]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/imdb.py
6108ed5526ba37f2e5b8d14b604974ca3c3f8273
[youtubedl] / youtube_dl / extractor / imdb.py
1 from __future__ import unicode_literals
2
3 import re
4 import json
5
6 from .common import InfoExtractor
7 from ..utils import (
8 compat_urlparse,
9 )
10
11
12 class ImdbIE(InfoExtractor):
13 IE_NAME = 'imdb'
14 IE_DESC = 'Internet Movie Database trailers'
15 _VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
16
17 _TEST = {
18 'url': 'http://www.imdb.com/video/imdb/vi2524815897',
19 'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
20 'info_dict': {
21 'id': '2524815897',
22 'ext': 'mp4',
23 'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
24 'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
25 }
26 }
27
28 def _real_extract(self, url):
29 video_id = self._match_id(url)
30 webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
31 descr = self._html_search_regex(
32 r'(?s)<span itemprop="description">(.*?)</span>',
33 webpage, 'description', fatal=False)
34 available_formats = re.findall(
35 r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
36 flags=re.MULTILINE)
37 formats = []
38 for f_id, f_path in available_formats:
39 f_path = f_path.strip()
40 format_page = self._download_webpage(
41 compat_urlparse.urljoin(url, f_path),
42 'Downloading info for %s format' % f_id)
43 json_data = self._search_regex(
44 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
45 format_page, 'json data', flags=re.DOTALL)
46 info = json.loads(json_data)
47 format_info = info['videoPlayerObject']['video']
48 formats.append({
49 'format_id': f_id,
50 'url': format_info['url'],
51 })
52
53 return {
54 'id': video_id,
55 'title': self._og_search_title(webpage),
56 'formats': formats,
57 'description': descr,
58 'thumbnail': format_info['slate'],
59 }
60
61
62 class ImdbListIE(InfoExtractor):
63 IE_NAME = 'imdb:list'
64 IE_DESC = 'Internet Movie Database lists'
65 _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
66 _TEST = {
67 'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
68 'info_dict': {
69 'id': 'JFs9NWw6XI0',
70 'title': 'March 23, 2012 Releases',
71 },
72 'playlist_count': 7,
73 }
74
75 def _real_extract(self, url):
76 list_id = self._match_id(url)
77 webpage = self._download_webpage(url, list_id)
78 entries = [
79 self.url_result('http://www.imdb.com' + m, 'Imdb')
80 for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
81
82 list_title = self._html_search_regex(
83 r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
84
85 return self.playlist_result(entries, list_id, list_title)