]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/gamespot.py
Imported Upstream version 2014.01.17.2
[youtubedl] / youtube_dl / extractor / gamespot.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_urllib_parse,
9 compat_urlparse,
10 unescapeHTML,
11 get_meta_content,
12 )
13
14
15 class GameSpotIE(InfoExtractor):
16 _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?'
17 _TEST = {
18 "url": "http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/",
19 "file": "gs-2300-6410818.mp4",
20 "md5": "b2a30deaa8654fcccd43713a6b6a4825",
21 "info_dict": {
22 "title": "Arma 3 - Community Guide: SITREP I",
23 'description': 'Check out this video where some of the basics of Arma 3 is explained.',
24 }
25 }
26
27 def _real_extract(self, url):
28 mobj = re.match(self._VALID_URL, url)
29 page_id = mobj.group('page_id')
30 webpage = self._download_webpage(url, page_id)
31 data_video_json = self._search_regex(r'data-video=\'(.*?)\'', webpage, u'data video')
32 data_video = json.loads(unescapeHTML(data_video_json))
33
34 # Transform the manifest url to a link to the mp4 files
35 # they are used in mobile devices.
36 f4m_url = data_video['videoStreams']['f4m_stream']
37 f4m_path = compat_urlparse.urlparse(f4m_url).path
38 QUALITIES_RE = r'((,\d+)+,?)'
39 qualities = self._search_regex(QUALITIES_RE, f4m_path, u'qualities').strip(',').split(',')
40 http_path = f4m_path[1:].split('/', 1)[1]
41 http_template = re.sub(QUALITIES_RE, r'%s', http_path)
42 http_template = http_template.replace('.csmil/manifest.f4m', '')
43 http_template = compat_urlparse.urljoin('http://video.gamespotcdn.com/', http_template)
44 formats = []
45 for q in qualities:
46 formats.append({
47 'url': http_template % q,
48 'ext': 'mp4',
49 'format_id': q,
50 })
51
52 return {
53 'id': data_video['guid'],
54 'title': compat_urllib_parse.unquote(data_video['title']),
55 'formats': formats,
56 'description': get_meta_content('description', webpage),
57 'thumbnail': self._og_search_thumbnail(webpage),
58 }