': 'http://www.imdb.com/videoplayer/vi1562949145',
37 'only_matching': True,
38 }, {
39 'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
40 'only_matching': True,
41 }]
42
43 def _real_extract(self, url):
44 video_id = self._match_id(url)
45 webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
46 descr = self._html_search_regex(
47 r'(?s)<span itemprop="description">(.*?)</span>',
48 webpage, 'description', fatal=False)
49 player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
50 player_page = self._download_webpage(
51 player_url, video_id, 'Downloading player page')
52 # the player page contains the info for the default format, we have to
53 # fetch other pages for the rest of the formats
54 extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
55 format_pages = [
56 self._download_webpage(
57 f_url, video_id, 'Downloading info for %s format' % f_name)
58 for f_url, f_name in extra_formats]
59 format_pages.append(player_page)
60
61 quality = qualities(('SD', '480p', '720p', '1080p'))
62 formats = []
63 for format_page in format_pages:
64 json_data = self._search_regex(
65 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
66 format_page, 'json data', flags=re.DOTALL)
67 info = self._parse_json(json_data, video_id, fatal=False)
68 if not info:
69 continue
70 format_info = info.get('videoPlayerObject', {}).get('video', {})
71 if not format_info:
72 continue
73 video_info_list = format_info.get('videoInfoList')
74 if not video_info_list or not isinstance(video_info_list, list):
75 continue
76 video_info = video_info_list[0]
77 if not video_info or not isinstance(video_info, dict):
78 continue
79 video_url = video_info.get('videoUrl')
80 if not video_url:
81 continue
82 format_id = format_info.get('ffname')
83 formats.append({
84 'format_id': format_id,
85 'url': video_url,
86 'ext': mimetype2ext(video_info.get('videoMimeType')),
87 'quality': quality(format_id),
88 })
89 self._sort_formats(formats)
90
91 return {
92 'id': video_id,
93 'title': remove_end(self._og_search_title(webpage), ' - IMDb'),
94 'formats': formats,
95 'description': descr,
96 'thumbnail': format_info.get('slate'),
97 }
98
99
100 class ImdbListIE(InfoExtractor):
101 IE_NAME = 'imdb:list'
102 IE_DESC = 'Internet Movie Database lists'
103 _VALID_URL = r'https?://(?:www\.)?imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
104 _TEST = {
105 'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
106 'info_dict': {
107 'id': 'JFs9NWw6XI0',
108 'title': 'March 23, 2012 Releases',
109 },
110 'playlist_count': 7,
111 }
112
113 def _real_extract(self, url):
114 list_id = self._match_id(url)
115 webpage = self._download_webpage(url, list_id)
116 entries = [
117 self.url_result('http://www.imdb.com' + m, 'Imdb')
118 for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
119
120 list_title = self._html_search_regex(
121 r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
122
123 return self.playlist_result(entries, list_id, list_title)